yao-meta-skill/reports/reference-synthesis.json

{
  "skill_name": "yao-meta-skill",
  "description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
  "intent_confidence": {
    "score": 100,
    "band": "high",
    "gate_passed": true
  },
  "github_benchmarks": [
    {
      "name": "obra/superpowers",
      "url": "https://github.com/obra/superpowers",
      "stars": 226125,
      "borrow": [
        "Borrow the way it turns a messy workflow into a repeatable operating path.",
        "Borrow the clear execution entrypoints and command structure."
      ]
    },
    {
      "name": "affaan-m/ECC",
      "url": "https://github.com/affaan-m/ECC",
      "stars": 214381,
      "borrow": [
        "Borrow the way it turns a messy workflow into a repeatable operating path.",
        "Borrow the clear execution entrypoints and command structure."
      ]
    },
    {
      "name": "multica-ai/andrej-karpathy-skills",
      "url": "https://github.com/multica-ai/andrej-karpathy-skills",
      "stars": 174264,
      "borrow": [
        "Borrow explicit validation and quality gates that make iteration safer.",
        "Borrow the way it separates explanation, examples, and reusable structure."
      ]
    }
  ],
  "source_tracks": [
    {
      "source_type": "official",
      "name": "Official skill anatomy and context discipline",
      "evidence_mode": "curated-pattern-track",
      "matched_keywords": [
        "metadata",
        "references"
      ],
      "borrow": "Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.",
      "avoid": "Do not let packaging or platform concerns swallow the core job boundary.",
      "why_relevant": "This track matches: metadata, references."
    },
    {
      "source_type": "research",
      "name": "Hypothesis-test-learn loop",
      "evidence_mode": "curated-pattern-track",
      "matched_keywords": [
        "test",
        "iteration"
      ],
      "borrow": "Borrow a small hypothesis-test-learn loop so the first revision is evidence-backed.",
      "avoid": "Do not create experimental overhead that exceeds the skill's real risk tier.",
      "why_relevant": "This track matches: test, iteration."
    },
    {
      "source_type": "principles",
      "name": "Boundary-first design",
      "evidence_mode": "curated-pattern-track",
      "matched_keywords": [
        "route",
        "trigger",
        "exclude"
      ],
      "borrow": "Borrow the discipline of defining what the skill should not own before growing the package.",
      "avoid": "Do not expand execution assets until route boundaries stay clean.",
      "why_relevant": "This track matches: route, trigger, exclude."
    }
  ],
  "synthesis": {
    "borrow_now": [
      "Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.",
      "Borrow a small hypothesis-test-learn loop so the first revision is evidence-backed.",
      "Borrow the discipline of defining what the skill should not own before growing the package.",
      "Borrow the way it turns a messy workflow into a repeatable operating path.",
      "Borrow the clear execution entrypoints and command structure."
    ],
    "avoid_now": [
      "Do not let packaging or platform concerns swallow the core job boundary.",
      "Do not create experimental overhead that exceeds the skill's real risk tier.",
      "Do not expand execution assets until route boundaries stay clean.",
      "Do not import process overhead that only exists for that project's scale.",
      "Do not copy repo-specific commands or environment assumptions verbatim."
    ],
    "quality_risers": [
      "Use GitHub repositories for concrete package and workflow patterns.",
      "Use curated official or commercial tracks for entrypoint and operator ergonomics.",
      "Use research tracks to justify the smallest evaluation loop that still catches regressions.",
      "Use principle tracks to keep the package small, boundary-aware, and outcome-driven."
    ],
    "pattern_gate": {
      "threshold": 4,
      "source_count": 6,
      "accepted": [
        {
          "name": "Official skill anatomy and context discipline",
          "source_type": "official",
          "borrow": "Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.",
          "avoid": "Do not let packaging or platform concerns swallow the core job boundary.",
          "gates": {
            "recurrence": true,
            "generativity": true,
            "distinctiveness": true,
            "boundary": true
          },
          "passed": [
            "recurrence",
            "generativity",
            "distinctiveness",
            "boundary"
          ],
          "missing": [],
          "score": 4
        },
        {
          "name": "Hypothesis-test-learn loop",
          "source_type": "research",
          "borrow": "Borrow a small hypothesis-test-learn loop so the first revision is evidence-backed.",
          "avoid": "Do not create experimental overhead that exceeds the skill's real risk tier.",
          "gates": {
            "recurrence": true,
            "generativity": true,
            "distinctiveness": true,
            "boundary": true
          },
          "passed": [
            "recurrence",
            "generativity",
            "distinctiveness",
            "boundary"
          ],
          "missing": [],
          "score": 4
        },
        {
          "name": "Boundary-first design",
          "source_type": "principles",
          "borrow": "Borrow the discipline of defining what the skill should not own before growing the package.",
          "avoid": "Do not expand execution assets until route boundaries stay clean.",
          "gates": {
            "recurrence": true,
            "generativity": true,
            "distinctiveness": true,
            "boundary": true
          },
          "passed": [
            "recurrence",
            "generativity",
            "distinctiveness",
            "boundary"
          ],
          "missing": [],
          "score": 4
        },
        {
          "name": "obra/superpowers",
          "source_type": "github",
          "borrow": "Borrow the way it turns a messy workflow into a repeatable operating path.; Borrow the clear execution entrypoints and command structure.",
          "avoid": "Do not import process overhead that only exists for that project's scale.",
          "gates": {
            "recurrence": true,
            "generativity": true,
            "distinctiveness": true,
            "boundary": true
          },
          "passed": [
            "recurrence",
            "generativity",
            "distinctiveness",
            "boundary"
          ],
          "missing": [],
          "score": 4
        },
        {
          "name": "affaan-m/ECC",
          "source_type": "github",
          "borrow": "Borrow the way it turns a messy workflow into a repeatable operating path.; Borrow the clear execution entrypoints and command structure.",
          "avoid": "Do not import process overhead that only exists for that project's scale.",
          "gates": {
            "recurrence": true,
            "generativity": true,
            "distinctiveness": true,
            "boundary": true
          },
          "passed": [
            "recurrence",
            "generativity",
            "distinctiveness",
            "boundary"
          ],
          "missing": [],
          "score": 4
        }
      ],
      "deferred": [
        {
          "name": "multica-ai/andrej-karpathy-skills",
          "source_type": "github",
          "borrow": "Borrow explicit validation and quality gates that make iteration safer.; Borrow the way it separates explanation, examples, and reusable structure.",
          "avoid": "Do not clone heavyweight evaluation scaffolding if a lighter gate is enough here.",
          "gates": {
            "recurrence": true,
            "generativity": false,
            "distinctiveness": true,
            "boundary": true
          },
          "passed": [
            "recurrence",
            "distinctiveness",
            "boundary"
          ],
          "missing": [
            "generativity"
          ],
          "score": 3
        }
      ],
      "summary": "5 accepted, 1 deferred using threshold 4/4."
    },
    "conflicts": [
      {
        "key": "lightweight_vs_governance",
        "summary": "The stated preference leans lightweight or speed-first, while the benchmark mix leans toward governance, review, or heavier evaluation structure.",
        "user_preference": "lightweight or speed-first",
        "benchmark_pressure": "governance or evaluation-heavy patterns"
      }
    ],
    "recommendation": {
      "summary": "Start by borrowing this pattern: Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts. Avoid this for the first pass: Do not let packaging or platform concerns swallow the core job boundary.",
      "borrow_now": [
        "Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.",
        "Borrow a small hypothesis-test-learn loop so the first revision is evidence-backed."
      ],
      "avoid_for_now": [
        "Do not let packaging or platform concerns swallow the core job boundary.",
        "Do not create experimental overhead that exceeds the skill's real risk tier."
      ],
      "why": "There is a real design conflict to resolve: The stated preference leans lightweight or speed-first, while the benchmark mix leans toward governance, review, or heavier evaluation structure.",
      "user_decision_required": true
    },
    "visibility": {
      "mode": "explicit",
      "user_decision_required": true,
      "reasons": [
        "design_conflict"
      ],
      "user_note": "Surface the recommendation because intent is still settling or there is a real design conflict that needs a user call.",
      "reviewer_note": "Keep the full benchmark and synthesis evidence visible for authors and reviewers."
    },
    "decision_prompt": "Use the recommendation by default. Only surface the underlying benchmark tradeoffs when intent is uncertain or a real design conflict needs a deliberate call.",
    "source_mix": {
      "github_benchmarks": 3,
      "curated_tracks": 3,
      "user_references": 0
    }
  }
}