agentleFS
emiliodominguezemiliodominguez/flow-skills/skills/flow-docs/SKILL.md

flow-docs

Skill1 starsChanged 46 days agoMITView on GitHub

Human-facing documentation grounded in current code. Use when writing or updating a README, contributing guide, usage docs, API reference or architecture docs. Feeds `flow-review` or `flow-ship`.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • cofin/flowtheir own version, first seen Nov 1, 2026

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start from the reader's question.

    line 10
  2. Distinctive:

    Run examples or check them against the installed API.

    line 25
  3. Very specific:

    Use flow-review for correctness review or flow-ship when the docs are part of delivery.

    line 43

≈ “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

Document

Start from the reader's question. Docs earn space by letting someone use, change or reason about the system without rediscovering its constraints.

Process

  1. Identify the reader and the doc's job: tutorial, task guide, reference or explanation. Inspect existing docs and the actual API, behavior, config and examples.
  2. Ground claims in source, tests, history, ADRs or issues. Explain invariants and tradeoffs; label inferred rationale as inference and never invent historical intent.
  3. Colocate docs with what they explain when the repo supports it. Keep one source of truth and link with stable anchors instead of maintaining contradictory copies. Generate repetitive reference material when existing tooling does it reliably.
  4. Give readers the procedure or contract: prerequisites, working commands, inputs, outputs, failure cases and limits. Keep consumer-facing signatures, parameters and examples even when they also appear in source.
  5. Run examples or check them against the installed API. Validate links and anchors, regenerate owned docs and inspect the output. Mark unrun or access-dependent examples as such.
  6. Prune obsolete or duplicated material with no reader value. Keep legal notices, tool directives, supported compatibility notes and still-needed rationale.

Anti-patterns

  • Paraphrasing source without answering a reader question.
  • Deleting useful reference material only because code also contains it.
  • Stale commands from memory or invented reasons for an old design.
  • Hand-editing generated pages instead of their generator or source.

Done when

  • The reader can perform the task or understand the stated contract.
  • Claims, examples and links match current source, with verification limits visible.
  • Generated artifacts and their sources agree.

Use flow-review for correctness review or flow-ship when the docs are part of delivery.

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.