Sdk Docs Auditor
Crawl an SDK documentation site, score six standard sections, cross-reference gaps, and download a styled HTML audit report before launch or GTM.
Overview
SDK Docs Auditor is an agent skill most often used in Ship (also Build docs, Launch distribution) that crawls an SDK docs site and delivers a scored, cross-referenced HTML quality report.
Install
npx skills add https://github.com/infrasity-labs/dev-gtm-claude-skills --skill sdk-docs-auditorWhat is this skill?
- Three-tier page discovery: llms.txt, then sitemap.xml via curl, then homepage nav crawl
- Audits six fixed sections: Installation, Quick Start, Error Handling, Troubleshooting, Examples, Best Practices
- Cross-references gaps across all SDK pages so missing-on-one-page does not false-flag content elsewhere
- Scores each section 0–100 with rating tiers in a self-contained downloadable HTML report
- Mandatory structured workflow: crawl → analyse → cross-reference → report (do not ad-hoc audit)
- 6 fixed audit sections
- Per-section scores from 0–100 with rating tiers
- 3-tier discovery: llms.txt, sitemap.xml, homepage nav
Adoption & trust: 1 installs on skills.sh; 24 GitHub stars; trending (+100% hot-view momentum).
What problem does it solve?
You pasted an SDK docs URL and have no systematic way to know if installation, quick start, errors, and examples are complete or scattered across pages.
Who is it for?
Indie API/SDK makers, dev-tool GTM leads, or agents asked to audit a competitor or own docs URL with a repeatable crawl-and-score method.
Skip if: Writing net-new tutorial content from scratch, or legal/compliance reviews unrelated to developer documentation structure.
When should I use this skill?
User provides a documentation URL and asks to audit, review, analyse, score, check quality, completeness, gaps, or crawl SDK docs (always use structured workflow).
What do I get? / Deliverables
You receive section scores 0–100, gap notes validated site-wide, and a downloadable HTML report suitable for prioritizing doc fixes before developers hit integration friction.
- Self-contained downloadable HTML audit report
- Per-section 0–100 scores and tier ratings
- Cross-referenced gap list across all crawled SDK pages
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Ship → review is the canonical shelf because the skill is a structured quality audit with scored sections and a downloadable report—classic pre-release or competitive doc review. Review subphase matches completeness scoring, gap analysis, and cross-page verification rather than authoring new reference pages from scratch.
Where it fits
After a docs refactor, re-run the six-section audit to see which reference areas still score below your launch bar.
Gate release on Installation and Quick Start both clearing your minimum 0–100 threshold in the HTML report.
Compare your SDK audit scores to a competitor URL before outbound dev-relations campaigns.
Prioritize troubleshooting and error-handling articles using the flagged cross-page gaps list.
How it compares
Structured multi-page SDK doc audit with cross-links—not a single-page Lighthouse run or informal chat opinion on docs quality.
Common Questions / FAQ
Who is sdk-docs-auditor for?
Solo builders and small dev-tool teams who need a scored, shareable SDK documentation audit from a URL without building a custom crawler.
When should I use sdk-docs-auditor?
In Ship before launch to harden docs, in Build when refactoring reference sections, or in Launch when benchmarking developer experience against another SDK site.
Is sdk-docs-auditor safe to install?
Check the Security Audits panel on this Prism page; the skill fetches external URLs and may use curl—scope network use and verify the generated HTML locally.
SKILL.md
READMESKILL.md - Sdk Docs Auditor
# SDK Docs Auditor Produces a comprehensive, cross-referenced audit of any SDK documentation site with a fully styled downloadable HTML report. ## What this skill does 1. Discovers all SDK pages via `llms.txt` first, falling back to `sitemap.xml` (using curl), then homepage nav crawl 2. Fetches and reads every relevant SDK page 3. Audits six fixed sections: Installation, Quick Start, Error Handling, Troubleshooting, Examples, Best Practices 4. Cross-references every gap across ALL other SDK pages — never flag something as missing if it exists elsewhere 5. Scores each section 0–100 and assigns a rating tier 6. Generates a beautiful, self-contained, downloadable HTML report --- ## Step 1 — Discover all SDK pages Use a three-tier discovery strategy, trying each method in order until one succeeds. ### 1a. Try llms.txt first (preferred) Run a bash curl command to fetch llms.txt: ```bash curl -s <docs_url>/llms.txt ``` If found: - Extract every URL from lines matching the pattern `- [Page Title](URL): description` - Filter to SDK-relevant pages only — keep URLs whose path contains any of: `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` - Exclude: marketing pages, changelog, blog, legal, community/forum pages - Store as `SDK_PAGES[]` — list of `{title, url, description}` - Note in the report: "Discovery method: llms.txt" ### 1b. Fallback — Try sitemap.xml If llms.txt is unavailable or returns no useful URLs, run a bash curl command to fetch the sitemap: ```bash curl -s <docs_url>/sitemap.xml | python3 -c "import sys, re; print('\n'.join(re.findall(r'<loc>(.*?)</loc>', sys.stdin.read())))" ``` If the sitemap returns URLs: - Parse every `<loc>` entry to get the full URL list - Filter using the same keyword list above - Store as `SDK_PAGES[]` — list of `{title, url}` - Note in the report: "Discovery method: sitemap.xml — N total URLs found, M SDK-relevant kept" Also check for a sitemap index (multiple sitemaps) by looking for `<sitemapindex>` in the response. If found, curl each child sitemap and aggregate all URLs before filtering. ### 1c. Final fallback — Homepage nav crawl If both llms.txt and sitemap.xml fail, fetch the docs homepage (`<docs_url>`) and extract all links from the nav sidebar or sitemap structure, filtering using the same keyword list. - Note in the report: "Discovery method: homepage nav crawl (llms.txt and sitemap.xml unavailable)" ### 1d. Identify section mapping From the discovered pages, identify which pages map to the six audit targets: | Audit section | Look for paths/titles containing | |---|---| | Installation | `install`, `setup`, `getting-started` | | Quick Start | `quick-start`, `quickstart`, `tutorial` | | Error Handling | `error`, `exception`, `errors` | | Troubleshooting | `troubleshoot`, `faq`, `debug` | | Examples | `example`, `sample`, `cookbook`, `tutorial` | | Best Practices | `best-practice`, `guide`, `pattern` | If a dedicated page is not found for a section, note it — the absence itself is a finding. ### Build the corpus All discovered pages form the **page corpus** used for