Shoalrun
Last scanned shoalrun.comCustom platform15 pages tested
AI agents can find, read and use these docs well. Shoalrun scores 90 out of 100 (grade A), passing 23 of 28 checks. 5 still need work.
This report covers shoalrun.com, where shoalrun.com redirects.
Developer docs
Kind of site
23/28
Checks passed
1
Partly passed
4
Failed
Access
Content discoverability5 passed2 failed
Pages point agents to llms.txt
No llms.txt directive found in HTML of any of 15 sampled pages
No agent-facing directive pointing to llms.txt was detected in the HTML of any tested page. Add a visually-hidden element near the top of each page (e.g., a div with CSS clip-rect) containing a link to your llms.txt. If your site serves markdown versions of pages, mention that in the directive too so agents know to request it.
Check your fix:
curl -s https://www.shoalrun.com/ | grep -n llms.txtfinds the link near the top of the HTML.Markdown pages point agents to llms.txt
No llms.txt directive found in markdown of any of 14 sampled pages; 1 had no markdown version
No llms.txt directive was detected in the markdown of any tested page. Add a blockquote near the top of each markdown page (e.g., "> For the complete documentation index, see [llms.txt](/llms.txt)").
Check your fix: The Markdown version of https://www.shoalrun.com/ (its .md URL, or the page fetched with
Accept: text/markdown) has the llms.txt line in its first few lines.llms.txt exists
llms.txt found at https://www.shoalrun.com/llms.txt
llms.txt follows the standard structure
llms.txt follows the proposed structure (H1, blockquote, heading-delimited link sections)
llms.txt fits in an agent's context
llms.txt is 29,483 characters (under 50,000 threshold)
llms.txt links work
All 15 same-origin sampled links resolve (164 total links)
llms.txt links point to Markdown
15/15 same-origin sampled links point to markdown content (100%)
Markdown availability2 passed
Pages are available as Markdown
14/14 sampled pages support .md URLs (100%)
Server returns Markdown when asked
14/14 sampled pages support content negotiation (100%)
Page size and truncation2 passed2 failed
HTML pages fit in context
1 of 15 sampled pages convert to over 100K chars (max 117K HTML → 583K markdown (65% boilerplate))
1 of 15 pages convert to over 100K characters of markdown. Break large pages into smaller units, reduce navigation boilerplate, or provide markdown versions that bypass the HTML conversion overhead.
Content starts near the top
7 of 15 sampled pages have content starting past 50% (worst 81%)
7 of 15 pages have content starting past 50% of the converted output. Agents may never see the documentation content. Reduce navigation, breadcrumb, and sidebar markup that precedes the content area.
Content is in the HTML without JavaScript
All 15 sampled pages contain server-rendered content
Markdown pages fit in context
All 14 pages under 50K chars (median 6K, max 39K)
Content structure3 passed
Tabs don't bloat the page
No tabbed content detected across 15 sampled pages
Headings inside tabs name their variant
No tabbed content found; header quality check not applicable
Code blocks are well-formed
All 85 code fences properly closed across 15 pages
URL stability2 passed
Missing pages return a real 404
All 15 sampled pages return proper error codes for bad URLs
Redirects stay on the same host
No redirects detected across 15 sampled pages
Content health2 passed1 partly
Markdown matches the HTML page
2 of 14 pages have minor content differences between markdown and HTML
2 pages have minor content differences between their markdown and HTML versions.
llms.txt covers the whole site
llms.txt covers 100% of 152 sitemap doc pages; 10 llms.txt links not in sitemap (may indicate stale links or incomplete sitemap)
Cache headers allow timely updates
All 16 endpoints have appropriate cache headers
Authentication and access1 passed
Gated docs offer another way in
All docs pages are publicly accessible; no alternative access paths needed
Docs are readable without logging in
All 15 sampled pages are publicly accessible
Crawler access2 passed
Crawlers and AI assistants may read the docs
robots.txt lets Googlebot, Bingbot, OAI-SearchBot, PerplexityBot, Claude-SearchBot and Claude-User read the docs.
Sitemap lists the docs pages
The sitemap at https://www.shoalrun.com/sitemap.xml lists 153 of the 155 docs pages found through llms.txt and page links.
Freshness
Maintenance3 passed
Pages say when they were last changed
14 of 14 sampled pages state when they were last changed.
Links and section anchors work
All 35 links and 6 section anchors checked on the sampled pages work.
Sitemap entries still exist
All 10 sitemap entries sampled still exist.
Consistency with the API spec1 passed
Endpoints in the docs exist in the API spec
All 2 endpoints mentioned on the sampled pages are in https://www.shoalrun.com/api/notes/production/current/openapi.yaml.
CurrencyNot applicable
Deprecated operations are marked as such
https://www.shoalrun.com/api/notes/production/current/openapi.yaml marks no operation as deprecated, so there is nothing to compare.
Additional checks
Not part of the score: optional extras that help agents use your docs.
MCP server is discoverable
No MCP server was found for these docs.
Offer a read-only MCP server with a search tool over your docs, and link it from llms.txt, so agents in Cursor, Claude and ChatGPT can query your docs directly.
llms-full.txt is available
No llms-full.txt found at https://www.shoalrun.com/llms-full.txt.
Publish /llms-full.txt with the full text of your docs in Markdown, so an agent can load everything in one request instead of crawling page by page.
Check your fix:
curl -sI https://www.shoalrun.com/llms-full.txtreturns 200.Agent skills are published
No agent skills index was found at /.well-known/agent-skills/index.json.
Publish an Agent Skills index at /.well-known/agent-skills/index.json with a SKILL.md for your main tasks, so agents can load task instructions without reading every page.
About this scan
- Scanned
- Oct 19, 2026
- Pages tested
- 15 of 163 found
- Platform
- Unknown
- Kind of site
- Developer docs
- AFDocs score, on its own
- 89 (B), 17 of 23 checks pass
- Based on 15 sampled pages, chosen deterministically from the sitemap and llms.txt. Pages outside the sample were not read.
- Pages were fetched without running JavaScript, the way most AI agents read the web.
- Answerability, where an AI agent answers real questions written from these pages, runs in the open-source scanner with your own API key. This web score is made of Access and Freshness.
Methodology 2026-09.6 · AFDocs 0.20.0
Pages we sampled (15)
- https://www.shoalrun.com/
- https://www.shoalrun.com/author/agents
- https://www.shoalrun.com/author/components/code-blocks
- https://www.shoalrun.com/author/components/file-tree
- https://www.shoalrun.com/author/components/timeline
- https://www.shoalrun.com/author/markdown-metadata
- https://www.shoalrun.com/author/templates
- https://www.shoalrun.com/changelog/authoring-search
- https://www.shoalrun.com/cli
- https://www.shoalrun.com/documents.json
- https://www.shoalrun.com/example-api/write-note
- https://www.shoalrun.com/non-goals
- https://www.shoalrun.com/publish/mcp
- https://www.shoalrun.com/recipes/build-docs
- https://www.shoalrun.com/start
Show your score
Add the badge to your docs or README. It updates each time the site is scanned.
Markdown
[](https://documentation.ai/agent-score/shoalrun)HTML
<a href="https://documentation.ai/agent-score/shoalrun"><img src="https://documentation.ai/agent-score/badge/shoalrun.svg" alt="Agent Readiness Score: 90 (A)" height="20"></a>Agent-ready docs by default
Live in under 5 min · No credit card required