Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to create, optimize, or structure a documentation site. Also use when the user mentions "docs," "documentation site," "docs subdomain," "docs.yourdomain.com," "help center," "knowledge base," "Getting Started," "API Reference," "user guides," or "tutorials." For API marketing landing, use api-page-generator.
.claude/skills/kostja94-docs-page-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-20 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-12 | ✓→✗ | ▼ Worse | 22% | 0% |
Guides documentation site structure, navigation, and content organization. Typically hosted on docs.* or help.* subdomain. Includes Getting Started, guides, tutorials, API Reference (endpoint docs), and troubleshooting. Distinct from API introduction page (api-page-generator).
When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read it for product, audience, and use cases.
Identify:
| Section | Purpose | Typical Content | |---------|---------|-----------------| | Getting Started | Onboarding, first steps | Quick start, installation, first task | | Guides / Tutorials | Step-by-step learning | How-to articles, workflows | | Concepts | Background, architecture | Key concepts, glossary links | | API Reference | Endpoint docs | Auth, request/response, examples; part of docs, not separate page | | Troubleshooting | Problem solving | FAQ, common errors, support links |
API Reference is a section of docs, not a standalone page. Include: endpoints by resource, auth, request/response schemas, error codes, rate limits, code examples (cURL, SDKs). Use OpenAPI/Swagger for consistency.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 17,761 | 16,922 | -5% | 1 | 1 | 0% | 3,477 | 3,553 | +2% | 0 | 0 | — |
case-02 | fail→pass | 23,856 | 12,913 | -46% | 1 | 1 | 0% | 4,563 | 3,004 | -34% | 0 | 0 | — |
case-03 | pass→pass | 16,775 | 13,132 | -22% | 1 | 1 | 0% | 3,292 | 3,174 | -4% | 0 | 0 | — |
case-04 | pass→pass | 14,938 | 9,468 | -37% | 1 | 1 | 0% | 3,404 | 2,698 | -21% | 0 | 0 | — |
case-05 | pass→pass | 18,848 | 23,197 | +23% | 1 | 1 | 0% | 3,734 | 4,708 | +26% | 0 | 0 | — |
case-06 | pass→pass | 14,250 | 11,858 | -17% | 1 | 1 | 0% | 2,514 | 2,818 | +12% | 0 | 0 | — |
case-07 | fail→pass | 8,932 | 8,365 | -6% | 1 | 1 | 0% | 1,809 | 2,194 | +21% | 0 | 0 | — |
case-08 | fail→pass | 13,152 | 10,704 | -19% | 1 | 1 | 0% | 2,066 | 2,532 | +23% | 0 | 0 | — |
case-09 | pass→pass | 12,061 | 8,612 | -29% | 1 | 1 | 0% | 2,479 | 2,361 | -5% | 0 | 0 | — |
case-10 | fail→fail | 12,833 | 9,600 | -25% | 1 | 1 | 0% | 2,621 | 2,593 | -1% | 0 | 0 | — |
case-11 | pass→pass | 9,730 | 7,941 | -18% | 1 | 1 | 0% | 1,829 | 2,043 | +12% | 0 | 0 | — |
case-12 | pass→fail | 11,652 | 11,578 | -1% | 1 | 1 | 0% | 2,234 | 2,734 | +22% | 0 | 0 | — |
case-13 | pass→pass | 11,383 | 10,300 | -10% | 1 | 1 | 0% | 1,903 | 2,430 | +28% | 0 | 0 | — |
case-18 | pass→pass | 14,045 | 9,358 | -33% | 1 | 1 | 0% | 2,721 | 2,409 | -11% | 0 | 0 | — |
case-14 | pass→pass | 14,967 | 18,205 | +22% | 1 | 1 | 0% | 2,906 | 4,053 | +39% | 0 | 0 | — |
case-15 | pass→pass | 13,033 | 11,061 | -15% | 1 | 1 | 0% | 2,781 | 3,089 | +11% | 0 | 0 | — |
case-16 | pass→pass | 14,347 | 9,317 | -35% | 1 | 1 | 0% | 2,434 | 2,218 | -9% | 0 | 0 | — |
case-17 | pass→pass | 12,145 | 10,087 | -17% | 1 | 1 | 0% | 2,140 | 2,789 | +30% | 0 | 0 | — |
case-19 | pass→pass | 13,883 | 9,224 | -34% | 1 | 1 | 0% | 2,527 | 2,253 | -11% | 0 | 0 | — |
case-20 | fail→pass | 12,370 | 4,876 | -61% | 1 | 1 | 0% | 2,227 | 1,564 | -30% | 0 | 0 | — |
case-21 | pass→pass | 16,006 | 9,489 | -41% | 1 | 1 | 0% | 2,753 | 2,311 | -16% | 0 | 0 | — |
case-22 | pass→pass | 9,875 | 8,424 | -15% | 1 | 1 | 0% | 1,775 | 2,174 | +22% | 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 +14 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.