diff --git a/Makefile b/Makefile
index 3fd29ad3..98791693 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 PYTHON ?= python3
 
-.PHONY: eval eval-suite failure-regression-check package-check package-failure-check snapshot-check validate lint test clean
+.PHONY: eval eval-suite results-panel failure-regression-check package-check package-failure-check snapshot-check validate lint test clean
 
 eval:
 	$(PYTHON) scripts/trigger_eval.py --description-file evals/improved_description.txt --cases evals/trigger_cases.json --baseline-description-file evals/baseline_description.txt
@@ -8,6 +8,9 @@ eval:
 eval-suite:
 	$(PYTHON) scripts/run_eval_suite.py
 
+results-panel:
+	$(PYTHON) scripts/render_eval_dashboard.py
+
 failure-regression-check:
 	$(PYTHON) tests/verify_failure_regressions.py
 
diff --git a/README.md b/README.md
index b79a5aba..0173f374 100644
--- a/README.md
+++ b/README.md
@@ -46,9 +46,46 @@ make test
 
 ## Results
 
-- `make test` passes locally
-- semantic trigger eval: `0` false positives, `0` false negatives on the current regression set
-- eval suite: train / dev / holdout all pass, with family-based reporting
+The homepage panel below is generated from the current eval suite so the family-level outcome is visible without opening raw JSON.
+
+<!-- BEGIN:EVAL_RESULTS -->
+- regression corpus: `66` prompts across `21` families
+- aggregate result: `0` false positives, `0` false negatives, average precision `1.0`, average recall `1.0`
+- suite status:
+
+| Suite | Cases | FP | FN | Precision | Recall |
+| --- | ---: | ---: | ---: | ---: | ---: |
+| train | 31 | 0 | 0 | 1.0 | 1.0 |
+| dev | 22 | 0 | 0 | 1.0 | 1.0 |
+| holdout | 13 | 0 | 0 | 1.0 | 1.0 |
+
+| Family | Cases | Pass Rate |
+| --- | ---: | ---: |
+| `brainstorm_only` | 2 | 1.0 |
+| `brainstorm_vs_build` | 1 | 1.0 |
+| `complex_multi_asset` | 3 | 1.0 |
+| `document_export_vs_agent_skill` | 4 | 1.0 |
+| `document_only` | 3 | 1.0 |
+| `explain_not_package` | 1 | 1.0 |
+| `explain_only` | 5 | 1.0 |
+| `future_outline_vs_build` | 4 | 1.0 |
+| `iterate_existing_skill` | 5 | 1.0 |
+| `long_context_document_only` | 3 | 1.0 |
+| `long_context_near_neighbor` | 3 | 1.0 |
+| `long_context_summary_only` | 2 | 1.0 |
+| `long_context_trigger` | 4 | 1.0 |
+| `meta_skill_creation` | 1 | 1.0 |
+| `one_off_vs_reusable` | 2 | 1.0 |
+| `package_for_team` | 2 | 1.0 |
+| `paraphrase_trigger` | 5 | 1.0 |
+| `partial_scaffold_not_full_skill` | 4 | 1.0 |
+| `summary_only` | 3 | 1.0 |
+| `translate_only` | 4 | 1.0 |
+| `workflow_to_skill` | 5 | 1.0 |
+
+Full reports: [reports/eval_suite.json](reports/eval_suite.json) and [reports/family_summary.md](reports/family_summary.md)
+<!-- END:EVAL_RESULTS -->
+
 - packaging validation: `openai`, `claude`, and `generic` targets pass contract checks
 - packaging failure fixtures: invalid metadata, invalid YAML, and unsupported targets fail as expected
 - failure library regressions: anti-pattern families pass automated checks
diff --git a/evals/README.md b/evals/README.md
index a60cc360..829f9340 100644
--- a/evals/README.md
+++ b/evals/README.md
@@ -12,6 +12,7 @@ Contents:
 - `sample_trigger_report.json`: example comparison output using the current recommended threshold
 - `failure-cases.md`: current weak spots and regression targets
 - `packaging_expectations.json`: required packaging behaviors for supported targets
+- `../reports/`: generated suite JSON plus the homepage-visible family summary panel source
 
 Use:
 
@@ -19,6 +20,7 @@ Use:
 python3 scripts/trigger_eval.py --description-file evals/improved_description.txt --cases evals/trigger_cases.json
 python3 scripts/trigger_eval.py --description-file evals/improved_description.txt --cases evals/trigger_cases.json --baseline-description-file evals/baseline_description.txt
 python3 scripts/run_eval_suite.py
+python3 scripts/render_eval_dashboard.py
 python3 tests/verify_failure_regressions.py
 python3 scripts/cross_packager.py . --platform openai --platform claude --expectations evals/packaging_expectations.json --zip
 python3 tests/verify_packager_failures.py
@@ -33,5 +35,7 @@ Regression scope now includes:
 - mixed-intent negatives
 - explicit "do not build a skill" negatives
 - semantic exclusion cases such as one-off, document-only, and future-outline prompts
+- paraphrase families that avoid the original wording while preserving the same trigger intent
+- long-context contamination cases where build intent or no-build intent appears after unrelated setup text
 - family-based reporting across workflow-to-skill, iterate-existing-skill, document-only, one-off, and future-outline cases
 - holdout verification
diff --git a/evals/dev/trigger_cases.json b/evals/dev/trigger_cases.json
index 6dd5da64..e64aacae 100644
--- a/evals/dev/trigger_cases.json
+++ b/evals/dev/trigger_cases.json
@@ -29,6 +29,18 @@
     {
       "text": "Tighten the trigger boundary on this existing skill and prepare it for team distribution.",
       "family": "iterate_existing_skill"
+    },
+    {
+      "text": "Turn the SOP, transcript, and cleanup notes into a maintained skill for the team library.",
+      "family": "paraphrase_trigger"
+    },
+    {
+      "text": "Codify this workflow into a shared capability package and validate the route boundary before distribution.",
+      "family": "paraphrase_trigger"
+    },
+    {
+      "text": "After the long handoff notes below, build a skill package for team reuse. The materials include a transcript, rough notes, and an onboarding flow, and the result should include references, scripts, and validation.",
+      "family": "long_context_trigger"
     }
   ],
   "should_not_trigger": [
@@ -51,6 +63,14 @@
     {
       "text": "Summarize this workflow and list the main points only.",
       "family": "summary_only"
+    },
+    {
+      "text": "This is a long incident write-up. Keep it as documentation only, explain it in simpler language, and do not convert it into a reusable capability.",
+      "family": "long_context_document_only"
+    },
+    {
+      "text": "I pasted a very long process note. For now I only need a recap and a short summary, not a skill package.",
+      "family": "long_context_summary_only"
     }
   ],
   "near_neighbor": [
@@ -73,6 +93,14 @@
     {
       "text": "Polish these notes into a reusable-looking document without turning them into an agent skill.",
       "family": "document_export_vs_agent_skill"
+    },
+    {
+      "text": "Turn the workflow below into a wiki-ready reference document and template only. We may build a skill later, but not now.",
+      "family": "long_context_near_neighbor"
+    },
+    {
+      "text": "Shape this idea for later and produce a future-ready outline, but do not build the skill package yet.",
+      "family": "future_outline_vs_build"
     }
   ]
 }
diff --git a/evals/holdout/trigger_cases.json b/evals/holdout/trigger_cases.json
index 2c1f3bdd..8ad1ea6f 100644
--- a/evals/holdout/trigger_cases.json
+++ b/evals/holdout/trigger_cases.json
@@ -21,6 +21,14 @@
     {
       "text": "Turn this recurring onboarding process into a reusable skill library entry with validation notes.",
       "family": "workflow_to_skill"
+    },
+    {
+      "text": "Codify this quarterly release routine into a reusable skill package with scripts, references, and packaging checks.",
+      "family": "paraphrase_trigger"
+    },
+    {
+      "text": "Below is a noisy transcript plus release notes and prompt history. Ignore the chatter and turn this playbook into an agent capability package for the team library.",
+      "family": "long_context_trigger"
     }
   ],
   "should_not_trigger": [
@@ -31,6 +39,14 @@
     {
       "text": "Explain this release checklist in simpler language; do not package it.",
       "family": "explain_only"
+    },
+    {
+      "text": "Keep this release workflow as documentation only for the wiki and produce a reference document, not for agent execution.",
+      "family": "long_context_document_only"
+    },
+    {
+      "text": "Translate this long runbook into Russian and keep it as documentation only with no skill package.",
+      "family": "translate_only"
     }
   ],
   "near_neighbor": [
@@ -45,6 +61,10 @@
     {
       "text": "Turn this into a document package for the wiki, not an agent skill.",
       "family": "document_export_vs_agent_skill"
+    },
+    {
+      "text": "From the long workflow below, create a template only and a checklist for discussion only. No skill package.",
+      "family": "long_context_near_neighbor"
     }
   ]
 }
diff --git a/evals/sample_trigger_report.json b/evals/sample_trigger_report.json
index f4b4515f..776e426a 100644
--- a/evals/sample_trigger_report.json
+++ b/evals/sample_trigger_report.json
@@ -7,18 +7,18 @@
   "recall": 1.0,
   "bucket_stats": {
     "should_trigger": {
-      "total": 16,
-      "passed": 16,
+      "total": 25,
+      "passed": 25,
       "pass_rate": 1.0
     },
     "should_not_trigger": {
-      "total": 15,
-      "passed": 15,
+      "total": 22,
+      "passed": 22,
       "pass_rate": 1.0
     },
     "near_neighbor": {
-      "total": 14,
-      "passed": 14,
+      "total": 19,
+      "passed": 19,
       "pass_rate": 1.0
     }
   },
@@ -58,6 +58,20 @@
       "false_negatives": 0,
       "pass_rate": 1.0
     },
+    "paraphrase_trigger": {
+      "total": 5,
+      "passed": 5,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "long_context_trigger": {
+      "total": 4,
+      "passed": 4,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
     "explain_only": {
       "total": 5,
       "passed": 5,
@@ -73,8 +87,8 @@
       "pass_rate": 1.0
     },
     "translate_only": {
-      "total": 2,
-      "passed": 2,
+      "total": 4,
+      "passed": 4,
       "false_positives": 0,
       "false_negatives": 0,
       "pass_rate": 1.0
@@ -93,6 +107,20 @@
       "false_negatives": 0,
       "pass_rate": 1.0
     },
+    "long_context_summary_only": {
+      "total": 2,
+      "passed": 2,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "long_context_document_only": {
+      "total": 3,
+      "passed": 3,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
     "one_off_vs_reusable": {
       "total": 2,
       "passed": 2,
@@ -115,8 +143,8 @@
       "pass_rate": 1.0
     },
     "partial_scaffold_not_full_skill": {
-      "total": 3,
-      "passed": 3,
+      "total": 4,
+      "passed": 4,
       "false_positives": 0,
       "false_negatives": 0,
       "pass_rate": 1.0
@@ -129,6 +157,13 @@
       "pass_rate": 1.0
     },
     "future_outline_vs_build": {
+      "total": 4,
+      "passed": 4,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "long_context_near_neighbor": {
       "total": 3,
       "passed": 3,
       "false_positives": 0,
@@ -708,7 +743,8 @@
                 "production-ready"
               ],
               "transform_workflow": [
-                "workflow"
+                "workflow",
+                "workflow fragments"
               ]
             },
             "negative": {}
@@ -912,7 +948,8 @@
                 "validation"
               ],
               "reuse_package": [
-                "reusable"
+                "reusable",
+                "library entry"
               ],
               "transform_workflow": [
                 "process"
@@ -921,6 +958,510 @@
             "negative": {}
           }
         }
+      },
+      {
+        "prompt": "Codify this recurring support escalation workflow into a maintained skill for the ops library.",
+        "family": "paraphrase_trigger",
+        "score": 0.397,
+        "predicted_trigger": true,
+        "expected_trigger": true,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "reuse_package",
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [],
+          "exclusive_negative_concepts": [],
+          "semantic_coverage": 0.364,
+          "support_score": 0,
+          "lexical_support": 0.286,
+          "negative_penalty": 0,
+          "coverage_boost": 0.04,
+          "concept_evidence": {
+            "positive": {
+              "reuse_package": [
+                "ops library",
+                "maintained"
+              ],
+              "transform_workflow": [
+                "workflow"
+              ]
+            },
+            "negative": {}
+          }
+        },
+        "boundary_case": true
+      },
+      {
+        "prompt": "Operationalize this workflow as a reusable skill with validation notes and team library metadata.",
+        "family": "paraphrase_trigger",
+        "score": 0.88,
+        "predicted_trigger": true,
+        "expected_trigger": true,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "build_skill",
+            "eval_optimize",
+            "reuse_package",
+            "team_operationalize",
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [],
+          "exclusive_negative_concepts": [],
+          "semantic_coverage": 0.855,
+          "support_score": 0,
+          "lexical_support": 0.429,
+          "negative_penalty": 0,
+          "coverage_boost": 0.06,
+          "concept_evidence": {
+            "positive": {
+              "build_skill": [
+                "operationalize this workflow as a reusable skill"
+              ],
+              "eval_optimize": [
+                "validation"
+              ],
+              "reuse_package": [
+                "reusable",
+                "team library",
+                "operationalize"
+              ],
+              "team_operationalize": [
+                "team"
+              ],
+              "transform_workflow": [
+                "workflow"
+              ]
+            },
+            "negative": {}
+          }
+        }
+      },
+      {
+        "prompt": "Turn the SOP, transcript, and cleanup notes into a maintained skill for the team library.",
+        "family": "paraphrase_trigger",
+        "score": 0.471,
+        "predicted_trigger": true,
+        "expected_trigger": true,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "reuse_package",
+            "team_operationalize",
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [],
+          "exclusive_negative_concepts": [],
+          "semantic_coverage": 0.4,
+          "support_score": 0,
+          "lexical_support": 0.538,
+          "negative_penalty": 0,
+          "coverage_boost": 0.06,
+          "concept_evidence": {
+            "positive": {
+              "reuse_package": [
+                "team library",
+                "maintained"
+              ],
+              "team_operationalize": [
+                "team"
+              ],
+              "transform_workflow": [
+                "sop",
+                "transcript"
+              ]
+            },
+            "negative": {}
+          }
+        }
+      },
+      {
+        "prompt": "Codify this workflow into a shared capability package and validate the route boundary before distribution.",
+        "family": "paraphrase_trigger",
+        "score": 0.868,
+        "predicted_trigger": true,
+        "expected_trigger": true,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "build_skill",
+            "eval_optimize",
+            "reuse_package",
+            "team_operationalize",
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [],
+          "exclusive_negative_concepts": [],
+          "semantic_coverage": 0.855,
+          "support_score": 0,
+          "lexical_support": 0.267,
+          "negative_penalty": 0,
+          "coverage_boost": 0.06,
+          "concept_evidence": {
+            "positive": {
+              "build_skill": [
+                "codify this workflow"
+              ],
+              "eval_optimize": [
+                "validate",
+                "route boundary"
+              ],
+              "reuse_package": [
+                "package",
+                "distribution",
+                "shared capability"
+              ],
+              "team_operationalize": [
+                "shared",
+                "distribution"
+              ],
+              "transform_workflow": [
+                "workflow"
+              ]
+            },
+            "negative": {}
+          }
+        }
+      },
+      {
+        "prompt": "Codify this quarterly release routine into a reusable skill package with scripts, references, and packaging checks.",
+        "family": "paraphrase_trigger",
+        "score": 0.858,
+        "predicted_trigger": true,
+        "expected_trigger": true,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "build_skill",
+            "eval_optimize",
+            "reuse_package",
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [
+            "multi_asset"
+          ],
+          "matched_negative_concepts": [],
+          "exclusive_negative_concepts": [],
+          "semantic_coverage": 0.818,
+          "support_score": 0.06,
+          "lexical_support": 0.375,
+          "negative_penalty": 0,
+          "coverage_boost": 0.06,
+          "concept_evidence": {
+            "positive": {
+              "build_skill": [
+                "skill package"
+              ],
+              "eval_optimize": [
+                "packaging checks"
+              ],
+              "multi_asset": [
+                "references",
+                "scripts"
+              ],
+              "reuse_package": [
+                "reusable",
+                "package",
+                "packaging"
+              ],
+              "transform_workflow": [
+                "quarterly release routine"
+              ]
+            },
+            "negative": {}
+          }
+        }
+      },
+      {
+        "prompt": "Below are release notes, rough notes, and a transcript from the last handoff. Ignore the noise and turn this runbook into a reusable agent skill with references and scripts so the team can reuse it every quarter.",
+        "family": "long_context_trigger",
+        "score": 0.758,
+        "predicted_trigger": true,
+        "expected_trigger": true,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "build_skill",
+            "reuse_package",
+            "team_operationalize",
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [
+            "multi_asset"
+          ],
+          "matched_negative_concepts": [],
+          "exclusive_negative_concepts": [],
+          "semantic_coverage": 0.709,
+          "support_score": 0.06,
+          "lexical_support": 0.387,
+          "negative_penalty": 0,
+          "coverage_boost": 0.06,
+          "concept_evidence": {
+            "positive": {
+              "build_skill": [
+                "agent skill"
+              ],
+              "multi_asset": [
+                "references",
+                "scripts"
+              ],
+              "reuse_package": [
+                "reusable",
+                "reuse"
+              ],
+              "team_operationalize": [
+                "team"
+              ],
+              "transform_workflow": [
+                "runbook",
+                "rough notes",
+                "transcript",
+                "release notes"
+              ]
+            },
+            "negative": {}
+          }
+        }
+      },
+      {
+        "prompt": "We have a standard operating procedure, checklist, and prompt history scattered across docs. Formalize this process into a reusable capability, add validation, and package it for team reuse.",
+        "family": "long_context_trigger",
+        "score": 0.88,
+        "predicted_trigger": true,
+        "expected_trigger": true,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "build_skill",
+            "eval_optimize",
+            "reuse_package",
+            "team_operationalize",
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [],
+          "exclusive_negative_concepts": [],
+          "semantic_coverage": 0.855,
+          "support_score": 0,
+          "lexical_support": 0.423,
+          "negative_penalty": 0,
+          "coverage_boost": 0.06,
+          "concept_evidence": {
+            "positive": {
+              "build_skill": [
+                "formalize this process into a reusable capability"
+              ],
+              "eval_optimize": [
+                "validation"
+              ],
+              "reuse_package": [
+                "reusable",
+                "reuse",
+                "package",
+                "team reuse"
+              ],
+              "team_operationalize": [
+                "team",
+                "team reuse"
+              ],
+              "transform_workflow": [
+                "process",
+                "checklist",
+                "prompt history",
+                "standard operating procedure"
+              ]
+            },
+            "negative": {}
+          }
+        }
+      },
+      {
+        "prompt": "After the long handoff notes below, build a skill package for team reuse. The materials include a transcript, rough notes, and an onboarding flow, and the result should include references, scripts, and validation.",
+        "family": "long_context_trigger",
+        "score": 0.891,
+        "predicted_trigger": true,
+        "expected_trigger": true,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "build_skill",
+            "eval_optimize",
+            "reuse_package",
+            "team_operationalize",
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [
+            "multi_asset"
+          ],
+          "matched_negative_concepts": [],
+          "exclusive_negative_concepts": [],
+          "semantic_coverage": 0.855,
+          "support_score": 0.06,
+          "lexical_support": 0.37,
+          "negative_penalty": 0,
+          "coverage_boost": 0.06,
+          "concept_evidence": {
+            "positive": {
+              "build_skill": [
+                "build a skill",
+                "skill package"
+              ],
+              "eval_optimize": [
+                "validation"
+              ],
+              "multi_asset": [
+                "references",
+                "scripts"
+              ],
+              "reuse_package": [
+                "reuse",
+                "package",
+                "team reuse"
+              ],
+              "team_operationalize": [
+                "team",
+                "team reuse"
+              ],
+              "transform_workflow": [
+                "rough notes",
+                "transcript",
+                "onboarding flow"
+              ]
+            },
+            "negative": {}
+          }
+        }
+      },
+      {
+        "prompt": "Below is a noisy transcript plus release notes and prompt history. Ignore the chatter and turn this playbook into an agent capability package for the team library.",
+        "family": "long_context_trigger",
+        "score": 0.744,
+        "predicted_trigger": true,
+        "expected_trigger": true,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "build_skill",
+            "reuse_package",
+            "team_operationalize",
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [],
+          "exclusive_negative_concepts": [],
+          "semantic_coverage": 0.709,
+          "support_score": 0,
+          "lexical_support": 0.4,
+          "negative_penalty": 0,
+          "coverage_boost": 0.06,
+          "concept_evidence": {
+            "positive": {
+              "build_skill": [
+                "turn this playbook into an agent capability package"
+              ],
+              "reuse_package": [
+                "package",
+                "team library"
+              ],
+              "team_operationalize": [
+                "team"
+              ],
+              "transform_workflow": [
+                "prompt history",
+                "transcript",
+                "release notes"
+              ]
+            },
+            "negative": {}
+          }
+        }
       }
     ],
     "should_not_trigger": [
@@ -1593,6 +2134,386 @@
             }
           }
         }
+      },
+      {
+        "prompt": "Below is a long SOP, but I only want a summary for leadership and a recap of the main points. Do not build anything reusable.",
+        "family": "long_context_summary_only",
+        "score": 0.0,
+        "predicted_trigger": false,
+        "expected_trigger": false,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "reuse_package",
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [
+            "no_build_directive",
+            "summarize_only"
+          ],
+          "exclusive_negative_concepts": [
+            "no_build_directive",
+            "summarize_only"
+          ],
+          "semantic_coverage": 0.364,
+          "support_score": 0,
+          "lexical_support": 0.19,
+          "negative_penalty": 0.72,
+          "coverage_boost": 0.04,
+          "concept_evidence": {
+            "positive": {
+              "reuse_package": [
+                "reusable"
+              ],
+              "transform_workflow": [
+                "sop"
+              ]
+            },
+            "negative": {
+              "no_build_directive": [
+                "do not build"
+              ],
+              "summarize_only": [
+                "summary",
+                "only want a summary",
+                "recap"
+              ]
+            }
+          }
+        }
+      },
+      {
+        "prompt": "Keep this as documentation only for the knowledge base and rewrite it as a reference document.",
+        "family": "long_context_document_only",
+        "score": 0.0,
+        "predicted_trigger": false,
+        "expected_trigger": false,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [
+            "document_only"
+          ],
+          "exclusive_negative_concepts": [],
+          "semantic_coverage": 0.0,
+          "support_score": 0,
+          "lexical_support": 0.2,
+          "negative_penalty": 0.18,
+          "coverage_boost": 0.0,
+          "concept_evidence": {
+            "positive": {},
+            "negative": {
+              "document_only": [
+                "document",
+                "reference document",
+                "knowledge base"
+              ]
+            }
+          }
+        }
+      },
+      {
+        "prompt": "Translate this long onboarding flow into French and keep it as documentation only with no skill package.",
+        "family": "translate_only",
+        "score": 0.0,
+        "predicted_trigger": false,
+        "expected_trigger": false,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "build_skill",
+            "reuse_package",
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [
+            "no_build_directive",
+            "translate_only"
+          ],
+          "exclusive_negative_concepts": [
+            "no_build_directive",
+            "translate_only"
+          ],
+          "semantic_coverage": 0.673,
+          "support_score": 0,
+          "lexical_support": 0.235,
+          "negative_penalty": 0.77,
+          "coverage_boost": 0.06,
+          "concept_evidence": {
+            "positive": {
+              "build_skill": [
+                "skill package"
+              ],
+              "reuse_package": [
+                "package"
+              ],
+              "transform_workflow": [
+                "onboarding flow"
+              ]
+            },
+            "negative": {
+              "no_build_directive": [
+                "no skill package",
+                "keep it as documentation only"
+              ],
+              "translate_only": [
+                "translate",
+                "into french"
+              ]
+            }
+          }
+        }
+      },
+      {
+        "prompt": "This is a long incident write-up. Keep it as documentation only, explain it in simpler language, and do not convert it into a reusable capability.",
+        "family": "long_context_document_only",
+        "score": 0.0,
+        "predicted_trigger": false,
+        "expected_trigger": false,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "reuse_package"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [
+            "explain_only",
+            "no_build_directive"
+          ],
+          "exclusive_negative_concepts": [
+            "explain_only",
+            "no_build_directive"
+          ],
+          "semantic_coverage": 0.182,
+          "support_score": 0,
+          "lexical_support": 0.182,
+          "negative_penalty": 0.68,
+          "coverage_boost": 0.0,
+          "concept_evidence": {
+            "positive": {
+              "reuse_package": [
+                "reusable"
+              ]
+            },
+            "negative": {
+              "explain_only": [
+                "explain it",
+                "in simpler language"
+              ],
+              "no_build_directive": [
+                "do not convert it into a reusable capability",
+                "keep it as documentation only"
+              ]
+            }
+          }
+        }
+      },
+      {
+        "prompt": "I pasted a very long process note. For now I only need a recap and a short summary, not a skill package.",
+        "family": "long_context_summary_only",
+        "score": 0.257,
+        "predicted_trigger": false,
+        "expected_trigger": false,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "build_skill",
+            "reuse_package",
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [
+            "summarize_only"
+          ],
+          "exclusive_negative_concepts": [
+            "summarize_only"
+          ],
+          "semantic_coverage": 0.673,
+          "support_score": 0,
+          "lexical_support": 0.353,
+          "negative_penalty": 0.3,
+          "coverage_boost": 0.06,
+          "concept_evidence": {
+            "positive": {
+              "build_skill": [
+                "skill package"
+              ],
+              "reuse_package": [
+                "package"
+              ],
+              "transform_workflow": [
+                "process"
+              ]
+            },
+            "negative": {
+              "summarize_only": [
+                "summary",
+                "recap"
+              ]
+            }
+          }
+        },
+        "boundary_case": true
+      },
+      {
+        "prompt": "Keep this release workflow as documentation only for the wiki and produce a reference document, not for agent execution.",
+        "family": "long_context_document_only",
+        "score": 0.0,
+        "predicted_trigger": false,
+        "expected_trigger": false,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [
+            "document_only",
+            "no_build_directive"
+          ],
+          "exclusive_negative_concepts": [
+            "no_build_directive"
+          ],
+          "semantic_coverage": 0.182,
+          "support_score": 0,
+          "lexical_support": 0.222,
+          "negative_penalty": 0.6,
+          "coverage_boost": 0.0,
+          "concept_evidence": {
+            "positive": {
+              "transform_workflow": [
+                "workflow"
+              ]
+            },
+            "negative": {
+              "document_only": [
+                "document",
+                "wiki",
+                "reference document"
+              ],
+              "no_build_directive": [
+                "not for agent execution"
+              ]
+            }
+          }
+        }
+      },
+      {
+        "prompt": "Translate this long runbook into Russian and keep it as documentation only with no skill package.",
+        "family": "translate_only",
+        "score": 0.0,
+        "predicted_trigger": false,
+        "expected_trigger": false,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "build_skill",
+            "reuse_package",
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [
+            "no_build_directive",
+            "translate_only"
+          ],
+          "exclusive_negative_concepts": [
+            "no_build_directive",
+            "translate_only"
+          ],
+          "semantic_coverage": 0.673,
+          "support_score": 0,
+          "lexical_support": 0.25,
+          "negative_penalty": 0.77,
+          "coverage_boost": 0.06,
+          "concept_evidence": {
+            "positive": {
+              "build_skill": [
+                "skill package"
+              ],
+              "reuse_package": [
+                "package"
+              ],
+              "transform_workflow": [
+                "runbook"
+              ]
+            },
+            "negative": {
+              "no_build_directive": [
+                "no skill package",
+                "keep it as documentation only"
+              ],
+              "translate_only": [
+                "translate",
+                "into russian"
+              ]
+            }
+          }
+        }
       }
     ],
     "near_neighbor": [
@@ -2062,15 +2983,17 @@
           ],
           "extra_positive_concepts": [],
           "matched_negative_concepts": [
+            "future_outline",
             "no_build_directive"
           ],
           "exclusive_negative_concepts": [
+            "future_outline",
             "no_build_directive"
           ],
           "semantic_coverage": 0.327,
           "support_score": 0,
           "lexical_support": 0.286,
-          "negative_penalty": 0.42,
+          "negative_penalty": 0.64,
           "coverage_boost": 0.04,
           "concept_evidence": {
             "positive": {
@@ -2082,6 +3005,9 @@
               ]
             },
             "negative": {
+              "future_outline": [
+                "future-ready outline"
+              ],
               "no_build_directive": [
                 "do not build"
               ]
@@ -2297,19 +3223,296 @@
             }
           }
         }
+      },
+      {
+        "prompt": "We may convert this workflow later, but for now keep it as documentation only and produce a reference document.",
+        "family": "long_context_near_neighbor",
+        "score": 0.0,
+        "predicted_trigger": false,
+        "expected_trigger": false,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [
+            "document_only",
+            "no_build_directive"
+          ],
+          "exclusive_negative_concepts": [
+            "no_build_directive"
+          ],
+          "semantic_coverage": 0.182,
+          "support_score": 0,
+          "lexical_support": 0.158,
+          "negative_penalty": 0.6,
+          "coverage_boost": 0.0,
+          "concept_evidence": {
+            "positive": {
+              "transform_workflow": [
+                "workflow"
+              ]
+            },
+            "negative": {
+              "document_only": [
+                "document",
+                "reference document"
+              ],
+              "no_build_directive": [
+                "keep it as documentation only"
+              ]
+            }
+          }
+        }
+      },
+      {
+        "prompt": "Draft a template only from this process and stop short of making a full skill package.",
+        "family": "partial_scaffold_not_full_skill",
+        "score": 0.0,
+        "predicted_trigger": false,
+        "expected_trigger": false,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "build_skill",
+            "reuse_package",
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [
+            "document_only",
+            "no_build_directive"
+          ],
+          "exclusive_negative_concepts": [
+            "no_build_directive"
+          ],
+          "semantic_coverage": 0.673,
+          "support_score": 0,
+          "lexical_support": 0.4,
+          "negative_penalty": 0.6,
+          "coverage_boost": 0.06,
+          "concept_evidence": {
+            "positive": {
+              "build_skill": [
+                "skill package"
+              ],
+              "reuse_package": [
+                "package"
+              ],
+              "transform_workflow": [
+                "process"
+              ]
+            },
+            "negative": {
+              "document_only": [
+                "template only"
+              ],
+              "no_build_directive": [
+                "stop short of making a full skill"
+              ]
+            }
+          }
+        }
+      },
+      {
+        "prompt": "Turn the workflow below into a wiki-ready reference document and template only. We may build a skill later, but not now.",
+        "family": "long_context_near_neighbor",
+        "score": 0.328,
+        "predicted_trigger": false,
+        "expected_trigger": false,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "build_skill",
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [
+            "document_only"
+          ],
+          "exclusive_negative_concepts": [],
+          "semantic_coverage": 0.491,
+          "support_score": 0,
+          "lexical_support": 0.2,
+          "negative_penalty": 0.18,
+          "coverage_boost": 0.04,
+          "concept_evidence": {
+            "positive": {
+              "build_skill": [
+                "build a skill"
+              ],
+              "transform_workflow": [
+                "workflow"
+              ]
+            },
+            "negative": {
+              "document_only": [
+                "document",
+                "wiki",
+                "reference document",
+                "template only"
+              ]
+            }
+          }
+        },
+        "boundary_case": true
+      },
+      {
+        "prompt": "Shape this idea for later and produce a future-ready outline, but do not build the skill package yet.",
+        "family": "future_outline_vs_build",
+        "score": 0.0,
+        "predicted_trigger": false,
+        "expected_trigger": false,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "build_skill",
+            "reuse_package"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [
+            "future_outline",
+            "no_build_directive"
+          ],
+          "exclusive_negative_concepts": [
+            "future_outline",
+            "no_build_directive"
+          ],
+          "semantic_coverage": 0.491,
+          "support_score": 0,
+          "lexical_support": 0.278,
+          "negative_penalty": 0.64,
+          "coverage_boost": 0.04,
+          "concept_evidence": {
+            "positive": {
+              "build_skill": [
+                "skill package"
+              ],
+              "reuse_package": [
+                "package"
+              ]
+            },
+            "negative": {
+              "future_outline": [
+                "for later",
+                "future-ready outline"
+              ],
+              "no_build_directive": [
+                "do not build"
+              ]
+            }
+          }
+        }
+      },
+      {
+        "prompt": "From the long workflow below, create a template only and a checklist for discussion only. No skill package.",
+        "family": "long_context_near_neighbor",
+        "score": 0.0,
+        "predicted_trigger": false,
+        "expected_trigger": false,
+        "passed": true,
+        "score_detail": {
+          "mode": "semantic-intent",
+          "desired_positive_concepts": [
+            "build_skill",
+            "transform_workflow",
+            "reuse_package",
+            "eval_optimize",
+            "iterate_existing_skill",
+            "team_operationalize"
+          ],
+          "matched_desired_concepts": [
+            "build_skill",
+            "reuse_package",
+            "transform_workflow"
+          ],
+          "extra_positive_concepts": [],
+          "matched_negative_concepts": [
+            "document_only",
+            "no_build_directive"
+          ],
+          "exclusive_negative_concepts": [
+            "no_build_directive"
+          ],
+          "semantic_coverage": 0.673,
+          "support_score": 0,
+          "lexical_support": 0.375,
+          "negative_penalty": 0.6,
+          "coverage_boost": 0.06,
+          "concept_evidence": {
+            "positive": {
+              "build_skill": [
+                "skill package"
+              ],
+              "reuse_package": [
+                "package"
+              ],
+              "transform_workflow": [
+                "workflow",
+                "checklist"
+              ]
+            },
+            "negative": {
+              "document_only": [
+                "template only"
+              ],
+              "no_build_directive": [
+                "no skill package",
+                "discussion only"
+              ]
+            }
+          }
+        }
       }
     ]
   },
   "comparison": {
-    "baseline_false_positives": 0,
+    "baseline_false_positives": 1,
     "baseline_false_negatives": 2,
     "improved_false_positives": 0,
     "improved_false_negatives": 0,
-    "false_positive_delta": 0,
+    "false_positive_delta": -1,
     "false_negative_delta": -2,
-    "baseline_precision": 1.0,
+    "baseline_precision": 0.958,
     "improved_precision": 1.0,
-    "baseline_recall": 0.875,
+    "baseline_recall": 0.92,
     "improved_recall": 1.0
   }
 }
diff --git a/evals/semantic_config.json b/evals/semantic_config.json
index f698c0a3..3bc1f852 100644
--- a/evals/semantic_config.json
+++ b/evals/semantic_config.json
@@ -19,7 +19,13 @@
         "meta skill",
         "meta-skill",
         "turn this into a skill",
-        "turn all of that into one reusable skill package"
+        "turn all of that into one reusable skill package",
+        "codify this workflow",
+        "codify this routine",
+        "operationalize this workflow as a reusable skill",
+        "formalize this process into a reusable capability",
+        "turn this playbook into an agent capability package",
+        "convert this into a maintained skill"
       ]
     },
     "transform_workflow": {
@@ -33,7 +39,15 @@
         "operations checklist",
         "internal process note",
         "existing skill draft",
-        "rough notes"
+        "rough notes",
+        "standard operating procedure",
+        "sop",
+        "transcript",
+        "workflow fragments",
+        "release notes",
+        "onboarding flow",
+        "support escalation routine",
+        "quarterly release routine"
       ]
     },
     "reuse_package": {
@@ -47,7 +61,13 @@
         "share it with the team",
         "team reuse",
         "internal workflows",
-        "production-ready"
+        "production-ready",
+        "library entry",
+        "shared capability",
+        "team library",
+        "ops library",
+        "maintained",
+        "operationalize"
       ]
     },
     "eval_optimize": {
@@ -60,7 +80,12 @@
         "benchmark",
         "validation",
         "validate",
-        "packaging checks"
+        "packaging checks",
+        "false positives",
+        "false negatives",
+        "stress test",
+        "route boundary",
+        "hardening"
       ]
     },
     "iterate_existing_skill": {
@@ -73,7 +98,11 @@
         "optimize skill triggering",
         "package this skill",
         "sharing it with the team",
-        "before sharing it with the team"
+        "before sharing it with the team",
+        "tighten the boundary",
+        "revise this skill",
+        "draft skill",
+        "harden this skill for library reuse"
       ]
     },
     "multi_asset": {
@@ -172,7 +201,12 @@
         "not a skill yet",
         "plain note",
         "keep it as a plain note",
-        "no packaging needed"
+        "no packaging needed",
+        "not for agent execution",
+        "no skill package",
+        "do not convert it into a reusable capability",
+        "keep it as documentation only",
+        "discussion only"
       ]
     },
     "document_only": {
@@ -187,7 +221,10 @@
         "article",
         "blog title",
         "headline",
-        "landing page"
+        "landing page",
+        "reference document",
+        "knowledge base",
+        "template only"
       ]
     },
     "future_outline": {
@@ -197,7 +234,10 @@
         "future skill",
         "possible future skill",
         "before we decide whether to build",
-        "outline for a possible future skill"
+        "outline for a possible future skill",
+        "maybe later",
+        "for later",
+        "future-ready outline"
       ]
     }
   }
diff --git a/evals/train/trigger_cases.json b/evals/train/trigger_cases.json
index a439d64d..0bfd2c10 100644
--- a/evals/train/trigger_cases.json
+++ b/evals/train/trigger_cases.json
@@ -41,6 +41,22 @@
     {
       "text": "Standardize this recurring workflow as a shareable skill package with references.",
       "family": "package_for_team"
+    },
+    {
+      "text": "Codify this recurring support escalation workflow into a maintained skill for the ops library.",
+      "family": "paraphrase_trigger"
+    },
+    {
+      "text": "Operationalize this workflow as a reusable skill with validation notes and team library metadata.",
+      "family": "paraphrase_trigger"
+    },
+    {
+      "text": "Below are release notes, rough notes, and a transcript from the last handoff. Ignore the noise and turn this runbook into a reusable agent skill with references and scripts so the team can reuse it every quarter.",
+      "family": "long_context_trigger"
+    },
+    {
+      "text": "We have a standard operating procedure, checklist, and prompt history scattered across docs. Formalize this process into a reusable capability, add validation, and package it for team reuse.",
+      "family": "long_context_trigger"
     }
   ],
   "should_not_trigger": [
@@ -75,6 +91,18 @@
     {
       "text": "Explain the difference between a runbook and a workflow.",
       "family": "explain_only"
+    },
+    {
+      "text": "Below is a long SOP, but I only want a summary for leadership and a recap of the main points. Do not build anything reusable.",
+      "family": "long_context_summary_only"
+    },
+    {
+      "text": "Keep this as documentation only for the knowledge base and rewrite it as a reference document.",
+      "family": "long_context_document_only"
+    },
+    {
+      "text": "Translate this long onboarding flow into French and keep it as documentation only with no skill package.",
+      "family": "translate_only"
     }
   ],
   "near_neighbor": [
@@ -101,6 +129,14 @@
     {
       "text": "Create a reusable-looking checklist, but keep it as a plain note instead of a skill.",
       "family": "partial_scaffold_not_full_skill"
+    },
+    {
+      "text": "We may convert this workflow later, but for now keep it as documentation only and produce a reference document.",
+      "family": "long_context_near_neighbor"
+    },
+    {
+      "text": "Draft a template only from this process and stop short of making a full skill package.",
+      "family": "partial_scaffold_not_full_skill"
     }
   ]
 }
diff --git a/evals/trigger_cases.json b/evals/trigger_cases.json
index a40816d0..1f54b9aa 100644
--- a/evals/trigger_cases.json
+++ b/evals/trigger_cases.json
@@ -73,6 +73,42 @@
     {
       "text": "Turn this recurring onboarding process into a reusable skill library entry with validation notes.",
       "family": "workflow_to_skill"
+    },
+    {
+      "text": "Codify this recurring support escalation workflow into a maintained skill for the ops library.",
+      "family": "paraphrase_trigger"
+    },
+    {
+      "text": "Operationalize this workflow as a reusable skill with validation notes and team library metadata.",
+      "family": "paraphrase_trigger"
+    },
+    {
+      "text": "Turn the SOP, transcript, and cleanup notes into a maintained skill for the team library.",
+      "family": "paraphrase_trigger"
+    },
+    {
+      "text": "Codify this workflow into a shared capability package and validate the route boundary before distribution.",
+      "family": "paraphrase_trigger"
+    },
+    {
+      "text": "Codify this quarterly release routine into a reusable skill package with scripts, references, and packaging checks.",
+      "family": "paraphrase_trigger"
+    },
+    {
+      "text": "Below are release notes, rough notes, and a transcript from the last handoff. Ignore the noise and turn this runbook into a reusable agent skill with references and scripts so the team can reuse it every quarter.",
+      "family": "long_context_trigger"
+    },
+    {
+      "text": "We have a standard operating procedure, checklist, and prompt history scattered across docs. Formalize this process into a reusable capability, add validation, and package it for team reuse.",
+      "family": "long_context_trigger"
+    },
+    {
+      "text": "After the long handoff notes below, build a skill package for team reuse. The materials include a transcript, rough notes, and an onboarding flow, and the result should include references, scripts, and validation.",
+      "family": "long_context_trigger"
+    },
+    {
+      "text": "Below is a noisy transcript plus release notes and prompt history. Ignore the chatter and turn this playbook into an agent capability package for the team library.",
+      "family": "long_context_trigger"
     }
   ],
   "should_not_trigger": [
@@ -135,6 +171,34 @@
     {
       "text": "Explain this release checklist in simpler language; do not package it.",
       "family": "explain_only"
+    },
+    {
+      "text": "Below is a long SOP, but I only want a summary for leadership and a recap of the main points. Do not build anything reusable.",
+      "family": "long_context_summary_only"
+    },
+    {
+      "text": "Keep this as documentation only for the knowledge base and rewrite it as a reference document.",
+      "family": "long_context_document_only"
+    },
+    {
+      "text": "Translate this long onboarding flow into French and keep it as documentation only with no skill package.",
+      "family": "translate_only"
+    },
+    {
+      "text": "This is a long incident write-up. Keep it as documentation only, explain it in simpler language, and do not convert it into a reusable capability.",
+      "family": "long_context_document_only"
+    },
+    {
+      "text": "I pasted a very long process note. For now I only need a recap and a short summary, not a skill package.",
+      "family": "long_context_summary_only"
+    },
+    {
+      "text": "Keep this release workflow as documentation only for the wiki and produce a reference document, not for agent execution.",
+      "family": "long_context_document_only"
+    },
+    {
+      "text": "Translate this long runbook into Russian and keep it as documentation only with no skill package.",
+      "family": "translate_only"
     }
   ],
   "near_neighbor": [
@@ -193,6 +257,26 @@
     {
       "text": "Turn this into a document package for the wiki, not an agent skill.",
       "family": "document_export_vs_agent_skill"
+    },
+    {
+      "text": "We may convert this workflow later, but for now keep it as documentation only and produce a reference document.",
+      "family": "long_context_near_neighbor"
+    },
+    {
+      "text": "Draft a template only from this process and stop short of making a full skill package.",
+      "family": "partial_scaffold_not_full_skill"
+    },
+    {
+      "text": "Turn the workflow below into a wiki-ready reference document and template only. We may build a skill later, but not now.",
+      "family": "long_context_near_neighbor"
+    },
+    {
+      "text": "Shape this idea for later and produce a future-ready outline, but do not build the skill package yet.",
+      "family": "future_outline_vs_build"
+    },
+    {
+      "text": "From the long workflow below, create a template only and a checklist for discussion only. No skill package.",
+      "family": "long_context_near_neighbor"
     }
   ]
 }
diff --git a/reports/eval_suite.json b/reports/eval_suite.json
new file mode 100644
index 00000000..1ba4b2d0
--- /dev/null
+++ b/reports/eval_suite.json
@@ -0,0 +1,3947 @@
+{
+  "summary": {
+    "suite_count": 3,
+    "total_cases": 66,
+    "family_count": 21,
+    "false_positives": 0,
+    "false_negatives": 0,
+    "average_precision": 1.0,
+    "average_recall": 1.0
+  },
+  "family_summary": {
+    "workflow_to_skill": {
+      "total": 5,
+      "passed": 5,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "iterate_existing_skill": {
+      "total": 5,
+      "passed": 5,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "package_for_team": {
+      "total": 2,
+      "passed": 2,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "meta_skill_creation": {
+      "total": 1,
+      "passed": 1,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "paraphrase_trigger": {
+      "total": 5,
+      "passed": 5,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "long_context_trigger": {
+      "total": 4,
+      "passed": 4,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "explain_only": {
+      "total": 5,
+      "passed": 5,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "summary_only": {
+      "total": 3,
+      "passed": 3,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "translate_only": {
+      "total": 4,
+      "passed": 4,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "document_only": {
+      "total": 3,
+      "passed": 3,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "long_context_summary_only": {
+      "total": 2,
+      "passed": 2,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "long_context_document_only": {
+      "total": 3,
+      "passed": 3,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "one_off_vs_reusable": {
+      "total": 2,
+      "passed": 2,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "brainstorm_vs_build": {
+      "total": 1,
+      "passed": 1,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "document_export_vs_agent_skill": {
+      "total": 4,
+      "passed": 4,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "partial_scaffold_not_full_skill": {
+      "total": 4,
+      "passed": 4,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "long_context_near_neighbor": {
+      "total": 3,
+      "passed": 3,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "complex_multi_asset": {
+      "total": 3,
+      "passed": 3,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "brainstorm_only": {
+      "total": 2,
+      "passed": 2,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "explain_not_package": {
+      "total": 1,
+      "passed": 1,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    },
+    "future_outline_vs_build": {
+      "total": 4,
+      "passed": 4,
+      "false_positives": 0,
+      "false_negatives": 0,
+      "pass_rate": 1.0
+    }
+  },
+  "suites": {
+    "train": {
+      "threshold": 0.33,
+      "threshold_explanation": "Prompts at or above the threshold are treated as trigger matches. Scores are driven primarily by semantic intent coverage: packaging intent, workflow-to-skill transformation intent, reuse/distribution intent, and eval intent. Explicit exclusions such as summary-only, translation-only, one-off, document-only, or do-not-build directives apply direct penalties and can override otherwise similar wording.",
+      "false_positives": 0,
+      "false_negatives": 0,
+      "precision": 1.0,
+      "recall": 1.0,
+      "bucket_stats": {
+        "should_trigger": {
+          "total": 12,
+          "passed": 12,
+          "pass_rate": 1.0
+        },
+        "should_not_trigger": {
+          "total": 11,
+          "passed": 11,
+          "pass_rate": 1.0
+        },
+        "near_neighbor": {
+          "total": 8,
+          "passed": 8,
+          "pass_rate": 1.0
+        }
+      },
+      "family_stats": {
+        "workflow_to_skill": {
+          "total": 3,
+          "passed": 3,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "iterate_existing_skill": {
+          "total": 2,
+          "passed": 2,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "package_for_team": {
+          "total": 2,
+          "passed": 2,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "meta_skill_creation": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "paraphrase_trigger": {
+          "total": 2,
+          "passed": 2,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "long_context_trigger": {
+          "total": 2,
+          "passed": 2,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "explain_only": {
+          "total": 3,
+          "passed": 3,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "summary_only": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "translate_only": {
+          "total": 2,
+          "passed": 2,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "document_only": {
+          "total": 3,
+          "passed": 3,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "long_context_summary_only": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "long_context_document_only": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "one_off_vs_reusable": {
+          "total": 2,
+          "passed": 2,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "brainstorm_vs_build": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "document_export_vs_agent_skill": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "partial_scaffold_not_full_skill": {
+          "total": 3,
+          "passed": 3,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "long_context_near_neighbor": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        }
+      },
+      "misfires": [],
+      "results": {
+        "should_trigger": [
+          {
+            "prompt": "Create a skill from this repeated workflow.",
+            "family": "workflow_to_skill",
+            "score": 0.549,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.491,
+              "support_score": 0,
+              "lexical_support": 0.714,
+              "negative_penalty": 0,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "create a skill"
+                  ],
+                  "transform_workflow": [
+                    "workflow"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Turn this runbook into a reusable agent skill.",
+            "family": "workflow_to_skill",
+            "score": 0.729,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.673,
+              "support_score": 0,
+              "lexical_support": 0.625,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "agent skill"
+                  ],
+                  "reuse_package": [
+                    "reusable"
+                  ],
+                  "transform_workflow": [
+                    "runbook"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Convert this process note into a reusable skill package for the team.",
+            "family": "workflow_to_skill",
+            "score": 0.766,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package",
+                "team_operationalize",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.709,
+              "support_score": 0,
+              "lexical_support": 0.667,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "skill package"
+                  ],
+                  "reuse_package": [
+                    "reusable",
+                    "package"
+                  ],
+                  "team_operationalize": [
+                    "team"
+                  ],
+                  "transform_workflow": [
+                    "process"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Improve this skill description and add evals.",
+            "family": "iterate_existing_skill",
+            "score": 0.353,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "eval_optimize",
+                "iterate_existing_skill"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.291,
+              "support_score": 0,
+              "lexical_support": 0.571,
+              "negative_penalty": 0,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "eval_optimize": [
+                    "evals"
+                  ],
+                  "iterate_existing_skill": [
+                    "this skill",
+                    "skill description"
+                  ]
+                },
+                "negative": {}
+              }
+            },
+            "boundary_case": true
+          },
+          {
+            "prompt": "Refactor this prompt into a proper skill package.",
+            "family": "iterate_existing_skill",
+            "score": 0.532,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.491,
+              "support_score": 0,
+              "lexical_support": 0.5,
+              "negative_penalty": 0,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "skill package"
+                  ],
+                  "reuse_package": [
+                    "package"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Package this skill for team reuse.",
+            "family": "package_for_team",
+            "score": 0.448,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "iterate_existing_skill",
+                "reuse_package",
+                "team_operationalize"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.364,
+              "support_score": 0,
+              "lexical_support": 0.667,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "iterate_existing_skill": [
+                    "this skill",
+                    "package this skill"
+                  ],
+                  "reuse_package": [
+                    "reuse",
+                    "package",
+                    "team reuse"
+                  ],
+                  "team_operationalize": [
+                    "team",
+                    "team reuse"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Create a meta-skill for packaging internal workflows.",
+            "family": "meta_skill_creation",
+            "score": 0.591,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package",
+                "team_operationalize"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.527,
+              "support_score": 0,
+              "lexical_support": 0.571,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "meta skill",
+                    "meta-skill"
+                  ],
+                  "reuse_package": [
+                    "packaging",
+                    "internal workflows"
+                  ],
+                  "team_operationalize": [
+                    "internal"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Standardize this recurring workflow as a shareable skill package with references.",
+            "family": "package_for_team",
+            "score": 0.749,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package",
+                "team_operationalize",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [
+                "multi_asset"
+              ],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.709,
+              "support_score": 0.06,
+              "lexical_support": 0.273,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "skill package"
+                  ],
+                  "multi_asset": [
+                    "references"
+                  ],
+                  "reuse_package": [
+                    "package"
+                  ],
+                  "team_operationalize": [
+                    "standardize"
+                  ],
+                  "transform_workflow": [
+                    "workflow"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Codify this recurring support escalation workflow into a maintained skill for the ops library.",
+            "family": "paraphrase_trigger",
+            "score": 0.397,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.364,
+              "support_score": 0,
+              "lexical_support": 0.286,
+              "negative_penalty": 0,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "reuse_package": [
+                    "ops library",
+                    "maintained"
+                  ],
+                  "transform_workflow": [
+                    "workflow"
+                  ]
+                },
+                "negative": {}
+              }
+            },
+            "boundary_case": true
+          },
+          {
+            "prompt": "Operationalize this workflow as a reusable skill with validation notes and team library metadata.",
+            "family": "paraphrase_trigger",
+            "score": 0.88,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "eval_optimize",
+                "reuse_package",
+                "team_operationalize",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.855,
+              "support_score": 0,
+              "lexical_support": 0.429,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "operationalize this workflow as a reusable skill"
+                  ],
+                  "eval_optimize": [
+                    "validation"
+                  ],
+                  "reuse_package": [
+                    "reusable",
+                    "team library",
+                    "operationalize"
+                  ],
+                  "team_operationalize": [
+                    "team"
+                  ],
+                  "transform_workflow": [
+                    "workflow"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Below are release notes, rough notes, and a transcript from the last handoff. Ignore the noise and turn this runbook into a reusable agent skill with references and scripts so the team can reuse it every quarter.",
+            "family": "long_context_trigger",
+            "score": 0.758,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package",
+                "team_operationalize",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [
+                "multi_asset"
+              ],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.709,
+              "support_score": 0.06,
+              "lexical_support": 0.387,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "agent skill"
+                  ],
+                  "multi_asset": [
+                    "references",
+                    "scripts"
+                  ],
+                  "reuse_package": [
+                    "reusable",
+                    "reuse"
+                  ],
+                  "team_operationalize": [
+                    "team"
+                  ],
+                  "transform_workflow": [
+                    "runbook",
+                    "rough notes",
+                    "transcript",
+                    "release notes"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "We have a standard operating procedure, checklist, and prompt history scattered across docs. Formalize this process into a reusable capability, add validation, and package it for team reuse.",
+            "family": "long_context_trigger",
+            "score": 0.88,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "eval_optimize",
+                "reuse_package",
+                "team_operationalize",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.855,
+              "support_score": 0,
+              "lexical_support": 0.423,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "formalize this process into a reusable capability"
+                  ],
+                  "eval_optimize": [
+                    "validation"
+                  ],
+                  "reuse_package": [
+                    "reusable",
+                    "reuse",
+                    "package",
+                    "team reuse"
+                  ],
+                  "team_operationalize": [
+                    "team",
+                    "team reuse"
+                  ],
+                  "transform_workflow": [
+                    "process",
+                    "checklist",
+                    "prompt history",
+                    "standard operating procedure"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          }
+        ],
+        "should_not_trigger": [
+          {
+            "prompt": "Explain what a workflow is.",
+            "family": "explain_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "explain_only"
+              ],
+              "exclusive_negative_concepts": [
+                "explain_only"
+              ],
+              "semantic_coverage": 0.182,
+              "support_score": 0,
+              "lexical_support": 0.2,
+              "negative_penalty": 0.26,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {
+                  "transform_workflow": [
+                    "workflow"
+                  ]
+                },
+                "negative": {
+                  "explain_only": [
+                    "explain what"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Just explain what a skill is.",
+            "family": "explain_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "explain_only"
+              ],
+              "exclusive_negative_concepts": [
+                "explain_only"
+              ],
+              "semantic_coverage": 0.0,
+              "support_score": 0,
+              "lexical_support": 0.333,
+              "negative_penalty": 0.26,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {},
+                "negative": {
+                  "explain_only": [
+                    "explain what",
+                    "just explain"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Summarize this random note.",
+            "family": "summary_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "summarize_only"
+              ],
+              "exclusive_negative_concepts": [
+                "summarize_only"
+              ],
+              "semantic_coverage": 0.0,
+              "support_score": 0,
+              "lexical_support": 0.0,
+              "negative_penalty": 0.3,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {},
+                "negative": {
+                  "summarize_only": [
+                    "summarize"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Translate this README into Japanese.",
+            "family": "translate_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "document_only",
+                "translate_only"
+              ],
+              "exclusive_negative_concepts": [
+                "translate_only"
+              ],
+              "semantic_coverage": 0.0,
+              "support_score": 0,
+              "lexical_support": 0.25,
+              "negative_penalty": 0.53,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {},
+                "negative": {
+                  "document_only": [
+                    "readme"
+                  ],
+                  "translate_only": [
+                    "translate",
+                    "into japanese"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Write a product headline for this landing page.",
+            "family": "document_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "document_only"
+              ],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.0,
+              "support_score": 0,
+              "lexical_support": 0.25,
+              "negative_penalty": 0.18,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {},
+                "negative": {
+                  "document_only": [
+                    "headline",
+                    "landing page"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Draft a blog title for this article.",
+            "family": "document_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "document_only"
+              ],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.0,
+              "support_score": 0,
+              "lexical_support": 0.286,
+              "negative_penalty": 0.18,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {},
+                "negative": {
+                  "document_only": [
+                    "article",
+                    "blog title"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Rewrite this paragraph more clearly, but do not package anything.",
+            "family": "document_only",
+            "score": 0.175,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "reuse_package"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.182,
+              "support_score": 0,
+              "lexical_support": 0.1,
+              "negative_penalty": 0,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {
+                  "reuse_package": [
+                    "package"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Explain the difference between a runbook and a workflow.",
+            "family": "explain_only",
+            "score": 0.187,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.182,
+              "support_score": 0,
+              "lexical_support": 0.25,
+              "negative_penalty": 0,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {
+                  "transform_workflow": [
+                    "workflow",
+                    "runbook"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Below is a long SOP, but I only want a summary for leadership and a recap of the main points. Do not build anything reusable.",
+            "family": "long_context_summary_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "no_build_directive",
+                "summarize_only"
+              ],
+              "exclusive_negative_concepts": [
+                "no_build_directive",
+                "summarize_only"
+              ],
+              "semantic_coverage": 0.364,
+              "support_score": 0,
+              "lexical_support": 0.19,
+              "negative_penalty": 0.72,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "reuse_package": [
+                    "reusable"
+                  ],
+                  "transform_workflow": [
+                    "sop"
+                  ]
+                },
+                "negative": {
+                  "no_build_directive": [
+                    "do not build"
+                  ],
+                  "summarize_only": [
+                    "summary",
+                    "only want a summary",
+                    "recap"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Keep this as documentation only for the knowledge base and rewrite it as a reference document.",
+            "family": "long_context_document_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "document_only"
+              ],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.0,
+              "support_score": 0,
+              "lexical_support": 0.2,
+              "negative_penalty": 0.18,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {},
+                "negative": {
+                  "document_only": [
+                    "document",
+                    "reference document",
+                    "knowledge base"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Translate this long onboarding flow into French and keep it as documentation only with no skill package.",
+            "family": "translate_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "no_build_directive",
+                "translate_only"
+              ],
+              "exclusive_negative_concepts": [
+                "no_build_directive",
+                "translate_only"
+              ],
+              "semantic_coverage": 0.673,
+              "support_score": 0,
+              "lexical_support": 0.235,
+              "negative_penalty": 0.77,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "skill package"
+                  ],
+                  "reuse_package": [
+                    "package"
+                  ],
+                  "transform_workflow": [
+                    "onboarding flow"
+                  ]
+                },
+                "negative": {
+                  "no_build_directive": [
+                    "no skill package",
+                    "keep it as documentation only"
+                  ],
+                  "translate_only": [
+                    "translate",
+                    "into french"
+                  ]
+                }
+              }
+            }
+          }
+        ],
+        "near_neighbor": [
+          {
+            "prompt": "Create a one-off prompt for this task.",
+            "family": "one_off_vs_reusable",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "one_off_request"
+              ],
+              "exclusive_negative_concepts": [
+                "one_off_request"
+              ],
+              "semantic_coverage": 0.0,
+              "support_score": 0,
+              "lexical_support": 0.429,
+              "negative_penalty": 0.24,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {},
+                "negative": {
+                  "one_off_request": [
+                    "one-off"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Write a custom answer for this request without creating a skill package.",
+            "family": "one_off_vs_reusable",
+            "score": 0.131,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "one_off_request"
+              ],
+              "exclusive_negative_concepts": [
+                "one_off_request"
+              ],
+              "semantic_coverage": 0.491,
+              "support_score": 0,
+              "lexical_support": 0.364,
+              "negative_penalty": 0.24,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "skill package"
+                  ],
+                  "reuse_package": [
+                    "package"
+                  ]
+                },
+                "negative": {
+                  "one_off_request": [
+                    "custom answer",
+                    "for this request"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Help me brainstorm process ideas without building a skill.",
+            "family": "brainstorm_vs_build",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "brainstorm_only",
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "brainstorm_only",
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.182,
+              "support_score": 0,
+              "lexical_support": 0.333,
+              "negative_penalty": 0.66,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {
+                  "transform_workflow": [
+                    "process"
+                  ]
+                },
+                "negative": {
+                  "brainstorm_only": [
+                    "brainstorm",
+                    "ideas"
+                  ],
+                  "no_build_directive": [
+                    "without building"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Improve this README but do not turn it into a skill.",
+            "family": "document_export_vs_agent_skill",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "document_only",
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.0,
+              "support_score": 0,
+              "lexical_support": 0.4,
+              "negative_penalty": 0.6,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {},
+                "negative": {
+                  "document_only": [
+                    "readme"
+                  ],
+                  "no_build_directive": [
+                    "do not turn it into a skill"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Make a checklist for this task, but not a reusable skill.",
+            "family": "partial_scaffold_not_full_skill",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.364,
+              "support_score": 0,
+              "lexical_support": 0.4,
+              "negative_penalty": 0.42,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "reuse_package": [
+                    "reusable"
+                  ],
+                  "transform_workflow": [
+                    "checklist"
+                  ]
+                },
+                "negative": {
+                  "no_build_directive": [
+                    "not a reusable skill"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Create a reusable-looking checklist, but keep it as a plain note instead of a skill.",
+            "family": "partial_scaffold_not_full_skill",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.364,
+              "support_score": 0,
+              "lexical_support": 0.231,
+              "negative_penalty": 0.42,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "reuse_package": [
+                    "reusable"
+                  ],
+                  "transform_workflow": [
+                    "checklist"
+                  ]
+                },
+                "negative": {
+                  "no_build_directive": [
+                    "plain note",
+                    "keep it as a plain note"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "We may convert this workflow later, but for now keep it as documentation only and produce a reference document.",
+            "family": "long_context_near_neighbor",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "document_only",
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.182,
+              "support_score": 0,
+              "lexical_support": 0.158,
+              "negative_penalty": 0.6,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {
+                  "transform_workflow": [
+                    "workflow"
+                  ]
+                },
+                "negative": {
+                  "document_only": [
+                    "document",
+                    "reference document"
+                  ],
+                  "no_build_directive": [
+                    "keep it as documentation only"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Draft a template only from this process and stop short of making a full skill package.",
+            "family": "partial_scaffold_not_full_skill",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "document_only",
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.673,
+              "support_score": 0,
+              "lexical_support": 0.4,
+              "negative_penalty": 0.6,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "skill package"
+                  ],
+                  "reuse_package": [
+                    "package"
+                  ],
+                  "transform_workflow": [
+                    "process"
+                  ]
+                },
+                "negative": {
+                  "document_only": [
+                    "template only"
+                  ],
+                  "no_build_directive": [
+                    "stop short of making a full skill"
+                  ]
+                }
+              }
+            }
+          }
+        ]
+      },
+      "comparison": {
+        "baseline_false_positives": 0,
+        "baseline_false_negatives": 1,
+        "improved_false_positives": 0,
+        "improved_false_negatives": 0,
+        "false_positive_delta": 0,
+        "false_negative_delta": -1,
+        "baseline_precision": 1.0,
+        "improved_precision": 1.0,
+        "baseline_recall": 0.917,
+        "improved_recall": 1.0
+      },
+      "returncode": 0
+    },
+    "dev": {
+      "threshold": 0.33,
+      "threshold_explanation": "Prompts at or above the threshold are treated as trigger matches. Scores are driven primarily by semantic intent coverage: packaging intent, workflow-to-skill transformation intent, reuse/distribution intent, and eval intent. Explicit exclusions such as summary-only, translation-only, one-off, document-only, or do-not-build directives apply direct penalties and can override otherwise similar wording.",
+      "false_positives": 0,
+      "false_negatives": 0,
+      "precision": 1.0,
+      "recall": 1.0,
+      "bucket_stats": {
+        "should_trigger": {
+          "total": 8,
+          "passed": 8,
+          "pass_rate": 1.0
+        },
+        "should_not_trigger": {
+          "total": 7,
+          "passed": 7,
+          "pass_rate": 1.0
+        },
+        "near_neighbor": {
+          "total": 7,
+          "passed": 7,
+          "pass_rate": 1.0
+        }
+      },
+      "family_stats": {
+        "workflow_to_skill": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "iterate_existing_skill": {
+          "total": 2,
+          "passed": 2,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "complex_multi_asset": {
+          "total": 2,
+          "passed": 2,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "paraphrase_trigger": {
+          "total": 2,
+          "passed": 2,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "long_context_trigger": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "brainstorm_only": {
+          "total": 2,
+          "passed": 2,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "explain_only": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "translate_only": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "summary_only": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "long_context_document_only": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "long_context_summary_only": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "explain_not_package": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "partial_scaffold_not_full_skill": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "document_export_vs_agent_skill": {
+          "total": 2,
+          "passed": 2,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "future_outline_vs_build": {
+          "total": 2,
+          "passed": 2,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "long_context_near_neighbor": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        }
+      },
+      "misfires": [],
+      "results": {
+        "should_trigger": [
+          {
+            "prompt": "Convert this operations checklist into a reusable skill.",
+            "family": "workflow_to_skill",
+            "score": 0.415,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.364,
+              "support_score": 0,
+              "lexical_support": 0.5,
+              "negative_penalty": 0,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "reuse_package": [
+                    "reusable"
+                  ],
+                  "transform_workflow": [
+                    "checklist",
+                    "operations checklist"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Add trigger evals to this skill before sharing it with the team.",
+            "family": "iterate_existing_skill",
+            "score": 0.388,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.327,
+              "support_score": 0,
+              "lexical_support": 0.333,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "eval_optimize": [
+                    "evals",
+                    "trigger evals"
+                  ],
+                  "iterate_existing_skill": [
+                    "this skill",
+                    "sharing it with the team",
+                    "before sharing it with the team"
+                  ],
+                  "team_operationalize": [
+                    "team",
+                    "sharing it with the team"
+                  ]
+                },
+                "negative": {}
+              }
+            },
+            "boundary_case": true
+          },
+          {
+            "prompt": "We have a messy release runbook, export process, and a prompt history; turn all of that into one reusable skill package with evals and packaging checks.",
+            "family": "complex_multi_asset",
+            "score": 0.843,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "eval_optimize",
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.818,
+              "support_score": 0,
+              "lexical_support": 0.375,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "skill package",
+                    "turn all of that into one reusable skill package"
+                  ],
+                  "eval_optimize": [
+                    "evals",
+                    "packaging checks"
+                  ],
+                  "reuse_package": [
+                    "reusable",
+                    "package",
+                    "packaging"
+                  ],
+                  "transform_workflow": [
+                    "runbook",
+                    "process",
+                    "prompt history"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Turn these workflow fragments, transcripts, and prompts into one production-ready skill with scripts and references.",
+            "family": "complex_multi_asset",
+            "score": 0.418,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [
+                "multi_asset"
+              ],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.364,
+              "support_score": 0.06,
+              "lexical_support": 0.357,
+              "negative_penalty": 0,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "multi_asset": [
+                    "references",
+                    "scripts"
+                  ],
+                  "reuse_package": [
+                    "production-ready"
+                  ],
+                  "transform_workflow": [
+                    "workflow",
+                    "workflow fragments"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Tighten the trigger boundary on this existing skill and prepare it for team distribution.",
+            "family": "iterate_existing_skill",
+            "score": 0.563,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "eval_optimize",
+                "iterate_existing_skill",
+                "reuse_package",
+                "team_operationalize"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.509,
+              "support_score": 0,
+              "lexical_support": 0.429,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "eval_optimize": [
+                    "trigger boundary"
+                  ],
+                  "iterate_existing_skill": [
+                    "existing skill"
+                  ],
+                  "reuse_package": [
+                    "distribution"
+                  ],
+                  "team_operationalize": [
+                    "team",
+                    "distribution"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Turn the SOP, transcript, and cleanup notes into a maintained skill for the team library.",
+            "family": "paraphrase_trigger",
+            "score": 0.471,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "reuse_package",
+                "team_operationalize",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.4,
+              "support_score": 0,
+              "lexical_support": 0.538,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "reuse_package": [
+                    "team library",
+                    "maintained"
+                  ],
+                  "team_operationalize": [
+                    "team"
+                  ],
+                  "transform_workflow": [
+                    "sop",
+                    "transcript"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Codify this workflow into a shared capability package and validate the route boundary before distribution.",
+            "family": "paraphrase_trigger",
+            "score": 0.868,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "eval_optimize",
+                "reuse_package",
+                "team_operationalize",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.855,
+              "support_score": 0,
+              "lexical_support": 0.267,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "codify this workflow"
+                  ],
+                  "eval_optimize": [
+                    "validate",
+                    "route boundary"
+                  ],
+                  "reuse_package": [
+                    "package",
+                    "distribution",
+                    "shared capability"
+                  ],
+                  "team_operationalize": [
+                    "shared",
+                    "distribution"
+                  ],
+                  "transform_workflow": [
+                    "workflow"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "After the long handoff notes below, build a skill package for team reuse. The materials include a transcript, rough notes, and an onboarding flow, and the result should include references, scripts, and validation.",
+            "family": "long_context_trigger",
+            "score": 0.891,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "eval_optimize",
+                "reuse_package",
+                "team_operationalize",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [
+                "multi_asset"
+              ],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.855,
+              "support_score": 0.06,
+              "lexical_support": 0.37,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "build a skill",
+                    "skill package"
+                  ],
+                  "eval_optimize": [
+                    "validation"
+                  ],
+                  "multi_asset": [
+                    "references",
+                    "scripts"
+                  ],
+                  "reuse_package": [
+                    "reuse",
+                    "package",
+                    "team reuse"
+                  ],
+                  "team_operationalize": [
+                    "team",
+                    "team reuse"
+                  ],
+                  "transform_workflow": [
+                    "rough notes",
+                    "transcript",
+                    "onboarding flow"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          }
+        ],
+        "should_not_trigger": [
+          {
+            "prompt": "Give me ideas for improving our process.",
+            "family": "brainstorm_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "brainstorm_only"
+              ],
+              "exclusive_negative_concepts": [
+                "brainstorm_only"
+              ],
+              "semantic_coverage": 0.182,
+              "support_score": 0,
+              "lexical_support": 0.286,
+              "negative_penalty": 0.24,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {
+                  "transform_workflow": [
+                    "process"
+                  ]
+                },
+                "negative": {
+                  "brainstorm_only": [
+                    "ideas"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Review this note and tell me what it means in plain English.",
+            "family": "explain_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "explain_only"
+              ],
+              "exclusive_negative_concepts": [
+                "explain_only"
+              ],
+              "semantic_coverage": 0.0,
+              "support_score": 0,
+              "lexical_support": 0.083,
+              "negative_penalty": 0.26,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {},
+                "negative": {
+                  "explain_only": [
+                    "tell me what it means",
+                    "plain english"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Help me brainstorm several ways to improve packaging, but do not generate any skill files.",
+            "family": "brainstorm_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "reuse_package"
+              ],
+              "extra_positive_concepts": [
+                "multi_asset"
+              ],
+              "matched_negative_concepts": [
+                "brainstorm_only",
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "brainstorm_only",
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.182,
+              "support_score": 0.06,
+              "lexical_support": 0.2,
+              "negative_penalty": 0.66,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {
+                  "multi_asset": [
+                    "files"
+                  ],
+                  "reuse_package": [
+                    "packaging"
+                  ]
+                },
+                "negative": {
+                  "brainstorm_only": [
+                    "brainstorm",
+                    "improve packaging"
+                  ],
+                  "no_build_directive": [
+                    "do not generate any skill files"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Translate these notes into French and keep the structure exactly as-is.",
+            "family": "translate_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "translate_only"
+              ],
+              "exclusive_negative_concepts": [
+                "translate_only"
+              ],
+              "semantic_coverage": 0.0,
+              "support_score": 0,
+              "lexical_support": 0.273,
+              "negative_penalty": 0.35,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {},
+                "negative": {
+                  "translate_only": [
+                    "translate",
+                    "into french"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Summarize this workflow and list the main points only.",
+            "family": "summary_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "summarize_only"
+              ],
+              "exclusive_negative_concepts": [
+                "summarize_only"
+              ],
+              "semantic_coverage": 0.182,
+              "support_score": 0,
+              "lexical_support": 0.111,
+              "negative_penalty": 0.3,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {
+                  "transform_workflow": [
+                    "workflow"
+                  ]
+                },
+                "negative": {
+                  "summarize_only": [
+                    "summarize"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "This is a long incident write-up. Keep it as documentation only, explain it in simpler language, and do not convert it into a reusable capability.",
+            "family": "long_context_document_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "reuse_package"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "explain_only",
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "explain_only",
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.182,
+              "support_score": 0,
+              "lexical_support": 0.182,
+              "negative_penalty": 0.68,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {
+                  "reuse_package": [
+                    "reusable"
+                  ]
+                },
+                "negative": {
+                  "explain_only": [
+                    "explain it",
+                    "in simpler language"
+                  ],
+                  "no_build_directive": [
+                    "do not convert it into a reusable capability",
+                    "keep it as documentation only"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "I pasted a very long process note. For now I only need a recap and a short summary, not a skill package.",
+            "family": "long_context_summary_only",
+            "score": 0.257,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "summarize_only"
+              ],
+              "exclusive_negative_concepts": [
+                "summarize_only"
+              ],
+              "semantic_coverage": 0.673,
+              "support_score": 0,
+              "lexical_support": 0.353,
+              "negative_penalty": 0.3,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "skill package"
+                  ],
+                  "reuse_package": [
+                    "package"
+                  ],
+                  "transform_workflow": [
+                    "process"
+                  ]
+                },
+                "negative": {
+                  "summarize_only": [
+                    "summary",
+                    "recap"
+                  ]
+                }
+              }
+            },
+            "boundary_case": true
+          }
+        ],
+        "near_neighbor": [
+          {
+            "prompt": "Review this process note and explain it, no packaging needed.",
+            "family": "explain_not_package",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "explain_only",
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "explain_only",
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.364,
+              "support_score": 0,
+              "lexical_support": 0.2,
+              "negative_penalty": 0.68,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "reuse_package": [
+                    "packaging"
+                  ],
+                  "transform_workflow": [
+                    "process"
+                  ]
+                },
+                "negative": {
+                  "explain_only": [
+                    "explain it"
+                  ],
+                  "no_build_directive": [
+                    "no packaging needed"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Turn this into a checklist and template, but stop short of making a full skill.",
+            "family": "partial_scaffold_not_full_skill",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.182,
+              "support_score": 0,
+              "lexical_support": 0.286,
+              "negative_penalty": 0.42,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {
+                  "transform_workflow": [
+                    "checklist"
+                  ]
+                },
+                "negative": {
+                  "no_build_directive": [
+                    "stop short of making a full skill"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Package this explanation as a document, not as an agent skill.",
+            "family": "document_export_vs_agent_skill",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "document_only",
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.491,
+              "support_score": 0,
+              "lexical_support": 0.4,
+              "negative_penalty": 0.6,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "agent skill"
+                  ],
+                  "reuse_package": [
+                    "package"
+                  ]
+                },
+                "negative": {
+                  "document_only": [
+                    "document"
+                  ],
+                  "no_build_directive": [
+                    "not as an agent skill"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Make a future-ready outline for this skill idea, but do not build the package.",
+            "family": "future_outline_vs_build",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "iterate_existing_skill",
+                "reuse_package"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "future_outline",
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "future_outline",
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.327,
+              "support_score": 0,
+              "lexical_support": 0.286,
+              "negative_penalty": 0.64,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "iterate_existing_skill": [
+                    "this skill"
+                  ],
+                  "reuse_package": [
+                    "package"
+                  ]
+                },
+                "negative": {
+                  "future_outline": [
+                    "future-ready outline"
+                  ],
+                  "no_build_directive": [
+                    "do not build"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Polish these notes into a reusable-looking document without turning them into an agent skill.",
+            "family": "document_export_vs_agent_skill",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "document_only",
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.491,
+              "support_score": 0,
+              "lexical_support": 0.462,
+              "negative_penalty": 0.6,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "agent skill"
+                  ],
+                  "reuse_package": [
+                    "reusable"
+                  ]
+                },
+                "negative": {
+                  "document_only": [
+                    "document",
+                    "reusable-looking document"
+                  ],
+                  "no_build_directive": [
+                    "without turning them into an agent skill"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Turn the workflow below into a wiki-ready reference document and template only. We may build a skill later, but not now.",
+            "family": "long_context_near_neighbor",
+            "score": 0.328,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "document_only"
+              ],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.491,
+              "support_score": 0,
+              "lexical_support": 0.2,
+              "negative_penalty": 0.18,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "build a skill"
+                  ],
+                  "transform_workflow": [
+                    "workflow"
+                  ]
+                },
+                "negative": {
+                  "document_only": [
+                    "document",
+                    "wiki",
+                    "reference document",
+                    "template only"
+                  ]
+                }
+              }
+            },
+            "boundary_case": true
+          },
+          {
+            "prompt": "Shape this idea for later and produce a future-ready outline, but do not build the skill package yet.",
+            "family": "future_outline_vs_build",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "future_outline",
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "future_outline",
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.491,
+              "support_score": 0,
+              "lexical_support": 0.278,
+              "negative_penalty": 0.64,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "skill package"
+                  ],
+                  "reuse_package": [
+                    "package"
+                  ]
+                },
+                "negative": {
+                  "future_outline": [
+                    "for later",
+                    "future-ready outline"
+                  ],
+                  "no_build_directive": [
+                    "do not build"
+                  ]
+                }
+              }
+            }
+          }
+        ]
+      },
+      "comparison": {
+        "baseline_false_positives": 1,
+        "baseline_false_negatives": 1,
+        "improved_false_positives": 0,
+        "improved_false_negatives": 0,
+        "false_positive_delta": -1,
+        "false_negative_delta": -1,
+        "baseline_precision": 0.875,
+        "improved_precision": 1.0,
+        "baseline_recall": 0.875,
+        "improved_recall": 1.0
+      },
+      "returncode": 0
+    },
+    "holdout": {
+      "threshold": 0.33,
+      "threshold_explanation": "Prompts at or above the threshold are treated as trigger matches. Scores are driven primarily by semantic intent coverage: packaging intent, workflow-to-skill transformation intent, reuse/distribution intent, and eval intent. Explicit exclusions such as summary-only, translation-only, one-off, document-only, or do-not-build directives apply direct penalties and can override otherwise similar wording.",
+      "false_positives": 0,
+      "false_negatives": 0,
+      "precision": 1.0,
+      "recall": 1.0,
+      "bucket_stats": {
+        "should_trigger": {
+          "total": 5,
+          "passed": 5,
+          "pass_rate": 1.0
+        },
+        "should_not_trigger": {
+          "total": 4,
+          "passed": 4,
+          "pass_rate": 1.0
+        },
+        "near_neighbor": {
+          "total": 4,
+          "passed": 4,
+          "pass_rate": 1.0
+        }
+      },
+      "family_stats": {
+        "complex_multi_asset": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "iterate_existing_skill": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "workflow_to_skill": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "paraphrase_trigger": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "long_context_trigger": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "summary_only": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "explain_only": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "long_context_document_only": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "translate_only": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "future_outline_vs_build": {
+          "total": 2,
+          "passed": 2,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "document_export_vs_agent_skill": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        },
+        "long_context_near_neighbor": {
+          "total": 1,
+          "passed": 1,
+          "false_positives": 0,
+          "false_negatives": 0,
+          "pass_rate": 1.0
+        }
+      },
+      "misfires": [],
+      "results": {
+        "should_trigger": [
+          {
+            "prompt": "Build a reusable skill from this long internal process note, and make sure it has references, scripts, and a trigger description.",
+            "family": "complex_multi_asset",
+            "score": 0.468,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "reuse_package",
+                "team_operationalize",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [
+                "multi_asset"
+              ],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.4,
+              "support_score": 0.06,
+              "lexical_support": 0.316,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "multi_asset": [
+                    "references",
+                    "scripts"
+                  ],
+                  "reuse_package": [
+                    "reusable"
+                  ],
+                  "team_operationalize": [
+                    "internal"
+                  ],
+                  "transform_workflow": [
+                    "process",
+                    "internal process note"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Take this existing skill draft, tighten the trigger boundary, add near-neighbor evals, and package it for distribution.",
+            "family": "iterate_existing_skill",
+            "score": 0.729,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "eval_optimize",
+                "iterate_existing_skill",
+                "reuse_package",
+                "team_operationalize",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.691,
+              "support_score": 0,
+              "lexical_support": 0.412,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "eval_optimize": [
+                    "evals",
+                    "near-neighbor",
+                    "trigger boundary"
+                  ],
+                  "iterate_existing_skill": [
+                    "existing skill"
+                  ],
+                  "reuse_package": [
+                    "package",
+                    "distribution"
+                  ],
+                  "team_operationalize": [
+                    "distribution"
+                  ],
+                  "transform_workflow": [
+                    "existing skill draft"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Turn this recurring onboarding process into a reusable skill library entry with validation notes.",
+            "family": "workflow_to_skill",
+            "score": 0.563,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "eval_optimize",
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.509,
+              "support_score": 0,
+              "lexical_support": 0.429,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "eval_optimize": [
+                    "validation"
+                  ],
+                  "reuse_package": [
+                    "reusable",
+                    "library entry"
+                  ],
+                  "transform_workflow": [
+                    "process"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Codify this quarterly release routine into a reusable skill package with scripts, references, and packaging checks.",
+            "family": "paraphrase_trigger",
+            "score": 0.858,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "eval_optimize",
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [
+                "multi_asset"
+              ],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.818,
+              "support_score": 0.06,
+              "lexical_support": 0.375,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "skill package"
+                  ],
+                  "eval_optimize": [
+                    "packaging checks"
+                  ],
+                  "multi_asset": [
+                    "references",
+                    "scripts"
+                  ],
+                  "reuse_package": [
+                    "reusable",
+                    "package",
+                    "packaging"
+                  ],
+                  "transform_workflow": [
+                    "quarterly release routine"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          },
+          {
+            "prompt": "Below is a noisy transcript plus release notes and prompt history. Ignore the chatter and turn this playbook into an agent capability package for the team library.",
+            "family": "long_context_trigger",
+            "score": 0.744,
+            "predicted_trigger": true,
+            "expected_trigger": true,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package",
+                "team_operationalize",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [],
+              "exclusive_negative_concepts": [],
+              "semantic_coverage": 0.709,
+              "support_score": 0,
+              "lexical_support": 0.4,
+              "negative_penalty": 0,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "turn this playbook into an agent capability package"
+                  ],
+                  "reuse_package": [
+                    "package",
+                    "team library"
+                  ],
+                  "team_operationalize": [
+                    "team"
+                  ],
+                  "transform_workflow": [
+                    "prompt history",
+                    "transcript",
+                    "release notes"
+                  ]
+                },
+                "negative": {}
+              }
+            }
+          }
+        ],
+        "should_not_trigger": [
+          {
+            "prompt": "I pasted a long process description below, but I only want a summary, not a reusable skill.",
+            "family": "summary_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "no_build_directive",
+                "summarize_only"
+              ],
+              "exclusive_negative_concepts": [
+                "no_build_directive",
+                "summarize_only"
+              ],
+              "semantic_coverage": 0.364,
+              "support_score": 0,
+              "lexical_support": 0.308,
+              "negative_penalty": 0.72,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "reuse_package": [
+                    "reusable"
+                  ],
+                  "transform_workflow": [
+                    "process"
+                  ]
+                },
+                "negative": {
+                  "no_build_directive": [
+                    "not a reusable skill"
+                  ],
+                  "summarize_only": [
+                    "summary",
+                    "only want a summary"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Explain this release checklist in simpler language; do not package it.",
+            "family": "explain_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "explain_only",
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "explain_only",
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.364,
+              "support_score": 0,
+              "lexical_support": 0.091,
+              "negative_penalty": 0.68,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "reuse_package": [
+                    "package"
+                  ],
+                  "transform_workflow": [
+                    "checklist"
+                  ]
+                },
+                "negative": {
+                  "explain_only": [
+                    "explain this",
+                    "in simpler language"
+                  ],
+                  "no_build_directive": [
+                    "do not package it"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Keep this release workflow as documentation only for the wiki and produce a reference document, not for agent execution.",
+            "family": "long_context_document_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "document_only",
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.182,
+              "support_score": 0,
+              "lexical_support": 0.222,
+              "negative_penalty": 0.6,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {
+                  "transform_workflow": [
+                    "workflow"
+                  ]
+                },
+                "negative": {
+                  "document_only": [
+                    "document",
+                    "wiki",
+                    "reference document"
+                  ],
+                  "no_build_directive": [
+                    "not for agent execution"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Translate this long runbook into Russian and keep it as documentation only with no skill package.",
+            "family": "translate_only",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "no_build_directive",
+                "translate_only"
+              ],
+              "exclusive_negative_concepts": [
+                "no_build_directive",
+                "translate_only"
+              ],
+              "semantic_coverage": 0.673,
+              "support_score": 0,
+              "lexical_support": 0.25,
+              "negative_penalty": 0.77,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "skill package"
+                  ],
+                  "reuse_package": [
+                    "package"
+                  ],
+                  "transform_workflow": [
+                    "runbook"
+                  ]
+                },
+                "negative": {
+                  "no_build_directive": [
+                    "no skill package",
+                    "keep it as documentation only"
+                  ],
+                  "translate_only": [
+                    "translate",
+                    "into russian"
+                  ]
+                }
+              }
+            }
+          }
+        ],
+        "near_neighbor": [
+          {
+            "prompt": "Help me shape an idea before we decide whether to build a skill.",
+            "family": "future_outline_vs_build",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "brainstorm_only",
+                "future_outline"
+              ],
+              "exclusive_negative_concepts": [
+                "brainstorm_only",
+                "future_outline"
+              ],
+              "semantic_coverage": 0.309,
+              "support_score": 0,
+              "lexical_support": 0.308,
+              "negative_penalty": 0.46,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "build a skill"
+                  ]
+                },
+                "negative": {
+                  "brainstorm_only": [
+                    "shape an idea"
+                  ],
+                  "future_outline": [
+                    "before we decide whether to build"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Create an outline for a possible future skill, but do not build the skill yet.",
+            "family": "future_outline_vs_build",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "future_outline",
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "future_outline",
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.0,
+              "support_score": 0,
+              "lexical_support": 0.357,
+              "negative_penalty": 0.64,
+              "coverage_boost": 0.0,
+              "concept_evidence": {
+                "positive": {},
+                "negative": {
+                  "future_outline": [
+                    "future skill",
+                    "possible future skill",
+                    "outline for a possible future skill"
+                  ],
+                  "no_build_directive": [
+                    "do not build"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "Turn this into a document package for the wiki, not an agent skill.",
+            "family": "document_export_vs_agent_skill",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "document_only",
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.491,
+              "support_score": 0,
+              "lexical_support": 0.538,
+              "negative_penalty": 0.6,
+              "coverage_boost": 0.04,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "agent skill"
+                  ],
+                  "reuse_package": [
+                    "package"
+                  ]
+                },
+                "negative": {
+                  "document_only": [
+                    "document",
+                    "document package",
+                    "wiki"
+                  ],
+                  "no_build_directive": [
+                    "not an agent skill"
+                  ]
+                }
+              }
+            }
+          },
+          {
+            "prompt": "From the long workflow below, create a template only and a checklist for discussion only. No skill package.",
+            "family": "long_context_near_neighbor",
+            "score": 0.0,
+            "predicted_trigger": false,
+            "expected_trigger": false,
+            "passed": true,
+            "score_detail": {
+              "mode": "semantic-intent",
+              "desired_positive_concepts": [
+                "build_skill",
+                "transform_workflow",
+                "reuse_package",
+                "eval_optimize",
+                "iterate_existing_skill",
+                "team_operationalize"
+              ],
+              "matched_desired_concepts": [
+                "build_skill",
+                "reuse_package",
+                "transform_workflow"
+              ],
+              "extra_positive_concepts": [],
+              "matched_negative_concepts": [
+                "document_only",
+                "no_build_directive"
+              ],
+              "exclusive_negative_concepts": [
+                "no_build_directive"
+              ],
+              "semantic_coverage": 0.673,
+              "support_score": 0,
+              "lexical_support": 0.375,
+              "negative_penalty": 0.6,
+              "coverage_boost": 0.06,
+              "concept_evidence": {
+                "positive": {
+                  "build_skill": [
+                    "skill package"
+                  ],
+                  "reuse_package": [
+                    "package"
+                  ],
+                  "transform_workflow": [
+                    "workflow",
+                    "checklist"
+                  ]
+                },
+                "negative": {
+                  "document_only": [
+                    "template only"
+                  ],
+                  "no_build_directive": [
+                    "no skill package",
+                    "discussion only"
+                  ]
+                }
+              }
+            }
+          }
+        ]
+      },
+      "comparison": {
+        "baseline_false_positives": 0,
+        "baseline_false_negatives": 0,
+        "improved_false_positives": 0,
+        "improved_false_negatives": 0,
+        "false_positive_delta": 0,
+        "false_negative_delta": 0,
+        "baseline_precision": 1.0,
+        "improved_precision": 1.0,
+        "baseline_recall": 1.0,
+        "improved_recall": 1.0
+      },
+      "returncode": 0
+    }
+  }
+}
diff --git a/reports/family_summary.md b/reports/family_summary.md
new file mode 100644
index 00000000..a258b507
--- /dev/null
+++ b/reports/family_summary.md
@@ -0,0 +1,34 @@
+# Eval Family Summary
+
+- total cases: `66`
+- families: `21`
+- false positives: `0`
+- false negatives: `0`
+- average precision: `1.0`
+- average recall: `1.0`
+
+## Family Results
+
+| Family | Cases | Passed | FP | FN | Pass Rate |
+| --- | ---: | ---: | ---: | ---: | ---: |
+| `brainstorm_only` | 2 | 2 | 0 | 0 | 1.0 |
+| `brainstorm_vs_build` | 1 | 1 | 0 | 0 | 1.0 |
+| `complex_multi_asset` | 3 | 3 | 0 | 0 | 1.0 |
+| `document_export_vs_agent_skill` | 4 | 4 | 0 | 0 | 1.0 |
+| `document_only` | 3 | 3 | 0 | 0 | 1.0 |
+| `explain_not_package` | 1 | 1 | 0 | 0 | 1.0 |
+| `explain_only` | 5 | 5 | 0 | 0 | 1.0 |
+| `future_outline_vs_build` | 4 | 4 | 0 | 0 | 1.0 |
+| `iterate_existing_skill` | 5 | 5 | 0 | 0 | 1.0 |
+| `long_context_document_only` | 3 | 3 | 0 | 0 | 1.0 |
+| `long_context_near_neighbor` | 3 | 3 | 0 | 0 | 1.0 |
+| `long_context_summary_only` | 2 | 2 | 0 | 0 | 1.0 |
+| `long_context_trigger` | 4 | 4 | 0 | 0 | 1.0 |
+| `meta_skill_creation` | 1 | 1 | 0 | 0 | 1.0 |
+| `one_off_vs_reusable` | 2 | 2 | 0 | 0 | 1.0 |
+| `package_for_team` | 2 | 2 | 0 | 0 | 1.0 |
+| `paraphrase_trigger` | 5 | 5 | 0 | 0 | 1.0 |
+| `partial_scaffold_not_full_skill` | 4 | 4 | 0 | 0 | 1.0 |
+| `summary_only` | 3 | 3 | 0 | 0 | 1.0 |
+| `translate_only` | 4 | 4 | 0 | 0 | 1.0 |
+| `workflow_to_skill` | 5 | 5 | 0 | 0 | 1.0 |
diff --git a/scripts/render_eval_dashboard.py b/scripts/render_eval_dashboard.py
new file mode 100644
index 00000000..da7f58d7
--- /dev/null
+++ b/scripts/render_eval_dashboard.py
@@ -0,0 +1,126 @@
+#!/usr/bin/env python3
+import argparse
+import json
+import subprocess
+import sys
+from pathlib import Path
+
+
+BEGIN_MARKER = "<!-- BEGIN:EVAL_RESULTS -->"
+END_MARKER = "<!-- END:EVAL_RESULTS -->"
+
+
+def run_eval_suite(args: argparse.Namespace) -> dict:
+    proc = subprocess.run(
+        [
+            sys.executable,
+            "scripts/run_eval_suite.py",
+            "--eval-dir",
+            args.eval_dir,
+            "--description-file",
+            args.description_file,
+            "--baseline-description-file",
+            args.baseline_description_file,
+        ],
+        capture_output=True,
+        text=True,
+        check=True,
+    )
+    return json.loads(proc.stdout)
+
+
+def render_readme_panel(report: dict) -> str:
+    summary = report["summary"]
+    suites = report["suites"]
+    families = report["family_summary"]
+
+    lines = [
+        BEGIN_MARKER,
+        f"- regression corpus: `{summary['total_cases']}` prompts across `{summary['family_count']}` families",
+        f"- aggregate result: `{summary['false_positives']}` false positives, `{summary['false_negatives']}` false negatives, average precision `{summary['average_precision']}`, average recall `{summary['average_recall']}`",
+        "- suite status:",
+        "",
+        "| Suite | Cases | FP | FN | Precision | Recall |",
+        "| --- | ---: | ---: | ---: | ---: | ---: |",
+    ]
+    for suite_name in ("train", "dev", "holdout"):
+        suite = suites[suite_name]
+        cases = sum(bucket["total"] for bucket in suite["bucket_stats"].values())
+        lines.append(
+            f"| {suite_name} | {cases} | {suite['false_positives']} | {suite['false_negatives']} | {suite['precision']} | {suite['recall']} |"
+        )
+
+    lines.extend(
+        [
+            "",
+            "| Family | Cases | Pass Rate |",
+            "| --- | ---: | ---: |",
+        ]
+    )
+    for family, stats in sorted(families.items()):
+        lines.append(f"| `{family}` | {stats['total']} | {stats['pass_rate']} |")
+
+    lines.extend(
+        [
+            "",
+            "Full reports: [reports/eval_suite.json](reports/eval_suite.json) and [reports/family_summary.md](reports/family_summary.md)",
+            END_MARKER,
+        ]
+    )
+    return "\n".join(lines)
+
+
+def render_family_summary(report: dict) -> str:
+    summary = report["summary"]
+    lines = [
+        "# Eval Family Summary",
+        "",
+        f"- total cases: `{summary['total_cases']}`",
+        f"- families: `{summary['family_count']}`",
+        f"- false positives: `{summary['false_positives']}`",
+        f"- false negatives: `{summary['false_negatives']}`",
+        f"- average precision: `{summary['average_precision']}`",
+        f"- average recall: `{summary['average_recall']}`",
+        "",
+        "## Family Results",
+        "",
+        "| Family | Cases | Passed | FP | FN | Pass Rate |",
+        "| --- | ---: | ---: | ---: | ---: | ---: |",
+    ]
+    for family, stats in sorted(report["family_summary"].items()):
+        lines.append(
+            f"| `{family}` | {stats['total']} | {stats['passed']} | {stats['false_positives']} | {stats['false_negatives']} | {stats['pass_rate']} |"
+        )
+    return "\n".join(lines) + "\n"
+
+
+def update_readme(readme_path: Path, panel: str) -> None:
+    text = readme_path.read_text(encoding="utf-8")
+    if BEGIN_MARKER not in text or END_MARKER not in text:
+        raise SystemExit(f"README markers not found in {readme_path}")
+    start = text.index(BEGIN_MARKER)
+    end = text.index(END_MARKER) + len(END_MARKER)
+    updated = text[:start] + panel + text[end:]
+    readme_path.write_text(updated, encoding="utf-8")
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Render README-visible eval results and full family report.")
+    parser.add_argument("--eval-dir", default="evals")
+    parser.add_argument("--description-file", default="evals/improved_description.txt")
+    parser.add_argument("--baseline-description-file", default="evals/baseline_description.txt")
+    parser.add_argument("--output-dir", default="reports")
+    parser.add_argument("--readme", default="README.md")
+    args = parser.parse_args()
+
+    report = run_eval_suite(args)
+    output_dir = Path(args.output_dir)
+    output_dir.mkdir(parents=True, exist_ok=True)
+
+    (output_dir / "eval_suite.json").write_text(json.dumps(report, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
+    (output_dir / "family_summary.md").write_text(render_family_summary(report), encoding="utf-8")
+    update_readme(Path(args.readme), render_readme_panel(report))
+
+
+if __name__ == "__main__":
+    main()
diff --git a/scripts/run_eval_suite.py b/scripts/run_eval_suite.py
index 90766316..c1bdd763 100644
--- a/scripts/run_eval_suite.py
+++ b/scripts/run_eval_suite.py
@@ -33,6 +33,7 @@ def main() -> None:
     parser.add_argument("--eval-dir", default="evals", help="Root eval directory")
     parser.add_argument("--description-file", default="evals/improved_description.txt")
     parser.add_argument("--baseline-description-file", default="evals/baseline_description.txt")
+    parser.add_argument("--output-file", help="Optional path to write the combined JSON report")
     args = parser.parse_args()
 
     root = Path(args.eval_dir).resolve()
@@ -65,15 +66,21 @@ def main() -> None:
     for family, stats in family_summary.items():
         stats["pass_rate"] = round(stats["passed"] / stats["total"], 3) if stats["total"] else None
 
+    total_cases = sum(stats["total"] for stats in family_summary.values())
     summary = {
         "suite_count": len(suites),
+        "total_cases": total_cases,
+        "family_count": len(family_summary),
         "false_positives": aggregate["false_positives"],
         "false_negatives": aggregate["false_negatives"],
         "average_precision": round(sum(aggregate["precision"]) / len(aggregate["precision"]), 3) if aggregate["precision"] else None,
         "average_recall": round(sum(aggregate["recall"]) / len(aggregate["recall"]), 3) if aggregate["recall"] else None,
     }
     output = {"summary": summary, "family_summary": family_summary, "suites": suites}
-    print(json.dumps(output, ensure_ascii=False, indent=2))
+    rendered = json.dumps(output, ensure_ascii=False, indent=2)
+    if args.output_file:
+        Path(args.output_file).write_text(rendered + "\n", encoding="utf-8")
+    print(rendered)
     if summary["false_positives"] > 0 or summary["false_negatives"] > 0:
         raise SystemExit(2)