agentleFS
bestdeejay-designbestdeejay-design/agent-skills/skills/docs-system/SKILL.md

docs-system

Skill6 starsChanged 3 months agoMITView on GitHub

Meta-guide + router for documentation: the two branches (docs-product for 'why/what', docs-project for 'how'), the phase order, completeness levels L1/L2/L3, and the completeness checklist. Load a branch directly when the task is clearly product or engineering; load this skill for the big picture, ordering and completeness gates. Triggers: 'документация', 'набор документации', 'каталог документов', 'документация структура', 'полная документация', 'docs catalog', 'documentation structure', 'какую документацию писать'.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Distinctive:

    If a doc has no reader and no question it answers — it does not belong.

    line 26
  2. Very specific:

    Keep as the meta-guide (not deprecated — it still carries order/levels/ completeness).

    line 54
  3. Very specific:

    Do not use to author one document branch directly.

    line 59

≈ “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

Docs System — meta-guide & router

This skill is now the meta-guide. The two branches live in focused skills: load them directly. Use this skill for the big picture: which docs to write, in which order, and how complete the set must be.

Two branches of documentation

BranchAnswersSkill
Product docs — «why» and «what»VISION → PRD → ROADMAP → FEATURESdocs-product
Project docs — «how»README/ENTRY/ARCHITECTURE/ADR/contracts/tests + REFERENCE mapdocs-project

Rule: product docs answer «why» and «what»; engineering docs answer «how». If a doc has no reader and no question it answers — it does not belong.

When to use this skill (router)

  • The task is about the documentation SYSTEM as a whole: what to write, in what order, how complete.
  • The phases / levels / completeness gates need to be applied.
  • The task is clearly product OR engineering → load the branch directly instead.

Order and levels

  • Phase order (when to write each doc): references/order.md.
  • Levels L1/L2/L3 (how deep a doc set must be for the system size): references/levels.md.
  • Completeness checklist (what a complete doc set looks like): references/completeness.md.

Golden rules

  • Nothing is written "from the end": VISION → PRD → ROADMAP → FEATURES, then engineering docs.
  • Contracts (OpenAPI/AsyncAPI) are written BEFORE code.
  • The map (REFERENCE.md) is written last — it describes everything above it.
  • Example monorepo that follows all rules: examples/example-monorepo/.
  • Skill roadmap: ROADMAP.md.

Removal plan

Keep as the meta-guide (not deprecated — it still carries order/levels/ completeness). The two branches are the focused entry points.

Boundaries

  • Do not use to author one document branch directly; route to docs-product or docs-project.

Evidence and completion gate

Ground recommendations in the supplied repository or brief. State assumptions, missing inputs, and unresolved risks. Return a concrete artifact or checklist with an owner/action for each open item, then verify that the result answers the requested goal rather than merely repeating the framework.

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.