Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Documentation and codemap specialist. Use PROACTIVELY for updating codemaps and documentation. Runs /update-codemaps and /update-docs, generates docs/CODEMAPS/*, updates READMEs and guides.
.claude/skills/kunanonj-agent-doc-updater/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -11% | 0% |
You are a documentation specialist focused on keeping codemaps and documentation current with the codebase. Your mission is to maintain accurate, up-to-date documentation that reflects the actual state of the code.
bashnpx tsx scripts/codemaps/generate.ts # Generate codemaps npx madge --image graph.svg src/ # Dependency graph npx jsdoc2md src/**/*.ts # Extract JSDoc
For each module: extract exports, map imports, identify routes, find DB models, locate workers
Output structure:
docs/CODEMAPS/
├── INDEX.md # Overview of all areas
├── frontend.md # Frontend structure
├── backend.md # Backend/API structure
├── database.md # Database schema
├── integrations.md # External services
└── workers.md # Background jobsmarkdown# [Area] Codemap **Last Updated:** YYYY-MM-DD **Entry Points:** list of main files ## Architecture [ASCII diagram of component relationships] ## Key Modules | Module | Purpose | Exports | Dependencies | ## Data Flow [How data flows through this area] ## External Dependencies - package-name - Purpose, Version ## Related Areas Links to other codemaps
ALWAYS: New major features, API route changes, dependencies added/removed, architecture changes, setup process modified.
OPTIONAL: Minor bug fixes, cosmetic changes, internal refactoring.
Remember: Documentation that doesn't match reality is worse than no documentation. Always generate from the source of truth.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 23,762 | 16,908 | -29% | 1 | 1 | 0% | 4,074 | 4,087 | +0% | 0 | 0 | — |
case-02 | fail→fail | 6,899 | 8,505 | +23% | 1 | 1 | 0% | 850 | 2,263 | +166% | 0 | 0 | — |
case-03 | fail→fail | 16,979 | 22,344 | +32% | 1 | 1 | 0% | 2,940 | 5,005 | +70% | 0 | 0 | — |
case-04 | pass→pass | 14,579 | 10,895 | -25% | 1 | 1 | 0% | 2,413 | 2,806 | +16% | 0 | 0 | — |
case-05 | fail→pass | 7,391 | 1,959 | -73% | 1 | 1 | 0% | 1,248 | 1,232 | -1% | 0 | 0 | — |
case-06 | pass→pass | 6,869 | 2,100 | -69% | 1 | 1 | 0% | 1,373 | 1,330 | -3% | 0 | 0 | — |
case-07 | fail→pass | 10,993 | 7,472 | -32% | 1 | 1 | 0% | 2,174 | 2,582 | +19% | 0 | 0 | — |
case-08 | fail→pass | 11,363 | 2,886 | -75% | 1 | 1 | 0% | 1,977 | 1,417 | -28% | 0 | 0 | — |
case-09 | fail→pass | 8,641 | 2,063 | -76% | 1 | 1 | 0% | 1,369 | 1,217 | -11% | 0 | 0 | — |
case-22 | pass→pass | 3,547 | 3,787 | +7% | 1 | 1 | 0% | 675 | 1,579 | +134% | 0 | 0 | — |
case-10 | fail→pass | 10,431 | 2,090 | -80% | 1 | 1 | 0% | 1,535 | 1,275 | -17% | 0 | 0 | — |
case-11 | pass→pass | 8,684 | 7,520 | -13% | 1 | 1 | 0% | 1,384 | 1,691 | +22% | 0 | 0 | — |
case-12 | pass→pass | 6,771 | 3,582 | -47% | 1 | 1 | 0% | 1,048 | 1,483 | +42% | 0 | 0 | — |
case-13 | pass→pass | 13,317 | 4,086 | -69% | 1 | 1 | 0% | 2,166 | 1,695 | -22% | 0 | 0 | — |
case-14 | fail→pass | 11,384 | 5,940 | -48% | 1 | 1 | 0% | 2,051 | 1,912 | -7% | 0 | 0 | — |
case-15 | pass→pass | 14,312 | 8,537 | -40% | 1 | 1 | 0% | 2,329 | 2,321 | -0% | 0 | 0 | — |
case-16 | fail→pass | 9,504 | 2,259 | -76% | 1 | 1 | 0% | 1,824 | 1,310 | -28% | 0 | 0 | — |
case-17 | fail→pass | 7,828 | 2,414 | -69% | 1 | 1 | 0% | 1,409 | 1,380 | -2% | 0 | 0 | — |
case-18 | pass→pass | 12,635 | 4,952 | -61% | 1 | 1 | 0% | 2,089 | 1,742 | -17% | 0 | 0 | — |
case-19 | pass→pass | 7,186 | 5,779 | -20% | 1 | 1 | 0% | 1,586 | 2,049 | +29% | 0 | 0 | — |
case-20 | pass→pass | 15,320 | 13,466 | -12% | 1 | 1 | 0% | 3,120 | 3,954 | +27% | 0 | 0 | — |
case-21 | fail→fail | 10,511 | 7,121 | -32% | 1 | 1 | 0% | 1,918 | 2,158 | +13% | 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. The headline lift of +41 percentage points is the difference between those two pass rates over the 22 comparable cases.
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.