agentleFS
PradnyeshpPradnyeshp/Claude-Skills/.claude/skills/readme/SKILL.md

readme

Skill2 starsChanged 4 months agoMITView on GitHub

Generate or update a project README from the codebase — what it is, how to install, run, test, and configure it. Use when the user says "write a README", "generate a readme", "update the README", "document this project", "my README is out of date", or "create project docs".

  • Reads credentials

39 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use favicon, glossary and 9 more.

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.
  • cpiprintSkill

    favicon

    Generate favicons from a source image

    Also in 3 projects that use this

  • Microsoft AzureSkill

    glossary

    Short glossary of domain terms used by the team.

    Also in 3 projects that use this

  • jaydubya818Skill

    how

    Use for runtime, ownership, layering, code-walkthrough, and placement questions.

    Also in 3 projects that use this

  • jaydubya818Skill

    why

    Use when design rationale must be recovered from source history and available records.

    Also in 3 projects that use this

  • 0xSeroSkill

    security

    Also in 3 projects that use this

  • Microsoft AzureSkill

    build

    Build the TypeSpec Rust emitter from source. Run this after cloning the repo, after pulling changes, or when TypeScript source files have been modified.

    Also in 3 projects that use this

  • +1 more from Azure

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 39 edited versions we read keep these.

  • 4

    Distinctive

    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:

    Identify the project: Read the manifests, entry points, and config to determine the name, purpose, language, framework, and runtime.

    line 25
  2. Distinctive:

    Decide create vs update: If a README already exists, preserve its structure, tone, and any hand-written sections (badges, screenshots, …

    line 27
  3. Distinctive:

    Document only what exists.

    line 52
  4. Very specific:

    Every command you list must come from a real script/Makefile/CI target — verify it exists before writing it.

    line 53
  5. Distinctive:

    Keep it skimmable: headings, short paragraphs, fenced code blocks for commands.

    line 55

“Common” is measured: kept by at least 6 in 10 of the 39 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

Project signals

!ls 2>/dev/null

!cat package.json pyproject.toml Cargo.toml go.mod composer.json 2>/dev/null | head -80

!ls Makefile docker-compose.yml Dockerfile .env.example LICENSE* CONTRIBUTING* 2>/dev/null

!cat README* 2>/dev/null | head -80

Instructions

Generate or update the project's README.md (focus on the $ARGUMENTS section if one was named). Write for a developer who just landed on the repo and wants to understand and run it quickly.

Method

  1. Identify the project. Read the manifests, entry points, and config to determine the name, purpose, language, framework, and runtime. Don't infer purpose from the directory name alone — confirm it in code or existing docs.
  2. Pull real commands. Take install/build/run/test commands from scripts in package.json, a Makefile, pyproject.toml/Cargo.toml, CI config, or CONTRIBUTING — not from convention. Note required env vars (check .env.example) and services (e.g. docker-compose).
  3. Decide create vs update. If a README already exists, preserve its structure, tone, and any hand-written sections (badges, screenshots, acknowledgements); refresh only what's stale or missing. If none exists, create one from the structure below.
  4. Write README.md at the repo root (or the path the user names).

Suggested structure

# <Project name>

<One-sentence description, then a short paragraph on what it does and why.>

## Features            # optional — only if there are clear, listable capabilities

## Installation        # prerequisites + the actual install steps

## Usage               # the common commands / a minimal code example

## Configuration       # env vars and config files, if any (link to .env.example)

## Development         # build, test, lint commands; how to contribute

## License             # match the LICENSE file if present

Rules

  1. Document only what exists. Don't invent features, commands, env vars, or badges. If you can't confirm how to run something, label it clearly as a best guess rather than asserting it.
  2. Every command you list must come from a real script/Makefile/CI target — verify it exists before writing it.
  3. Match the project's tone and any existing README conventions. Omit sections that don't apply (don't write an empty "License" if there's no license).
  4. Keep it skimmable: headings, short paragraphs, fenced code blocks for commands. This is a front door, not a manual.
  5. Output raw markdown to the file. After writing, summarize what you created or changed and flag anything you marked as a guess.

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.