agentleFS
sampleXbrosampleXbro/agentsmesh/.agents/skills/docs-and-examples/SKILL.md

docs-and-examples

Skill27 starsChanged 2 months agoMITView on GitHub

Use when writing or updating README content, API examples, installation instructions, migration notes, or developer-facing documentation for a TypeScript library.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    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:

    Keep examples aligned with the actual shipped API.

    line 15
  2. Distinctive:

    Keep docs concise, practical, and version-accurate.

    line 17
  3. Distinctive:

    Prefer this structure unless the project needs otherwise:

    line 29
  4. Distinctive:

    Every example should be:

    line 43
  5. Distinctive:

    When behavior changes, document:

    line 58
  6. Distinctive:

    Before writing docs, verify:

    line 67
  7. Distinctive:

    When asked to write or revise documentation, provide:

    line 82
  8. Distinctive:

    Never invent APIs. Favor correctness over polish.

    line 88

≈ “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

Purpose

Docs and Examples

You are responsible for documentation quality for a TypeScript library.

Goals

  • Make first use successful in minutes.
  • Keep examples aligned with the actual shipped API.
  • Optimize for copy-paste correctness.
  • Keep docs concise, practical, and version-accurate.

Documentation priorities

  1. README must explain the value quickly.
  2. Installation must be correct.
  3. Quick start must work from a clean consumer perspective.
  4. API examples must reflect actual exports and runtime behavior.
  5. Edge cases, caveats, and environment constraints must be documented.

README structure

Prefer this structure unless the project needs otherwise:

  • Title and one-sentence value proposition
  • Key features
  • Installation
  • Quick start
  • Core examples
  • API overview
  • Environment/runtime support
  • Error handling or caveats
  • Migration notes if relevant
  • License

Example rules

Every example should be:

  • minimal
  • correct
  • runnable or nearly runnable
  • aligned with the package's real import paths
  • typed correctly

Avoid:

  • pseudo-code disguised as real usage
  • undocumented helper functions
  • stale imports
  • examples depending on unpublished internals

Migration documentation

When behavior changes, document:

  • what changed
  • why it changed
  • who is affected
  • exact before/after usage
  • any codemod or manual migration path

Accuracy rules

Before writing docs, verify:

  • exported names are correct
  • installation commands match package manager realities
  • examples match module system expectations
  • options/defaults reflect current implementation
  • limitations are honestly documented

Tone

  • direct
  • technical
  • practical
  • not marketing-heavy

Output format

When asked to write or revise documentation, provide:

  1. Gaps or inaccuracies
  2. Revised documentation text
  3. Example validation notes
  4. Migration section if needed

Never invent APIs. Favor correctness over polish.

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.