Files
yao-meta-skill/reports/eval_suite.json
T
2026-05-01 14:27:51 +08:00

3960 lines
127 KiB
JSON

{
"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": 0.739,
"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": 0.75,
"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": 0.365,
"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": 0.714,
"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": 0.542,
"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": 0.625,
"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": 0.455,
"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": 0.833,
"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": 0.595,
"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": 0.625,
"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": 0.756,
"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": 0.364,
"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": 0.886,
"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": 0.5,
"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": 0.756,
"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": 0.355,
"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": 0.2,
"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": 0.174,
"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": 0.267,
"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": 0.294,
"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": 0.375,
"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": 0.455,
"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": 0.357,
"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": 0.211,
"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": 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
},
"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": 0.401,
"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": 0.5,
"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": 0.422,
"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": 0.4,
"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": 0.568,
"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": 0.5,
"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": 0.474,
"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": 0.571,
"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": 0.889,
"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": 0.346,
"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": 0.333,
"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": 0.217,
"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": 0.256,
"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": 0.333,
"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": 0.357,
"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": 0.6,
"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": 0.267,
"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": 0.5,
"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": 0.0,
"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",
"transform_workflow"
],
"extra_positive_concepts": [],
"matched_negative_concepts": [
"document_only",
"future_outline",
"no_build_directive"
],
"exclusive_negative_concepts": [
"future_outline",
"no_build_directive"
],
"semantic_coverage": 0.491,
"support_score": 0,
"lexical_support": 0.238,
"negative_penalty": 0.82,
"coverage_boost": 0.04,
"concept_evidence": {
"positive": {
"build_skill": [
"build a skill"
],
"transform_workflow": [
"workflow"
]
},
"negative": {
"document_only": [
"document",
"wiki",
"reference document",
"template only"
],
"future_outline": [
"not now",
"later but not now"
],
"no_build_directive": [
"not now",
"later but not now"
]
}
}
}
},
{
"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": 0.263,
"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": 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": 0.875,
"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": 0.472,
"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": 0.368,
"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": 0.731,
"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": 0.444,
"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": 0.568,
"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": 0.5,
"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": 0.286,
"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": 0.278,
"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": 0.312,
"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": 0.615,
"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": 0.438,
"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
}
}
}