agentleFS
jensenhuangyankaijensenhuangyankai/living-docs-skill/skills/living-docs/SKILL.md

living-docs

Skill0 starsChanged 6 months agoMITView on GitHub

Bootstrap, navigate, update, and align source-linked living docs. Use when the user mentions docs, design docs, architecture docs, keeping docs in sync, asks what docs already exist, needs missing docs created, or wants to grill, stress-test, or clarify a codebase plan before implementation.

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. mehrad-dm/mastermind★ 23same name
    2. ejklock/living-docs-skill★ 14same name
    3. mpklu/living-doc★ 1same name
    4. phlx0/living-docs★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Bootstrap: No living-docs system exists yet.

    line 19
  2. Distinctive:

    Treat "docs", "design docs", "architecture docs", and similar wording as a likely trigger for this skill.

    line 29
  3. Distinctive:

    Treat "grill", "stress-test", "align before build", "clarify the plan", and "interview me" as Align mode triggers when a codebase is …

    line 31
  4. Distinctive:

    Search first and read only the relevant docs or templates.

    line 33
  5. Distinctive:

    Prefer the smallest accurate docs update over broad rewrites.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

Living Docs

Single entrypoint for the living-docs workflow. It can also align a proposed change against the repo's documented language before implementation begins.

Infer the Mode

Choose the mode from the request and repository state. Do not ask the user to pick unless the situation is genuinely ambiguous.

  • Align: The user has a plan, feature idea, or design direction and wants it grilled, stress-tested, clarified, or aligned before building. Load align.md.
  • Bootstrap: No living-docs system exists yet. Load bootstrap.md.
  • Navigate: The repo already has docs and you need context. Load navigate.md.
  • Update: Code changed and the docs must be synchronized. Load update.md.

Rules

  • Pick one mode first. Do not load every reference file up front.
  • Treat "docs", "design docs", "architecture docs", and similar wording as a likely trigger for this skill.
  • Treat "grill", "stress-test", "align before build", "clarify the plan", and "interview me" as Align mode triggers when a codebase is involved.
  • Search first and read only the relevant docs or templates.
  • Prefer the smallest accurate docs update over broad rewrites.

Helpers

  • Scaffold docs: scripts/scaffold-docs.sh
  • List changed files: scripts/list-changed-files.sh
  • Match changed files to docs: scripts/match-source-files.py

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.