[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EDECRMSDCN7W0QP57X3DAS":3,"skill-same:01M7EDECRMSDCN7W0QP57X3DAS":49},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":13,"repositoryHtmlUrl":25,"repositoryHomepageUrl":6,"ownerHtmlUrl":26,"ownerBlogUrl":6,"ownerDescription":27,"updatedAt":28,"install":29,"resources":42},"01M7EDECRMSDCN7W0QP57X3DAS","sdk-docs-auditor",null,"jonahthan433\u002FCortexOS","jonahthan433","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F211465495?v=4","01M7ECH9HPHGA89DCXHHJBTS3C","jonah.ai","01M7ECH9JCEM45DZMWPT7148S1",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fproductivity\u002Fsdk-docs-auditor\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"# sdk-docs-auditor\n\n# SDK Docs Auditor\n\nProduces a comprehensive, cross-referenced audit of any SDK documentation site with a fully styled downloadable HTML report.\n\n## What this skill does\n\n1. Discovers all SDK pages via `llms.txt` first, falling back to `sitemap.xml` (using curl), then homepage nav crawl\n2. Fetches and reads every relevant SDK page\n3. Audits six fixed sections: Installation, Quick Start, Error Handling, Troubleshooting, Examples, Best Practices\n4. Cross-references every gap across ALL other SDK pages — never flag something as missing if it exists elsewhere\n5. Scores each section 0–100 and assigns a rating tier\n6. Generates a beautiful, self-contained, downloadable HTML report\n\n---\n\n## Step 1 — Discover all SDK pages\n\nUse a three-tier discovery strategy, trying each method in order until one succeeds.\n\n### 1a. Try llms.txt first (preferred)\n\nRun a bash curl command to fetch llms.txt:\n\n```bash\ncurl -s \u003Cdocs_url>\u002Fllms.txt\n```\n\nIf found:\n- Extract every URL from lines matching the pattern `- [Page Title](URL): description`\n- Filter to SDK-relevant pages only — keep URLs whose path contains any of:\n  `sdk`, `installation`, `quickstart`, `quick-start`, `error`, `troubleshoot`, `example`, `best-practice`, `getting-started`, `reference`, `api-reference`, `overview`, `client`, `service`, `memory`, `search`, `worker`, `job`, `policy`, `agent`, `team`\n- Exclude: marketing pages, changelog, blog, legal, community\u002Fforum pages\n- Store as `SDK_PAGES[]` — list of `{title, url, description}`\n- Note in the report: \"Discovery method: llms.txt\"\n\n### 1b. Fallback — Try sitemap.xml\n\nIf llms.txt is unavailable or returns no useful URLs, run a bash curl command to fetch the sitemap:\n\n```bash\ncurl -s \u003Cdocs_url>\u002Fsitemap.xml | python3 -c \"import sys, re; print('\\n'.join(re.findall(r'\u003Cloc>(.*?)\u003C\u002Floc>', sys.stdin.read())))\"\n```\n\nIf the sitemap returns URLs:\n- Parse every `\u003Cloc>` entry to get the full URL list\n- Filter using the same keyword list above\n- Store as `SDK_PAGES[]` — list of `{title, url}`\n- Note in the report: \"Discovery method: sitemap.xml — N total URLs found, M SDK-relevant kept\"\n\nAlso check for a sitemap index (multiple sitemaps) by looking for `\u003Csitemapindex>` in the response. If found, curl each child sitemap and aggregate all URLs before filtering.\n\n### 1c. Final fallback — Homepage nav crawl\n\nIf both llms.txt and sitemap.xml fail, fetch the docs homepage (`\u003Cdocs_url>`) and extract all links from the nav sidebar or sitemap structure, filtering using the same keyword list.\n- Note in the report: \"Discovery method: homepage nav crawl (llms.txt and sitemap.xml unavailable)\"\n\n### 1d. Identify section mapping\n\nFrom the discovered pages, identify which pages map to the six audit targets:\n\n| Audit section | Look for paths\u002Ftitles containing |\n|---|---|\n| Installation | `install`, `setup`, `getting-started` |\n| Quick Start | `quick-start`, `quickstart`, `tutorial` |\n| Error Handling | `error`, `exception`, `errors` |\n| Troubleshooting | `troubleshoot`, `faq`, `debug` |\n| Examples | `example`, `sample`, `cookbook`, `tutorial` |\n| Best Practices | `best-practice`, `guide`, `pattern` |\n\nIf a dedicated page is not found for a section, note it — the absence itself is a finding.\n\n### Build the corpus\n\nAll discovered pages form the **page corpus** used for both section auditing and cross-referencing.\n\nReport discovery summary:\n> Found N pages via [sitemap.xml \u002F llms.txt \u002F nav crawl]. Kept M SDK-relevant pages. Fetching now...\n\n---\n\n## Step 2 — Fetch every page in the corpus\n\nFetch each page using `bash_tool` with `curl`, stripping HTML tags via Python to extract plain text. Do NOT use `web_fetch` for corpus pages — curl is more reliable and avoids permission errors.\n\nUse this pattern for each page URL:\n\n```bash\ncurl -s \"https:\u002F\u002Fdocs.example.com\u002Fsdk\u002Fsome-page\" -L | python3 -c \"\nimport sys, re, html\ncontent = sys.stdin.read()\ncontent = re.sub(r'\u003Cscript[^>]*>.*?\u003C\u002Fscript>', '', content, flags=re.DOTALL)\ncontent = re.sub(r'\u003Cstyle[^>]*>.*?\u003C\u002Fstyle>', '', content, flags=re.DOTALL)\ntext = re.sub(r'\u003C[^>]+>', ' ', content)\ntext = html.unescape(text)\ntext = re.sub(r'\\s+', ' ', text).strip()\nprint(text[:6000])\n\"\n\nBatch multiple pages in a single bash call using a loop to minimise round-trips:\n\n```bash\nfor page in installation quick-start error-handling troubleshooting examples best-practices overview api-reference; do\n  echo \"=== PAGE: $page ===\"\n  curl -s \"https:\u002F\u002Fdocs.example.com\u002Fsdk\u002F$page\" -L | python3 -c \"\nimport sys, re, html\ncontent = sys.stdin.read()\ncontent = re.sub(r'\u003Cscript[^>]*>.*?\u003C\u002Fscript>', '', content, flags=re.DOTALL)\ncontent = re.sub(r'\u003Cstyle[^>]*>.*?\u003C\u002Fstyle>', '', content, flags=re.DOTALL)\ntext = re.sub(r'\u003C[^>]+>', ' ', content)\ntext = html.unescape(text)\ntext = re.sub(r'\\s+', ' ', text).strip()\nprint(text[:6000])\n\"\n  echo \"\"\ndone\n```\n\nFor large sites (>30 pages), prioritise in this order:\n1. The six target section pages (installation, quick-start, error-handling, troubleshooting, examples, best-practices)\n2. Overview \u002F client overview pages\n3. API reference\n4. Service-specific pages (agents, jobs, workers, policies, memory, search, etc.)\n\n---\n\n## Step 3 — Audit the six target sections\n\nFor each of the six sections below, read its page carefully and evaluate against the criteria. Then check every other fetched page to see if any gap is actually addressed elsewhere.\n\n### 3a. Installation\n\n**Must have (deduct heavily if missing):**\n- Prerequisites with exact versions (Python\u002FNode\u002Flanguage version, package manager)\n- At least one complete install command (pip\u002Fnpm\u002Fetc.)\n- Authentication setup with exact steps to obtain and configure credentials\n- A working verification snippet that proves the install succeeded\n- At least one expected output or confirmation of success\n\n**Should have (deduct moderately):**\n- Multiple install methods (package manager, source, Docker)\n- IDE\u002Feditor setup\n- Environment variable configuration with `.env` examples\n- Version compatibility table\n- Optional dependency explanations (what each extra includes)\n- Constructor parameter reference (all params, types, defaults)\n\n**Common gaps to check across other pages:**\n- Env-var auto-detection (does the client read env vars when called with no args?) — check api-reference, overview\n- Advanced constructor params (timeout, retries, org) — check api-reference\n- Version pinning guidance — check any getting-started pages\n\n### 3b. Quick Start\n\n**Must have:**\n- A minimal, numbered step-by-step path a first-time user can follow in under 5 minutes\n- Complete working code from zero to first successful call\n- Expected output for every code snippet\n- Explanation of any prerequisite service\u002Fresource (queues, workers, etc.)\n\n**Should have:**\n- Both env-var and inline credential patterns\n- Multiple install options (pip + poetry, etc.)\n- Links to deeper docs for each concept introduced\n\n**Common gaps to check:**\n- Worker\u002Fqueue prerequisites — check workers\u002Fenvironments pages\n- Valid model\u002Fruntime IDs — check models\u002Fruntimes service pages\n- Execute call signature accuracy — check api-reference and agents service pages\n\n### 3c. Error Handling\n\n**Must have:**\n- Complete exception hierarchy (all exception classes, inheritance tree)\n- Every exception class documented with: description, import path, code example\n- At minimum: authentication, connection, timeout, rate-limit, API\u002FHTTP errors\n- HTTP status code branching (400\u002F401\u002F403\u002F404\u002F500 at minimum)\n- At least one resilience pattern (retry with backoff)\n\n**Should have:**\n- Resource-specific exceptions (one per major service)\n- Streaming error handling\n- Context manager cleanup pattern\n- Testing\u002Fpytest examples for error scenarios\n- Do\u002Fdon't anti-pattern examples\n\n**Cross-reference check — critical:**\n- List every exception class that appears in the api-reference or service pages\n- Flag any that are missing from this page\n- Check execute\u002Fmethod call signatures match across all pages — flag any discrepancies\n\n### 3d. Troubleshooting\n\n**Must have:**\n- Authentication failures with diagnostic steps\n- Connection \u002F timeout issues with solutions\n- At least one service-specific troubleshooting section\n\n**Should have:**\n- Troubleshooting for every major service (workers, jobs, policies, agents, etc.)\n- Self-hosted \u002F custom base_url issues\n- Import errors with correct import paths\n- A summary error-message lookup table\n- Rate limiting with backoff references\n- Actionable \"getting help\" checklist with actual links\u002Fcommands\n\n**Cross-reference check:**\n- For every service page that has its own error handling section, check if its scenarios appear here\n- Check if dataset\u002Fresource creation methods are linked when \"not found\" errors are described\n- Check if health check API is referenced in the \"verify status\" step\n\n### 3e. Examples\n\n**Must have:**\n- At least one complete, runnable end-to-end example per major service\n- Expected output shown for every example\n- Error handling within workflow examples\n\n**Should have:**\n- Coverage across: agent lifecycle, jobs\u002Fscheduling, memory\u002Frecall, semantic search, policy management, worker management, streaming\n- No \"workflow\" examples that only survey resources without executing anything\n- Multi-turn \u002F session management examples where the SDK supports sessions\n\n**Cross-reference check — this is where most gaps accumulate:**\n- For every service that has its own dedicated page with examples, check if those examples are represented here\n- Flag each missing service category with the source page that has the examples\n\n### 3f. Best Practices\n\n**Must have:**\n- Authentication \u002F credential security section\n- Error handling \u002F retry logic\n- Performance (batching, pagination, caching)\n\n**Should have:**\n- One best-practices section per major service (workers, jobs, policies, agents)\n- Resource cleanup \u002F context managers\n- Code organisation (type hints, reusable functions)\n- Testing patterns\n- Concurrency \u002F thread-safety guidance\n- Secret rotation \u002F credential lifecycle\n\n**Cross-reference check:**\n- For every service page that defines its own best practices, check if those patterns appear here\n- Note if concurrency\u002Fthread-safety is addressed anywhere in the entire corpus\n\n---\n\n## Step 4 — Score each section\n\nScore 0–100 using this rubric:\n\n| Score | Meaning |\n|-------|---------|\n| 85–100 | Strong — all must-haves present, most should-haves, few gaps |\n| 70–84 | Good — all must-haves, some should-haves missing |\n| 50–69 | Adequate — most must-haves but notable gaps |\n| 30–49 | Weak — multiple must-haves missing |\n| 0–29 | Poor — section is superficial or largely absent |\n\nAssign a rating label: **Strong \u002F Good \u002F Adequate \u002F Weak \u002F Poor**\n\n---\n\n## Step 5 — Build the gap list for each section\n\nFor every gap:\n- Write a clear one-sentence description of what is missing\n- Tag it with where the content EXISTS in the corpus (if it does): `[covered in: page-name]`\n- Or tag it: `[not covered anywhere in corpus]`\n\nThis distinction is critical — a gap that exists nowhere needs a new page; a gap that exists elsewhere just needs a cross-reference or consolidation.\n\n---\n\n## Step 6 — Derive top priority recommendations\n\nRank the top 6–8 actions by impact × effort. Prioritise:\n1. Factual errors \u002F signature mismatches (highest priority — causes user failures)\n2. Must-have gaps not covered anywhere\n3. Must-have gaps covered elsewhere but not linked\n4. High-value should-have gaps\n5. Cross-referencing and consolidation opportunities\n\n---\n\n## Step 7 — Generate the HTML report\n\nRead the template at `assets\u002Freport-template.html` and inject all audit data into it.\n\nFill these placeholders:\n- `__AUDIT_URL__` → the audited URL\n- `__PAGES_FETCHED__` → total pages fetched\n- `__AUDIT_DATE__` → today's date\n- `__SECTION_DATA_JSON__` → JSON blob (see schema below)\n- `__PRIORITIES_JSON__` → JSON blob (see schema below)\n- `__OVERALL_SCORE__` → integer 0-100 (weighted average of six scores)\n\n### Data schema\n\n```json\n{\n  \"sections\": [\n    {\n      \"num\": \"01\",\n      \"name\": \"Installation Guide\",\n      \"rating\": \"Good\",\n      \"score\": 74,\n      \"strengths\": [\"string\", ...],\n      \"gaps\": [\n        {\n          \"text\": \"Description of the gap\",\n          \"covered_in\": [\"page-name-1\", \"page-name-2\"],\n          \"nowhere\": false\n        }\n      ]\n    }\n  ]\n}\n```\n\nSet `\"nowhere\": true` and `\"covered_in\": []` when the gap exists nowhere in the corpus.\n\n```json\n{\n  \"priorities\": [\n    {\n      \"rank\": 1,\n      \"text\": \"Fix X in Y page. The correct form per api-reference is Z.\",\n      \"type\": \"error\"\n    }\n  ]\n}\n```\n\nPriority types: `\"error\"` (factual mistake), `\"missing\"` (not covered anywhere), `\"xref\"` (covered elsewhere, needs linking), `\"improvement\"` (should-have gap).\n\n---\n\n## Output\n\nSave the final report to `\u002Fmnt\u002Fuser-data\u002Foutputs\u002Fsdk-audit-report.html` and present it with `present_files`.\n\nTell the user:\n- How many pages were fetched\n- The overall score and what it means\n- The single most critical finding\n\nDo NOT reproduce the full report text in the chat — just present the file and give the brief summary.\n",{},"main","38b32c99e7ed0b8e215d638e92cfa452c1ec3079","skills\u002Fimported\u002Fproductivity\u002Fsdk-docs-auditor","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS","https:\u002F\u002Fgithub.com\u002Fjonahthan433","AI Consultant","2026-10-24 05:13:39",{"source":7,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add jonahthan433\u002FCortexOS --skill sdk-docs-auditor",{"tool":35,"command":36},"bunx","bunx skills add jonahthan433\u002FCortexOS --skill sdk-docs-auditor",{"tool":38,"command":39},"pnpm","pnpm dlx skills add jonahthan433\u002FCortexOS --skill sdk-docs-auditor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fproductivity\u002Fsdk-docs-auditor\u002FSKILL.md",true,[43],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},"skill.json","REFERENCE","参考文档",599,"https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fproductivity\u002Fsdk-docs-auditor\u002Fskill.json",[50,56,62,68,74,80],{"skillNo":51,"name":52,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":18},"01M7EDQZDQX3Q8Y7GCQX6KN9V7","opportunity-brief","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fsales\u002Fopportunity-brief\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":18},"01M7EDQYA0V9Y99VKBREJJ3MRT","morning-intel","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Fmorning-intel\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M7EDQVX1JVY0B6PDHKKGM19G","decision-brief","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Fdecision-brief\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M7EDQV1GENZAC2SZSD8KZ3GM","weekly-review","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fweekly-review\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7EDQT2KETJ1Y3CGVN9EKW2J","system-health","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fops\u002Fsystem-health\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7EDQQN2JK3XPWMS1M4T0F3K","backup-restore","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fops\u002Fbackup-restore\u002FSKILL.md",[],[]]