agentleFS
cheyuriycheyuriy/codelabgen/skills/source-official-docs/SKILL.md

source-official-docs

Skill1 starsChanged 23 days agoMITView on GitHub

How to find and map a technology's official documentation for a codelabgen course — docs site, version-specific docs, guides, tutorials, API reference, best practices, and LLM-oriented docs (llms.txt). Source type `official-docs`.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Start from research/overview.md (docs and homepage URLs) and codelabgen pkg-info (registry links).

    line 13
  2. Very specific:

    Run codelabgen llms-txt <docs root>.

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Official documentation (official-docs)

The official docs are the backbone of the course: the main source of code-truth and concepts, and often of structure (the order the maintainers teach things in). Find them first, map them, and record the sections that matter.

Find the docs for the pinned version

  1. Start from research/overview.md (docs and homepage URLs) and codelabgen pkg-info (registry links).
  2. Find out how the site handles versions: a version switcher, /v1/ or /latest/ paths, or separate sites per major version. Make sure you record pages for the pinned major version, not an older one that search engines still rank higher.
  3. Run codelabgen llms-txt <docs root>. When llms.txt exists, it is the best map of the docs: a curated list of pages. llms-full.txt is the whole site in one file; grep it, don't read it.

Map the docs

Fetch the landing page and the navigation (the sidebar usually appears in the fetched Markdown or in llms.txt). Identify:

  • Getting started / quickstart / tutorials: the maintainers' intended learning order (structure, code-truth)
  • Concepts / guides / how-to: explanations of each concept (concepts, code-truth)
  • API reference: exact signatures (code-truth). Record its root, not every page.
  • Best practices, production, troubleshooting, FAQ (pitfalls, concepts)
  • Migration guides belong to release-notes; leave them to that hunter.

What to record

Record sections, not every page: a section landing page whose subpages cover one area, such as "Persistence" or "Graph API". Aim for the pages a teacher would hand out. Typically:

  • the docs root or llms.txt (structure)
  • the tutorial sequence (structure, code-truth)
  • 3–6 concept or guide sections central to the technology (concepts, code-truth)
  • the API reference root (code-truth)
  • best practices or troubleshooting, if they exist (pitfalls)

Official docs score high (0.85–1.0) when they match the pinned version. Pages for an older major version score low, or aren't recorded at all.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.