agentleFS
Kuan-AI-comKuan-AI-com/agent-skills/skills/readme-writer/SKILL.md

readme-writer

Skill0 starsChanged 6 days agoMITView on GitHub

Write a new README or update an outdated one for a project, with setup, configuration and usage that match the actual code. Use when the user says "write a README", "document how to run this", "update the README", "setup instructions", or "onboarding docs".

  • Reads credentials

25 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use security-audit.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CloudflareSkill

    security-audit

    Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions, focused reviews, vulnerability research, security audits, or pen tests. Run the complete workflow only for explicit codebase audit or pen-test requests, full/comprehensive/end-to-end reviews, or requested report artifacts.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 7

    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:

    Every command, file name and env var in the README must exist in the repo.

    line 8
  2. Distinctive:

    Keep the author's structure and any sections you cannot verify (mark them for the user to check instead of deleting).

    line 22
  3. Distinctive:

    Common tasks: test, lint, build, migrate, deploy, each with its exact command.

    line 29
  4. Distinctive:

    Project layout: only the folders a newcomer needs to find, one line each.

    line 30
  5. Distinctive:

    Troubleshooting: only real problems (from issues, comments in code, or ones you hit while verifying).

    line 31
  6. Distinctive:

    Run the quick start and common task commands if the environment allows it (skip deploys and anything touching production).

    line 38
  7. Distinctive:

    Check that every relative link and file path in the README exists.

    line 40

“Common” is measured: kept by at least 6 in 10 of the 20 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

README writer

Every command, file name and env var in the README must exist in the repo. A wrong quick start is worse than none.

1. Collect facts from the repo

  • What it is: entry points, package.json description, existing docs, the main routes or CLI commands.
  • Runtime and versions: .nvmrc, .node-version, engines, .python-version, pyproject.toml, go.mod, .tool-versions, Dockerfile base image.
  • Package manager from the lockfile: package-lock.json npm, pnpm-lock.yaml pnpm, yarn.lock yarn, bun.lockb bun, poetry.lock poetry, uv.lock uv.
  • Commands: scripts in package.json, Makefile targets, justfile, Taskfile, CI workflows (they show the real build and test order).
  • Configuration: .env.example, plus a search for where config is read (process.env., os.environ, os.Getenv, config(). Mark which ones the app cannot start without.
  • External services: database, queue, cache, third-party APIs, and how they are started locally (docker-compose?).
  • License: only from a LICENSE file.

2. Updating an existing README

Keep the author's structure and any sections you cannot verify (mark them for the user to check instead of deleting). Fix outdated commands, add what is missing, and tell the user what you changed.

3. Structure

  1. Name + one sentence: what it does and for whom. Then, if useful, 2-3 bullets of what it can do. No hype.
  2. Quick start: prerequisites with versions, then copy-paste commands from clone to a running app, ending with how to see it works (URL, expected output).
  3. Configuration: table of env vars: name, required, example value, what it does. Placeholders only, never real values.
  4. Common tasks: test, lint, build, migrate, deploy, each with its exact command.
  5. Project layout: only the folders a newcomer needs to find, one line each.
  6. Troubleshooting: only real problems (from issues, comments in code, or ones you hit while verifying).
  7. Contributing and license, if the repo has them.

Drop any section that would be empty or speculative. A small library may need only sections 1, 2 and 4 plus a usage example.

4. Verify

  • Run the quick start and common task commands if the environment allows it (skip deploys and anything touching production). Fix the README or tell the user when a command fails.
  • Commands you could not run: say so in your reply, not in the README.
  • Check that every relative link and file path in the README exists.

Do not

  • Invent features, badges, benchmarks, support channels or a roadmap.
  • Paste secrets, internal hostnames or personal data found in config files.
  • Duplicate long reference docs; link to them.

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.