[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PEB7P9HVB1W3ABD73FRTKH":3,"skill-same:01M6PEB7P9HVB1W3ABD73FRTKH":102},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":37,"publishedAt":58,"linkOnly":59,"markdownContent":60,"markdownBody":61,"frontMatter":62,"refName":68,"commitSha":69,"skillDirectory":70,"forksCount":14,"repositoryHtmlUrl":71,"repositoryHomepageUrl":6,"ownerHtmlUrl":72,"ownerBlogUrl":73,"ownerDescription":6,"updatedAt":74,"install":75,"resources":87},"01M6PEB7P9HVB1W3ABD73FRTKH","api-docs-quality-report",null,"Audits any API documentation site by crawling every endpoint page and scoring each one across 5 checks: description quality, OpenAPI spec presence, body param descriptions, response codes, and response schema completeness. Produces a polished interactive HTML report with a summary scorecard, site-wide pattern analysis, ranked top issues, and per-endpoint findings with specific fix guidance.\nTrigger this skill whenever a user provides a documentation URL and asks to audit, review, analyse, or check their API docs. Also trigger for: \"do the same audit for X\", \"audit docs.company.com\", \"check the API docs at X\", \"run the API docs audit on X\", \"review the docs for Y API\", or pastes a URL alongside words like audit, review, crawl, check, analyse, quality, completeness, or gaps. Always use this skill — do not attempt the audit without following this structured crawl-score-report workflow.","headmktlucca-ui\u002Fneuroads-lp","headmktlucca-ui","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F247379838?v=4","01M6PDVAV6M1W96D1SR1PDF8CS","NeuroAds","01M6PDVAZ4P281GNDKD45CYTF5",0,"MIT","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fapi-docs-quality-report\u002FSKILL.md",[18,23,26,29,34],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":30,"categoryName":31,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":35,"categoryName":36,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000034","行政与办公人员",[38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"docs","api docs quality report","quality report","quality","api","report","analysis","issues","html report","fix","crawl","scoring","across","api-docs","URL","presence","scorecard","company","workflow","review","2026-11-10 10:12:30",false,"---\nname: api-docs-quality-report\ndescription: >\n  Audits any API documentation site by crawling every endpoint page and scoring each one\n  across 5 checks: description quality, OpenAPI spec presence, body param descriptions,\n  response codes, and response schema completeness. Produces a polished interactive HTML\n  report with a summary scorecard, site-wide pattern analysis, ranked top issues, and\n  per-endpoint findings with specific fix guidance.\n\n  Trigger this skill whenever a user provides a documentation URL and asks to audit, review,\n  analyse, or check their API docs. Also trigger for: \"do the same audit for X\", \"audit\n  docs.company.com\", \"check the API docs at X\", \"run the API docs audit on X\", \"review the\n  docs for Y API\", or pastes a URL alongside words like audit, review, crawl, check, analyse,\n  quality, completeness, or gaps. Always use this skill — do not attempt the audit\n  without following this structured crawl-score-report workflow.\nuser-invokable: true\nargument-hint: \"\u003Cdocs_url>\"\nlicense: MIT\nmetadata:\n  version: \"1.0.0\"\n  category: api-docs\n---\n\n# API Docs Audit Skill\n\nCrawls every API reference endpoint page on a documentation site, scores each against\n5 quality checks, detects site-wide patterns, and outputs an interactive HTML report\nmatching the style of previously-generated audits in this session.\n\n---\n\n## STEP 0 — COLLECT INPUT\n\nYou need exactly one input: the docs URL.\n\nIf the user hasn't provided it, ask:\n> Which API docs URL should I audit?\n\nIf the URL is provided, strip trailing slashes and confirm it before proceeding.\n\n**Special case — \"do the same for X\":**\nIf the user says \"do the same\" or \"same audit for X\", they want the identical workflow\nand HTML report format applied to the new URL. Proceed directly to Step 1.\n\n---\n\n## STEP 1 — DISCOVER ALL ENDPOINT PAGES\n\n### 1a. Try llms.txt first\n\nFetch `\u003Cdocs_url>\u002Fllms.txt`.\n\nIf found:\n- Extract every line matching the pattern `- [Page Title](URL): description`\n- Filter to API reference pages only — look for paths containing any of:\n  `api-reference`, `api-reference\u002F`, `\u002Fapi\u002F`, `\u002Fendpoints\u002F`, `\u002Frest\u002F`, `\u002Fdocs\u002F`, `\u002Freference\u002F` or versioned paths (e.g., `\u002Fv1\u002F`)\n- Exclude: overview\u002Findex pages (no HTTP method implied), SDK docs, CLI docs,\n  Terraform docs, guides, quickstart pages\n- Store as `ENDPOINT_PAGES[]` — list of `{title, url, description}`\n\nIf not found or returns 404:\n- Fetch the docs homepage\n- Look for a nav sidebar or sitemap link referencing API\u002Fendpoints\n- Extract all API reference page URLs from the nav structure\n- Note in the report that llms.txt was unavailable\n\n### 1b. Identify categories\n\nGroup discovered pages by their URL path prefix or nav section:\n- e.g. `\u002Fapi-reference\u002Fagents\u002F` → Agents category\n- e.g. `\u002Fapi-reference\u002Fexecutions\u002F` → Executions category\n- Pages at the root level of api-reference → Uncategorized or infer from title\n\nStore `CATEGORIES[]` — list of `{name, page_count, pages[]}`.\n\nReport discovery summary:\n> Found N endpoint pages across K categories. Fetching now...\n\n---\n\n## STEP 2 — CHECK OPENAPI SPEC AVAILABILITY\n\nBefore fetching individual pages, check if a standalone OpenAPI spec exists.\n\nTry these discovery methods in order (stop at first success):\n1. Inspect the `Link` HTTP header (RFC 8288) on the homepage or docs root for `rel=\"openapi\"` or `rel=\"describedby\"` — this is the standard discovery mechanism for API specifications\n2. `\u003Cdocs_url>\u002Fopenapi.json`\n3. `\u003Cdocs_url>\u002Fopenapi.yaml`\n4. `\u003Cdocs_url>\u002Fapi\u002Fopenapi.json`\n5. Any URL referenced in llms.txt under \"## OpenAPI Specs\"\n\n**Result:**\n- If accessible: `SPEC_AVAILABLE = true`, store the URL\n- If 404 on all attempts and no Link header found: `SPEC_AVAILABLE = false`\n\nA missing spec is itself a **top-priority finding** — record it as Issue #1.\n\n---\n\n## STEP 3 — FETCH AND PARSE ALL ENDPOINT PAGES\n\nFetch each URL in `ENDPOINT_PAGES[]`. For each page, extract:\n\n### 3a. Page-level prose description\nThe text that appears **above** the OpenAPI block (or between the `#` title and the\nfirst `## OpenAPI` heading). This is the human-written description.\n\n### 3b. OpenAPI block\nLook for a fenced code block with language hint `yaml` or `json` that contains\nan OpenAPI spec. Extract:\n- `HTTP_METHOD` — e.g. `GET`, `POST`, `PUT`, `DELETE`, `PATCH`\n- `HTTP_PATH` — e.g. `\u002Fapi\u002Fv1\u002Fagents\u002F{agent_id}\u002Fexecute`\n- `REQUEST_BODY_SCHEMA` — the requestBody schema section (if any)\n- `PARAMETERS` — path + query params (if any)\n- `RESPONSES` — the full responses object\n- `RESPONSE_200_SCHEMA` — the schema under responses.200 or 201\n\nIf no OpenAPI block found, mark `SPEC_INLINE = false`.\n\n---\n\n## STEP 4 — SCORE EACH ENDPOINT (5 CHECKS)\n\nFor every endpoint, evaluate all 5 checks. Store results as\n`{check_name: \"pass\"|\"warn\"|\"fail\", current_state: string, fix_guidance: string}`.\n\nRead `references\u002Fscoring-rules.md` for the exact scoring criteria per check.\n\n**Check 1 — Endpoint Description**\n**Check 2 — OpenAPI Spec**\n**Check 3 — Body Param Descriptions**\n**Check 4 — Response Codes**\n**Check 5 — Response Schema**\n\n---\n\n## STEP 5 — DETECT SITE-WIDE PATTERNS\n\nAfter scoring all endpoints, look for patterns that repeat across many pages.\n\nA pattern qualifies if it affects **≥ 60% of endpoints**:\n\n| Pattern to detect | How to identify |\n|---|---|\n| Universal missing error codes | All endpoints missing 401, 429, 500 etc. |\n| Universal empty response schemas | `schema: {}` on most endpoints |\n| Free-form body schemas | `additionalProperties: true` on most request bodies |\n| Inline spec only \u002F broken canonical spec | All pages embed spec inline but canonical 404s |\n| One-liner descriptions everywhere | Descriptions under 10 words on most pages |\n| 422-only validation errors | Only FastAPI's 422 documented, not business errors |\n\nFor each detected pattern, write a **single paragraph** summarising:\n- What the pattern is\n- How many endpoints it affects\n- Root cause (e.g. FastAPI auto-generation, missing middleware docs)\n- Impact on developer experience\n\nStore as `SITE_WIDE_PATTERNS[]`.\n\n---\n\n## STEP 6 — COMPILE TOP ISSUES\n\nRank the **10 most impactful issues** across all findings. Prioritise by:\n\n1. Issues affecting the most endpoints\n2. Issues on the highest-traffic \u002F most important endpoints\n3. Security-sensitive gaps (auth endpoints, credential endpoints with empty schemas)\n4. Deprecated endpoints with no migration path\n5. Spec availability (404 canonical spec blocks all SDK tooling)\n\nFor each issue, write:\n- A concise `\u003Cstrong>title\u003C\u002Fstrong>`\n- 1-2 sentence description with specific endpoint names or counts\n- Badge: FAIL or WARN\n\nStore as `TOP_ISSUES[]` (max 10).\n\n---\n\n## STEP 7 — BUILD SCORECARD\n\nFor each category, calculate:\n- `total` — endpoint count\n- `pass_count` — endpoints with all 5 checks passing\n- `warn_count` — endpoints with at least one WARN and no FAIL\n- `fail_count` — endpoints with at least one FAIL\n\nCalculate overall totals.\n\nStore as `SCORECARD[]`.\n\n---\n\n## STEP 8 — GENERATE HTML REPORT\n\nRead `references\u002Fhtml-template.md` for the complete HTML structure, CSS variables,\nJavaScript, and all section markup.\n\nSubstitute all `{{VARIABLE}}` placeholders with real audit data, ensuring all values are HTML-escaped to prevent XSS.\n\n**Key variable map:**\n\n| Variable | Source |\n|---|---|\n| `{{DOCS_URL}}` | Input URL |\n| `{{AUDIT_DATE}}` | Today's date |\n| `{{TOTAL_ENDPOINTS}}` | Count of ENDPOINT_PAGES |\n| `{{TOTAL_PASS}}` | Sum of all pass_count across categories |\n| `{{TOTAL_WARN}}` | Sum of all warn_count |\n| `{{TOTAL_FAIL}}` | Sum of all fail_count |\n| `{{SPEC_COUNT}}` | 1 if SPEC_AVAILABLE, else 0 |\n| `{{SCORECARD_ROWS}}` | Generated `\u003Ctr>` rows from SCORECARD |\n| `{{PATTERN_BOX}}` | Pattern box HTML (if SITE_WIDE_PATTERNS found) |\n| `{{TOP_ISSUES_HTML}}` | Generated issue row HTML from TOP_ISSUES |\n| `{{SIDEBAR_LINKS}}` | Generated sidebar `\u003Cdiv class=\"sbl\">` links |\n| `{{SECTIONS_HTML}}` | All section HTML for each category |\n\nFor section HTML generation rules, see `references\u002Fhtml-template.md` → Section: SECTIONS_HTML.\n\n**Output the file to:**\n```\n\u002Fmnt\u002Fuser-data\u002Foutputs\u002F\u003Cslug>-api-audit-report.html\n```\nWhere `\u003Cslug>` is the domain name with dots replaced by hyphens\n(e.g. `docs.kubiya.ai` → `kubiya-ai`).\n\nThen call `present_files` to deliver it.\n\n---\n\n## ERROR HANDLING\n\n| Situation | Action |\n|---|---|\n| `llms.txt` returns 404 | Crawl nav links from homepage; note in report |\n| Individual endpoint page returns 404 | Skip it; add to \"inaccessible pages\" count in footer |\n| Page has no OpenAPI block | Score Spec check as FAIL; still score other checks from prose |\n| Page has no prose description | Score Description as FAIL with note \"No prose description\" |\n| Endpoint page is robots.txt blocked | Note in report; do not fetch |\n| More than 200 endpoints found | Batch fetching — process in groups of 20, progress-report to user |\n| Canonical spec accessible | Note as positive finding; do not flag as issue |\n\n---\n\n## WHAT NOT TO DO\n\n- ❌ Never start generating HTML before all pages are fetched and scored\n- ❌ Never skip an endpoint page — fetch every one listed in llms.txt\n- ❌ Never infer scores from page titles alone — fetch the actual page content\n- ❌ Never mark Response Codes as PASS just because 200 is documented\n- ❌ Never mark Response Schema as PASS for `schema: {}` — that is FAIL\n- ❌ Never mark Body Params as PASS for `additionalProperties: true` — that is WARN at minimum\n- ❌ Never report a pattern as site-wide unless it affects ≥ 60% of endpoints\n- ❌ Never put generic fix text — every fix_guidance must reference the specific endpoint\n\n---\n\n## REFERENCE FILES\n\n- `references\u002Fscoring-rules.md` — Exact PASS\u002FWARN\u002FFAIL criteria for all 5 checks,\n  with worked examples. **Read before scoring any endpoint.**\n\n- `references\u002Fhtml-template.md` — Complete HTML\u002FCSS\u002FJS template with all section\n  markup, variable map, and rendering instructions.\n  **Read before writing any HTML.**","# API Docs Audit Skill\n\nCrawls every API reference endpoint page on a documentation site, scores each against\n5 quality checks, detects site-wide patterns, and outputs an interactive HTML report\nmatching the style of previously-generated audits in this session.\n\n---\n\n## STEP 0 — COLLECT INPUT\n\nYou need exactly one input: the docs URL.\n\nIf the user hasn't provided it, ask:\n> Which API docs URL should I audit?\n\nIf the URL is provided, strip trailing slashes and confirm it before proceeding.\n\n**Special case — \"do the same for X\":**\nIf the user says \"do the same\" or \"same audit for X\", they want the identical workflow\nand HTML report format applied to the new URL. Proceed directly to Step 1.\n\n---\n\n## STEP 1 — DISCOVER ALL ENDPOINT PAGES\n\n### 1a. Try llms.txt first\n\nFetch `\u003Cdocs_url>\u002Fllms.txt`.\n\nIf found:\n- Extract every line matching the pattern `- [Page Title](URL): description`\n- Filter to API reference pages only — look for paths containing any of:\n  `api-reference`, `api-reference\u002F`, `\u002Fapi\u002F`, `\u002Fendpoints\u002F`, `\u002Frest\u002F`, `\u002Fdocs\u002F`, `\u002Freference\u002F` or versioned paths (e.g., `\u002Fv1\u002F`)\n- Exclude: overview\u002Findex pages (no HTTP method implied), SDK docs, CLI docs,\n  Terraform docs, guides, quickstart pages\n- Store as `ENDPOINT_PAGES[]` — list of `{title, url, description}`\n\nIf not found or returns 404:\n- Fetch the docs homepage\n- Look for a nav sidebar or sitemap link referencing API\u002Fendpoints\n- Extract all API reference page URLs from the nav structure\n- Note in the report that llms.txt was unavailable\n\n### 1b. Identify categories\n\nGroup discovered pages by their URL path prefix or nav section:\n- e.g. `\u002Fapi-reference\u002Fagents\u002F` → Agents category\n- e.g. `\u002Fapi-reference\u002Fexecutions\u002F` → Executions category\n- Pages at the root level of api-reference → Uncategorized or infer from title\n\nStore `CATEGORIES[]` — list of `{name, page_count, pages[]}`.\n\nReport discovery summary:\n> Found N endpoint pages across K categories. Fetching now...\n\n---\n\n## STEP 2 — CHECK OPENAPI SPEC AVAILABILITY\n\nBefore fetching individual pages, check if a standalone OpenAPI spec exists.\n\nTry these discovery methods in order (stop at first success):\n1. Inspect the `Link` HTTP header (RFC 8288) on the homepage or docs root for `rel=\"openapi\"` or `rel=\"describedby\"` — this is the standard discovery mechanism for API specifications\n2. `\u003Cdocs_url>\u002Fopenapi.json`\n3. `\u003Cdocs_url>\u002Fopenapi.yaml`\n4. `\u003Cdocs_url>\u002Fapi\u002Fopenapi.json`\n5. Any URL referenced in llms.txt under \"## OpenAPI Specs\"\n\n**Result:**\n- If accessible: `SPEC_AVAILABLE = true`, store the URL\n- If 404 on all attempts and no Link header found: `SPEC_AVAILABLE = false`\n\nA missing spec is itself a **top-priority finding** — record it as Issue #1.\n\n---\n\n## STEP 3 — FETCH AND PARSE ALL ENDPOINT PAGES\n\nFetch each URL in `ENDPOINT_PAGES[]`. For each page, extract:\n\n### 3a. Page-level prose description\nThe text that appears **above** the OpenAPI block (or between the `#` title and the\nfirst `## OpenAPI` heading). This is the human-written description.\n\n### 3b. OpenAPI block\nLook for a fenced code block with language hint `yaml` or `json` that contains\nan OpenAPI spec. Extract:\n- `HTTP_METHOD` — e.g. `GET`, `POST`, `PUT`, `DELETE`, `PATCH`\n- `HTTP_PATH` — e.g. `\u002Fapi\u002Fv1\u002Fagents\u002F{agent_id}\u002Fexecute`\n- `REQUEST_BODY_SCHEMA` — the requestBody schema section (if any)\n- `PARAMETERS` — path + query params (if any)\n- `RESPONSES` — the full responses object\n- `RESPONSE_200_SCHEMA` — the schema under responses.200 or 201\n\nIf no OpenAPI block found, mark `SPEC_INLINE = false`.\n\n---\n\n## STEP 4 — SCORE EACH ENDPOINT (5 CHECKS)\n\nFor every endpoint, evaluate all 5 checks. Store results as\n`{check_name: \"pass\"|\"warn\"|\"fail\", current_state: string, fix_guidance: string}`.\n\nRead `references\u002Fscoring-rules.md` for the exact scoring criteria per check.\n\n**Check 1 — Endpoint Description**\n**Check 2 — OpenAPI Spec**\n**Check 3 — Body Param Descriptions**\n**Check 4 — Response Codes**\n**Check 5 — Response Schema**\n\n---\n\n## STEP 5 — DETECT SITE-WIDE PATTERNS\n\nAfter scoring all endpoints, look for patterns that repeat across many pages.\n\nA pattern qualifies if it affects **≥ 60% of endpoints**:\n\n| Pattern to detect | How to identify |\n|---|---|\n| Universal missing error codes | All endpoints missing 401, 429, 500 etc. |\n| Universal empty response schemas | `schema: {}` on most endpoints |\n| Free-form body schemas | `additionalProperties: true` on most request bodies |\n| Inline spec only \u002F broken canonical spec | All pages embed spec inline but canonical 404s |\n| One-liner descriptions everywhere | Descriptions under 10 words on most pages |\n| 422-only validation errors | Only FastAPI's 422 documented, not business errors |\n\nFor each detected pattern, write a **single paragraph** summarising:\n- What the pattern is\n- How many endpoints it affects\n- Root cause (e.g. FastAPI auto-generation, missing middleware docs)\n- Impact on developer experience\n\nStore as `SITE_WIDE_PATTERNS[]`.\n\n---\n\n## STEP 6 — COMPILE TOP ISSUES\n\nRank the **10 most impactful issues** across all findings. Prioritise by:\n\n1. Issues affecting the most endpoints\n2. Issues on the highest-traffic \u002F most important endpoints\n3. Security-sensitive gaps (auth endpoints, credential endpoints with empty schemas)\n4. Deprecated endpoints with no migration path\n5. Spec availability (404 canonical spec blocks all SDK tooling)\n\nFor each issue, write:\n- A concise `\u003Cstrong>title\u003C\u002Fstrong>`\n- 1-2 sentence description with specific endpoint names or counts\n- Badge: FAIL or WARN\n\nStore as `TOP_ISSUES[]` (max 10).\n\n---\n\n## STEP 7 — BUILD SCORECARD\n\nFor each category, calculate:\n- `total` — endpoint count\n- `pass_count` — endpoints with all 5 checks passing\n- `warn_count` — endpoints with at least one WARN and no FAIL\n- `fail_count` — endpoints with at least one FAIL\n\nCalculate overall totals.\n\nStore as `SCORECARD[]`.\n\n---\n\n## STEP 8 — GENERATE HTML REPORT\n\nRead `references\u002Fhtml-template.md` for the complete HTML structure, CSS variables,\nJavaScript, and all section markup.\n\nSubstitute all `{{VARIABLE}}` placeholders with real audit data, ensuring all values are HTML-escaped to prevent XSS.\n\n**Key variable map:**\n\n| Variable | Source |\n|---|---|\n| `{{DOCS_URL}}` | Input URL |\n| `{{AUDIT_DATE}}` | Today's date |\n| `{{TOTAL_ENDPOINTS}}` | Count of ENDPOINT_PAGES |\n| `{{TOTAL_PASS}}` | Sum of all pass_count across categories |\n| `{{TOTAL_WARN}}` | Sum of all warn_count |\n| `{{TOTAL_FAIL}}` | Sum of all fail_count |\n| `{{SPEC_COUNT}}` | 1 if SPEC_AVAILABLE, else 0 |\n| `{{SCORECARD_ROWS}}` | Generated `\u003Ctr>` rows from SCORECARD |\n| `{{PATTERN_BOX}}` | Pattern box HTML (if SITE_WIDE_PATTERNS found) |\n| `{{TOP_ISSUES_HTML}}` | Generated issue row HTML from TOP_ISSUES |\n| `{{SIDEBAR_LINKS}}` | Generated sidebar `\u003Cdiv class=\"sbl\">` links |\n| `{{SECTIONS_HTML}}` | All section HTML for each category |\n\nFor section HTML generation rules, see `references\u002Fhtml-template.md` → Section: SECTIONS_HTML.\n\n**Output the file to:**\n```\n\u002Fmnt\u002Fuser-data\u002Foutputs\u002F\u003Cslug>-api-audit-report.html\n```\nWhere `\u003Cslug>` is the domain name with dots replaced by hyphens\n(e.g. `docs.kubiya.ai` → `kubiya-ai`).\n\nThen call `present_files` to deliver it.\n\n---\n\n## ERROR HANDLING\n\n| Situation | Action |\n|---|---|\n| `llms.txt` returns 404 | Crawl nav links from homepage; note in report |\n| Individual endpoint page returns 404 | Skip it; add to \"inaccessible pages\" count in footer |\n| Page has no OpenAPI block | Score Spec check as FAIL; still score other checks from prose |\n| Page has no prose description | Score Description as FAIL with note \"No prose description\" |\n| Endpoint page is robots.txt blocked | Note in report; do not fetch |\n| More than 200 endpoints found | Batch fetching — process in groups of 20, progress-report to user |\n| Canonical spec accessible | Note as positive finding; do not flag as issue |\n\n---\n\n## WHAT NOT TO DO\n\n- ❌ Never start generating HTML before all pages are fetched and scored\n- ❌ Never skip an endpoint page — fetch every one listed in llms.txt\n- ❌ Never infer scores from page titles alone — fetch the actual page content\n- ❌ Never mark Response Codes as PASS just because 200 is documented\n- ❌ Never mark Response Schema as PASS for `schema: {}` — that is FAIL\n- ❌ Never mark Body Params as PASS for `additionalProperties: true` — that is WARN at minimum\n- ❌ Never report a pattern as site-wide unless it affects ≥ 60% of endpoints\n- ❌ Never put generic fix text — every fix_guidance must reference the specific endpoint\n\n---\n\n## REFERENCE FILES\n\n- `references\u002Fscoring-rules.md` — Exact PASS\u002FWARN\u002FFAIL criteria for all 5 checks,\n  with worked examples. **Read before scoring any endpoint.**\n\n- `references\u002Fhtml-template.md` — Complete HTML\u002FCSS\u002FJS template with all section\n  markup, variable map, and rendering instructions.\n  **Read before writing any HTML.**",{"name":5,"license":15,"metadata":63,"description":65,"argument-hint":66,"user-invokable":67},{"version":64,"category":51},"1.0.0","Audits any API documentation site by crawling every endpoint page and scoring each one across 5 checks: description quality, OpenAPI spec presence, body param descriptions, response codes, and response schema completeness. Produces a polished interactive HTML report with a summary scorecard, site-wide pattern analysis, ranked top issues, and per-endpoint findings with specific fix guidance.\nTrigger this skill whenever a user provides a documentation URL and asks to audit, review, analyse, or check their API docs. Also trigger for: \"do the same audit for X\", \"audit docs.company.com\", \"check the API docs at X\", \"run the API docs audit on X\", \"review the docs for Y API\", or pastes a URL alongside words like audit, review, crawl, check, analyse, quality, completeness, or gaps. Always use this skill — do not attempt the audit without following this structured crawl-score-report workflow.\n","\u003Cdocs_url>",true,"main","7a940b8e5af16c95e5c190a524421d32fc7445a9",".agent\u002Fskills\u002Fapi-docs-quality-report","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui","https:\u002F\u002Fneuroads.com.br","2026-08-12 00:42:44",{"source":8,"skillName":5,"commands":76,"prompt":86,"zipAvailable":67},[77,80,83],{"tool":78,"command":79},"npx","npx skills add headmktlucca-ui\u002Fneuroads-lp --skill api-docs-quality-report",{"tool":81,"command":82},"bunx","bunx skills add headmktlucca-ui\u002Fneuroads-lp --skill api-docs-quality-report",{"tool":84,"command":85},"pnpm","pnpm dlx skills add headmktlucca-ui\u002Fneuroads-lp --skill api-docs-quality-report","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fapi-docs-quality-report\u002FSKILL.md",[88,94,98],{"path":89,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":92,"sourceHtmlUrl":93},"README.md","REFERENCE","参考文档",5258,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fapi-docs-quality-report\u002FREADME.md",{"path":95,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fhtml-template.md",25628,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fapi-docs-quality-report\u002Freferences\u002Fhtml-template.md",{"path":99,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fscoring-rules.md",9084,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fapi-docs-quality-report\u002Freferences\u002Fscoring-rules.md",[103,125,150,176,193,224],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":113,"publishedAt":58},"01M6PTDCZTXTGSTX4RFK901YSZ","xunit-skill","Generates xUnit.net tests in C#. Covers Fact\u002FTheory, constructor injection, IClassFixture, and FluentAssertions. Use when user mentions \"xUnit\", \"[Fact]\", \"[Theory]\", \"Assert.Equal\", \"C# xUnit\". Triggers on: \"xUnit\", \"[Fact]\", \"[Theory]\", \"Assert.Equal C#\", \"xUnit.net\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fxunit-skill\u002FSKILL.md",[109,112],{"categoryNo":110,"categoryName":111,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[114,115,116,117,118,119,120,121,122,123,124],"xunit","xunit skill","testing","injection","user","use","tests","triggers","unit","unit-testing","C#",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":133,"publishedAt":58},"01M6PTCB59ZTG5FTMWGPYEMMBP","xcuitest-skill","Generates XCUITest UI tests for iOS\u002FiPadOS apps in Swift. Apple's native testing framework for reliable, fast UI automation. Supports local simulators and TestMu AI cloud real devices. Use when user mentions \"XCUITest\", \"XCTest\", \"iOS UI test\", \"Swift test\", \"XCUIApplication\". Triggers on: \"XCUITest\", \"XCTest UI\", \"iOS UI test\", \"Swift UI test\", \"XCUIApplication\", \"TestMu\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fxcuitest-skill\u002FSKILL.md",[131,132],{"categoryNo":110,"categoryName":111,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[134,135,116,136,137,138,139,140,119,141,142,143,144,145,120,121,146,147,148,149],"xcuitest","xcuitest skill","automation","test","testing framework","ios","devices","mobile","mobile-testing","ui test","local","apple","apps","native","for","objective",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":160,"publishedAt":58},"01M6PTATMNTY9NF4J7KSR76YK6","world-builder","Create and manage generative game zones for Dorothy's Pokemon-style world. Use this skill when creating, updating, or designing game worlds via MCP tools.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fworld-builder\u002FSKILL.md",[156,159],{"categoryNo":157,"categoryName":158,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[161,162,163,164,165,166,167,168,119,169,170,171,172,173,174,148,175],"builder","world","world builder","MCP","create","mcp tools","Tools","game","pokemon","manage","style","via","theme","zone","generative",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":184,"publishedAt":58},"01M6PT9Z92JTSQEHE1QR0NNW5F","webdriverio-skill","Generates WebdriverIO (WDIO) automation tests in JavaScript or TypeScript. Supports local and TestMu AI cloud. Use when user mentions \"WebdriverIO\", \"WDIO\", \"wdio.conf\", \"browser.url\", \"$\", \"$$\". Triggers on: \"WebdriverIO\", \"WDIO\", \"wdio\", \"browser.$\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwebdriverio-skill\u002FSKILL.md",[182,183],{"categoryNo":110,"categoryName":111,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[185,116,186,136,187,188,189,190,118,119,191,144,120,121,52,192],"webdriverio skill","typescript","javascript","browser","cloud","e2e","e2e-testing","conf",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":204,"publishedAt":58},"01M6PT9NVK36ZWCQ69YXK3FR4K","web-design-guidelines","Web platform design and accessibility guidelines. Use when building web interfaces, auditing accessibility, implementing responsive layouts, or reviewing web UI code. Triggers on tasks involving HTML, CSS, web components, WCAG compliance, responsive design, or web performance.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fweb\u002FSKILL.md",[199,200,201],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":157,"categoryName":158,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":202,"categoryName":203,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000032","设计师",[205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,121,223],"design","web","guidelines","web design guidelines","web design","css","performance","components","web components","tasks","code","web performance","ui","platform design","html","responsive design","responsive","platform","implementing",{"skillNo":225,"name":226,"nameZh":6,"description":227,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":228,"categories":229,"keywords":232,"publishedAt":58},"01M6PT9A3JKRE3X34276F2FW5R","watchos-design-guidelines","Apple Human Interface Guidelines for Apple Watch. Use when building watchOS apps, complications, or workout features. Triggers on tasks involving Watch UI, Digital Crown, glanceable interfaces, or wrist-based interactions.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwatchos\u002FSKILL.md",[230,231],{"categoryNo":157,"categoryName":158,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":202,"categoryName":203,"taxonomyType":32,"taxonomyTypeDesc":33},[205,207,233,214,217,119,234,235,145,222,236,121,146,237,148,238,239],"watchos design guidelines","workout","human","watch","interface","platform-design","features"]