Claude API scores 71/100 (Grade C), passing 10 of 22 checks (45%). The documentation is broadly accessible to AI agents but has 11 areas that could be improved to better serve automated tooling.
# Agent Score Fix Report — Claude API URL: https://docs.anthropic.com Score: 71/100 (Grade C) I need help improving the AI-readiness of the documentation at https://docs.anthropic.com. Agent Score found 6 failing checks and 5 warnings. ## Failing Checks (6) - [content-discoverability] Llms Txt Directive: No llms.txt directive found in any of 10 sampled pages - [page-size] Page Size Markdown: 2 of 7 pages exceed 100K chars (max 125K) - [page-size] Page Size Html: 2 of 10 sampled pages convert to over 100K chars (max 125K, 0% boilerplate) - [page-size] Content Start Position: 3 of 10 sampled pages have content starting past 50% (worst 100%) - [url-stability] Http Status Codes: 10 of 10 sampled pages return 200 for non-existent URLs (soft 404) - [observability] Markdown Content Parity: 3 of 7 pages have substantive content differences between markdown and HTML (avg 16% missing) ## Warnings (5) - [content-discoverability] Llms Txt Exists: llms.txt found but only reachable via cross-host redirect (agents may not follow it); 1 failed to fetch - [content-discoverability] Llms Txt Valid: llms.txt contains parseable links but doesn't fully follow the proposed structure: https://platform.claude.com/llms.txt: No blockquote summary found - [content-discoverability] Llms Txt Size: llms.txt is 64,354 characters (between 50,000 and 100,000; consider splitting) - [markdown-availability] Markdown Url Support: 7/10 sampled pages support .md URLs (70%); inconsistent support - [markdown-availability] Content Negotiation: Content negotiation partially supported: 7 correct type, 0 wrong type, 3 HTML only ## Fix Instructions For each issue above, please: 1. Analyze the documentation site at https://docs.anthropic.com 2. Implement the specific fix 3. Verify the fix would cause the check to pass ### Common fixes: - **No llms.txt**: Create /llms.txt following https://llmstxt.org — list all doc pages in markdown format - **No .md URL support**: Configure your docs platform to serve pages at equivalent .md URLs (e.g. /docs/quickstart.md) - **No content negotiation**: Return markdown when request includes Accept: text/markdown header - **Large page size**: Reduce nav boilerplate, inline scripts, and repetitive markup - **No sitemap**: Generate /sitemap.xml listing all documentation URLs - **Auth walls**: Ensure docs pages return 200 without requiring login cookies or tokens - **No Last-Modified header**: Configure your server/CDN to include Last-Modified response headers - **Tab content hidden**: Ensure tabbed content is rendered in the HTML (not JS-only) so agents can read all variants ## Run afdocs Locally for More Detail To get deeper visibility into what's failing, run afdocs against your docs: npx afdocs https://docs.anthropic.com --fixes --verbose - **--fixes**: Adds "Fix:" lines to the output for each warn/fail check with actionable remediation steps - **-v, --verbose**: Shows per-page details (specific URLs, character counts, error codes) for checks with issues — useful for per-URL visibility into what's failing
CHECK RESULTS
How your docs scored
page-size-markdown2 of 7 pages exceed 100K chars (max 125K)
page-size-html2 of 10 sampled pages convert to over 100K chars (max 125K, 0% boilerplate)
content-start-position3 of 10 sampled pages have content starting past 50% (worst 100%)
rendering-strategyAll 10 sampled pages contain server-rendered content
markdown-url-support7/10 sampled pages support .md URLs (70%); inconsistent support
content-negotiationContent negotiation partially supported: 7 correct type, 0 wrong type, 3 HTML only
http-status-codes10 of 10 sampled pages return 200 for non-existent URLs (soft 404)
redirect-behaviorNo redirects detected across 10 sampled pages
auth-gate-detectionAll 10 sampled pages are publicly accessible
auth-alternative-accessAll docs pages are publicly accessible; no alternative access paths needed
llms-txt-directiveNo llms.txt directive found in any of 10 sampled pages
llms-txt-existsllms.txt found but only reachable via cross-host redirect (agents may not follow it); 1 failed to fetch
llms-txt-validllms.txt contains parseable links but doesn't fully follow the proposed structure: https://platform.claude.com/llms.txt: No blockquote summary found
llms-txt-sizellms.txt is 64,354 characters (between 50,000 and 100,000; consider splitting)
llms-txt-links-resolveAll 10 same-origin sampled links resolve (621 total links)
llms-txt-links-markdown10/10 same-origin sampled links point to markdown content (100%)
markdown-content-parity3 of 7 pages have substantive content differences between markdown and HTML (avg 16% missing)
llms-txt-freshnessllms.txt covers 100% of 620 sitemap doc pages
cache-header-hygieneAll 11 endpoints have appropriate cache headers
tabbed-content-serializationNo tabbed content detected across 10 sampled pages
section-header-qualityNo tabbed content found; header quality check not applicable
markdown-code-fence-validityAll 27 code fences properly closed across 8 pages
