agentleFS
toilanguyen2910toilanguyen2910/claude-code-starter-pack/skills/readme-writer/SKILL.md

readme-writer

Skill1 starsChanged 41 days agoMITView on GitHub

Generates or updates a project README from the actual codebase structure, package manifest, and entry points. Use when the user asks to write, generate, or update a README.

23 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

8 rules. 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before writing anything, inspect the project instead of guessing:

    line 11
  2. Very specific:

    Read the package manifest if present (package.json, pyproject.toml, Cargo.toml, go.mod, *.csproj, project.godot, etc.) for the name, …

    line 13
  3. Very specific:

    Look for an existing entry point (main.*, index.*, app.*) to understand how the project actually runs.

    line 18
  4. Distinctive:

    If a README already exists, read it fully — preserve any sections with information you can't infer from the code (like deployment notes or …

    line 20
  5. Distinctive:

    Never invent features, badges, or stats (star counts, build status) that aren't verifiable from the repo.

    line 41
  6. Distinctive:

    Don't add a "Contributing" or "Roadmap" section unless the user asks — most starter READMEs don't need one on day one.

    line 43
  7. Distinctive:

    Keep the tone plain and direct.

    line 45
  8. Very specific:

    Write it as a .md file at the project root, not inline in chat, unless the user is only asking for a section to paste in themselves.

    line 48

“Common” is measured: kept by at least 6 in 10 of the 18 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

Gather context first

Before writing anything, inspect the project instead of guessing:

  1. Read the package manifest if present (package.json, pyproject.toml, Cargo.toml, go.mod, *.csproj, project.godot, etc.) for the name, description, and dependencies.
  2. Glob the top-level structure to understand the project type (web app, CLI, library, game, script collection).
  3. Look for an existing entry point (main.*, index.*, app.*) to understand how the project actually runs.
  4. If a README already exists, read it fully — preserve any sections with information you can't infer from the code (like deployment notes or screenshots) instead of deleting them.

Structure to produce

  1. Title + one-line description — what it does, in plain language.
  2. Features — 3-6 bullets, only things actually implemented, not a roadmap.
  3. Installation — the exact commands, taken from the manifest/lockfile, not a generic placeholder.
  4. Usage — a minimal working example. If it's a CLI, show the actual command and flags. If it's a library, show a short code snippet.
  5. Project structure — only if the layout isn't a standard framework default and a reader would benefit from a map.
  6. Configuration — environment variables or config files, if any exist.
  7. License — pull from an existing LICENSE file if present; otherwise ask the user rather than assuming MIT.

Rules

  • Never invent features, badges, or stats (star counts, build status) that aren't verifiable from the repo.
  • Don't add a "Contributing" or "Roadmap" section unless the user asks — most starter READMEs don't need one on day one.
  • Keep the tone plain and direct. Skip marketing language like "blazing fast" or "seamless" unless it's demonstrably true and the user wants that tone.
  • Write it as a .md file at the project root, not inline in chat, unless the user is only asking for a section to paste in themselves.

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.