Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Manifest-driven knowledge asset generator — converts any structured package into maestro knowhow + spec entries with ref linking. Triggers on "codify-to-knowhow", "style to knowhow", "知识固化".
.claude/skills/catlog22-codify-to-knowhow/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 84% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 95% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 32% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 133% | 0% |
> Plan tracking: codex 无 TaskCreate/TaskUpdate/TodoWrite 任务板。进度清单用 update_plan({ explanation?, plan: [{ step, status }] }) 维护(整体提交步骤数组,status: pending | in_progress | completed),权威状态始终在 session 工件中;依赖/认领(addBlockedBy/owner)是工件字段,不是工具参数。
通用 manifest 驱动的知识资产生成器。读取 knowhow-manifest.json,按声明创建 knowhow 文件和 spec 条目,通过 ref 建立索引-详文桥梁。
适用场景: 任何工作流产出需要固化为知识资产时使用。上游 skill(如 maestro-impeccable --codify)负责生成 manifest,本 skill 负责执行知识写入。
┌─────────────────────────────────────────────────────────────┐
│ Codify to Knowhow (SKILL.md) — Manifest-Driven │
│ → Read manifest → Create knowhow → Create specs → Verify │
└──────────────────────────┬──────────────────────────────────┘
│
┌──────────┬───────────┼───────────┬──────────┐
↓ ↓ ↓ ↓ │
┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐ │
│Phase 1 │ │Phase 2 │ │Phase 3 │ │Phase 4 │ │
│ Load │ │Generate│ │Generate│ │ Index │ │
│Manifest│ │Knowhow │ │ Specs │ │ Verify │ │
└───┬────┘ └───┬────┘ └───┬────┘ └───┬────┘ │
│ │ │ │ │
manifest AST-/DCS- spec-entry verified │
parsed files + ref assets │knowhow-manifest.json 声明,不含硬编码领域知识ref 引用 knowhow 详文<spec-entry>/<knowhow-entry> 闭合标签knowhow-manifest.json 由上游 skill 生成,放在 package 目录中:
json{ "slug": "my-style-v1", "domain": "ui-design", "roles": ["implement", "review"], "packagePath": ".workflow/reference_style/my-style-v1", "knowhow": [ { "prefix": "AST", "fileSlug": "tokens", "title": "Design Tokens", "category": "asset", "assetType": "design-tokens", "codePaths": ["src/styles/"], "tags": ["design-tokens", "colors"], "entries": [ { "category": "pattern", "keywords": "colors,tokens", "title": "Color System", "body": "## Colors\n\n..." } ] } ], "specs": [ { "category": "coding", "keywords": "colors,design-tokens", "title": "颜色编码约定", "ref": "knowhow/AST-my-style-v1-tokens.md", "body": "主色使用 var(--color-primary)..." } ] }
Input: <package-path> (must contain knowhow-manifest.json)
Phase 1: Load and Validate Manifest
└─ Ref: phases/01-load-manifest.md
├─ Validate package path and manifest existence
├─ Parse knowhow-manifest.json
└─ Output: manifest object
Phase 2: Generate Knowhow Assets
└─ Ref: phases/02-generate-knowhow.md
├─ Idempotency check per file
├─ Write knowhow files per manifest.knowhow[]
└─ Output: knowhowPaths[]
Phase 3: Generate Spec Entries
└─ Ref: phases/03-generate-specs.md
├─ Idempotency check per entry
├─ Write spec entries per manifest.specs[]
└─ Output: specEntryCount
Phase 4: Index and Verify
└─ Ref: phases/04-index-verify.md
└─ Output: verification reportPhase Reference Documents:
| Phase | Document | Purpose | |-------|----------|---------| | 1 | phases/01-load-manifest.md | Load and validate manifest | | 2 | phases/02-generate-knowhow.md | Create knowhow files | | 3 | phases/03-generate-specs.md | Create spec entries with ref | | 4 | phases/04-index-verify.md | Verify assets and index |
Input (packagePath)
↓
Phase 1 → manifest: { slug, knowhow[], specs[] }
↓
Phase 2 → knowhowPaths: string[], knowhowIds: string[]
↓
Phase 3 → specEntryCount: number
↓
Phase 4 → verificationResult
↓
Completion reportjson[ {"content": "Phase 1: 加载 Manifest", "status": "in_progress"}, {"content": "Phase 2: 生成 Knowhow 资产", "status": "pending"}, {"content": "Phase 3: 生成 Spec 条目", "status": "pending"}, {"content": "Phase 4: 索引验证", "status": "pending"} ]
上游: maestro-impeccable --codify, maestro-learn decompose, 或任何生成 manifest 的 skill 后续: maestro wiki list --category coding, maestro load --type spec --keyword <slug>
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 5,452 | 8,347 | +53% | 1 | 1 | 0% | 230 | 2,104 | +815% | 0 | 0 | — |
case-02 | fail→fail | 3,049 | 8,370 | +175% | 1 | 1 | 0% | 291 | 2,105 | +623% | 0 | 0 | — |
case-03 | fail→fail | 5,039 | 7,838 | +56% | 1 | 1 | 0% | 159 | 2,045 | +1186% | 0 | 0 | — |
case-04 | fail→fail | 23,987 | 5,982 | -75% | 1 | 1 | 0% | 4,651 | 1,817 | -61% | 0 | 0 | — |
case-05 | fail→fail | 4,164 | 7,070 | +70% | 1 | 1 | 0% | 586 | 2,131 | +264% | 0 | 0 | — |
case-06 | pass→fail | 14,390 | 9,147 | -36% | 1 | 1 | 0% | 2,391 | 2,333 | -2% | 0 | 0 | — |
case-07 | fail→pass | 9,948 | 8,249 | -17% | 1 | 1 | 0% | 1,650 | 3,038 | +84% | 0 | 0 | — |
case-08 | fail→pass | 8,154 | 2,877 | -65% | 1 | 1 | 0% | 1,077 | 2,095 | +95% | 0 | 0 | — |
case-09 | fail→pass | 12,816 | 6,448 | -50% | 1 | 1 | 0% | 2,037 | 2,696 | +32% | 0 | 0 | — |
case-10 | pass→pass | 11,793 | 2,895 | -75% | 1 | 1 | 0% | 1,954 | 2,094 | +7% | 0 | 0 | — |
case-11 | fail→fail | 15,938 | 5,637 | -65% | 1 | 1 | 0% | 2,895 | 2,592 | -10% | 0 | 0 | — |
case-12 | fail→pass | 12,735 | 4,496 | -65% | 1 | 1 | 0% | 1,916 | 2,294 | +20% | 0 | 0 | — |
case-13 | pass→pass | 5,057 | 4,651 | -8% | 1 | 1 | 0% | 767 | 2,341 | +205% | 0 | 0 | — |
case-14 | fail→pass | 6,757 | 4,522 | -33% | 1 | 1 | 0% | 1,059 | 2,470 | +133% | 0 | 0 | — |
case-15 | fail→pass | 9,451 | 3,167 | -66% | 1 | 1 | 0% | 1,367 | 2,072 | +52% | 0 | 0 | — |
case-16 | pass→pass | 7,624 | 3,435 | -55% | 1 | 1 | 0% | 1,127 | 2,176 | +93% | 0 | 0 | — |
case-17 | fail→pass | 12,436 | 4,954 | -60% | 1 | 1 | 0% | 1,819 | 2,432 | +34% | 0 | 0 | — |
case-18 | fail→pass | 10,634 | 7,842 | -26% | 1 | 1 | 0% | 1,506 | 2,918 | +94% | 0 | 0 | — |
case-19 | fail→pass | 9,200 | 3,715 | -60% | 1 | 1 | 0% | 1,508 | 2,297 | +52% | 0 | 0 | — |
case-20 | fail→pass | 11,600 | 6,514 | -44% | 1 | 1 | 0% | 1,654 | 2,714 | +64% | 0 | 0 | — |
case-21 | pass→fail | 14,123 | 5,848 | -59% | 1 | 1 | 0% | 1,926 | 1,900 | -1% | 0 | 0 | — |
case-22 | pass→pass | 6,604 | 5,154 | -22% | 1 | 1 | 0% | 981 | 2,458 | +151% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 15 counted toward the lift figure. The other 7 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +36 percentage points is the difference between those two pass rates over the 15 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.