Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →17 Claude Code skills for AI-context, testing, and MCP development. IANA-registered format (application/vnd.faf+yaml). Create .faf project DNA, score AI-readiness (0-100%), sync with CLAUDE.md, build MCP servers, generate test suites. 36,000+ downloads across npm, PyPI, crates.io.
.claude/skills/bilal140202-faf-skills/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 130% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -42% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 129% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -57% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -55% | 0% |
17 skills under the faf: namespace.
| Skill | Purpose | |-------|---------| | faf:context | Generate .faf project DNA for any codebase | | faf:expert | .faf format specialist | | faf:score | AI-readiness scoring (0-100%) | | faf:enhance | Guided improvement to higher tiers | | faf:sync | Bidirectional .faf ↔ CLAUDE.md sync (8ms) | | faf:validate | IANA format compliance | | faf:migrate | Upgrade old formats to current standard | | faf:git | Git practices for .faf files | | faf:docs | Documentation and reference | | faf:platforms | Platform comparison (CLI vs MCP vs claude.ai) | | faf:teacher | Foundational education | | faf:format-inspector | Dual format validation | | faf:mcp-builder | MCP server creation guide | | faf:n8n-builder | n8n workflow creation | | faf:n8n-debugger | n8n debugging | | faf:wjttc-builder | Championship test suite generation | | faf:wjttc-tester | F1-inspired testing |
bashclaude /plugin install faf-skills
The package.json for AI context. IANA-registered (application/vnd.faf+yaml). Define your project once, every AI tool reads it forever.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 6,964 | 11,726 | +68% | 1 | 1 | 0% | 1,251 | 2,883 | +130% | 0 | 0 | — |
case-02 | fail→pass | 12,496 | 4,770 | -62% | 1 | 1 | 0% | 2,237 | 1,289 | -42% | 0 | 0 | — |
case-03 | fail→pass | 3,008 | 3,395 | +13% | 1 | 1 | 0% | 441 | 1,011 | +129% | 0 | 0 | — |
case-04 | fail→pass | 9,150 | 1,200 | -87% | 1 | 1 | 0% | 1,519 | 656 | -57% | 0 | 0 | — |
case-05 | fail→pass | 8,405 | 2,353 | -72% | 1 | 1 | 0% | 1,429 | 640 | -55% | 0 | 0 | — |
case-06 | pass→pass | 10,143 | 2,070 | -80% | 1 | 1 | 0% | 1,854 | 801 | -57% | 0 | 0 | — |
case-07 | fail→pass | 5,063 | 2,084 | -59% | 1 | 1 | 0% | 898 | 810 | -10% | 0 | 0 | — |
case-08 | fail→pass | 10,414 | 2,255 | -78% | 1 | 1 | 0% | 1,791 | 980 | -45% | 0 | 0 | — |
case-09 | pass→pass | 10,193 | 1,505 | -85% | 1 | 1 | 0% | 1,826 | 798 | -56% | 0 | 0 | — |
case-10 | fail→pass | 11,975 | 3,397 | -72% | 1 | 1 | 0% | 2,046 | 1,204 | -41% | 0 | 0 | — |
case-11 | fail→pass | 11,268 | 3,150 | -72% | 1 | 1 | 0% | 2,226 | 1,090 | -51% | 0 | 0 | — |
case-12 | fail→pass | 8,187 | 2,409 | -71% | 1 | 1 | 0% | 1,455 | 939 | -35% | 0 | 0 | — |
case-13 | fail→pass | 11,737 | 3,768 | -68% | 1 | 1 | 0% | 2,046 | 1,208 | -41% | 0 | 0 | — |
case-14 | fail→pass | 12,292 | 3,046 | -75% | 1 | 1 | 0% | 2,029 | 1,056 | -48% | 0 | 0 | — |
case-15 | fail→pass | 10,696 | 1,602 | -85% | 1 | 1 | 0% | 1,712 | 770 | -55% | 0 | 0 | — |
case-16 | fail→pass | 15,208 | 2,047 | -87% | 1 | 1 | 0% | 2,656 | 842 | -68% | 0 | 0 | — |
case-17 | fail→pass | 15,125 | 1,910 | -87% | 1 | 1 | 0% | 2,381 | 779 | -67% | 0 | 0 | — |
case-18 | fail→pass | 17,317 | 3,050 | -82% | 1 | 1 | 0% | 3,285 | 1,033 | -69% | 0 | 0 | — |
case-19 | fail→pass | 6,399 | 2,347 | -63% | 1 | 1 | 0% | 1,053 | 879 | -17% | 0 | 0 | — |
case-20 | pass→pass | 3,026 | 4,055 | +34% | 1 | 1 | 0% | 676 | 1,265 | +87% | 0 | 0 | — |
case-21 | pass→pass | 4,017 | 3,840 | -4% | 1 | 1 | 0% | 741 | 1,148 | +55% | 0 | 0 | — |
case-22 | pass→pass | 2,961 | 2,183 | -26% | 1 | 1 | 0% | 537 | 833 | +55% | 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 +77 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.