agentleFS
ATOM00blueATOM00blue/agent-skills-pro/skills/readme-generator/SKILL.md

readme-generator

Skill0 starsChanged 6 months agoMITView on GitHub

Generates a clear, well-structured project README from the codebase — title, badges, description, features, install, usage, configuration, contributing, and license. Use when the user asks to write, create, generate, or improve a README, project documentation, or docs for a repository.

  • Reads credentials
  • Installs packages

37 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use book-chapter-generator, concept-classifier 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.
  • vishalsachdevSkill

    book-chapter-generator

    This skill generates a structured chapter outline for intelligent textbooks by analyzing course descriptions, learning graphs, and concept dependencies. Use this skill after the learning graph has been created and before generating chapter content, to design an optimal chapter structure that respects concept dependencies and distributes content evenly across 6-20 chapters.

    Also in 3 projects that use this

  • vishalsachdevSkill

    concept-classifier

    Create an interactive classification quiz MicroSim using p5.js where students read scenarios and classify them into the correct category from multiple choice options. Uses a data.json file for easy question editing. Ideal for teaching students to recognize patterns, identify types, or categorize examples across any subject domain.

    Also in 3 projects that use this

  • JayRHaSkill

    changelog-keeper

    Maintains a CHANGELOG.md in the Keep a Changelog format with Semantic Versioning, grouping user-facing entries under Added/Changed/Deprecated/Removed/Fixed/Security and cutting dated releases from an Unreleased section. Use this skill when the user asks to "update the changelog", "add a changelog entry", "cut a release", "bump the version", "what changed since the last release", or to create/clean up a CHANGELOG.md or release notes.

    Also in 3 projects that use this

  • peopleforresterSkill

    refactoring-guide

    Safe refactoring patterns and techniques. Use when the user wants to improve code structure, reduce duplication, or make code more maintainable without changing behavior. Emphasizes incremental changes with test coverage.

    Also in 3 projects that use this

  • +7 more from vishalsachdev

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 8

    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:

    Write a README that lets a newcomer understand the project and get it running in minutes.

    line 13
  2. Distinctive:

    Never invent install commands, options, or badges that aren't true.

    line 34
  3. Distinctive:

    Add a Table of Contents only for long READMEs.

    line 72
  4. Distinctive:

    Make commands real: Every command should run as written.

    line 79
  5. Distinctive:

    Use shields.io. Common, accurate badges:

    line 86
  6. Distinctive:

    Don't add badges for services the project doesn't use.

    line 92
  7. Distinctive:

    Monorepo: keep a top-level README that orients, plus a focused README per package.

    line 131
  8. Distinctive:

    Sparse repo: ask for or infer the missing pieces (purpose, audience) rather than fabricating features.

    line 134

“Common” is measured: kept by at least 6 in 10 of the 31 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 Generator

Write a README that lets a newcomer understand the project and get it running in minutes. Base it on the actual repository, not assumptions.

Workflow

- [ ] 1. Learn the project (manifest, entry point, scripts, existing docs)
- [ ] 2. Draft sections in priority order
- [ ] 3. Make every command copy-pasteable and accurate
- [ ] 4. Trim filler; keep it scannable

Step 1 — Read the repo first

Ground the README in evidence. Inspect:

  • The package manifest (package.json, pyproject.toml, go.mod, Cargo.toml) for name, description, scripts, dependencies, and entry point.
  • The main entry file and CLI/flags for real usage.
  • Existing config files, .env.example, and any docs to reuse.
  • The license file for the license name.

Never invent install commands, options, or badges that aren't true.

Step 2 — Structure (most-read sections first)

# Project Name

> One-sentence description of what it does and who it's for.

[badges: build, version, license, etc.]

Short paragraph: the problem it solves and why someone would use it.

## Features
- Key capability 1
- Key capability 2

## Quick start / Installation
\`\`\`bash
<exact install command>
\`\`\`

## Usage
\`\`\`bash
<minimal working example with expected output>
\`\`\`

## Configuration
| Option | Default | Description |
| ------ | ------- | ----------- |

## API / Commands        (if applicable)

## Contributing          (link to CONTRIBUTING.md if it exists)

## License

Add a Table of Contents only for long READMEs. Add Screenshots/Demo near the top for anything with a UI. Omit sections that don't apply rather than padding them.

Step 3 — Writing rules

  • Lead with value. The first two lines must answer "what is this and why do I care?"
  • Show, don't tell. A 5-line working example beats a paragraph of prose.
  • Make commands real. Every command should run as written; include the expected output for the key one.
  • Be honest about status (alpha/beta, supported platforms, requirements/versions).
  • Use relative links for in-repo files; check headings are unique for anchor links.

Badges (only true ones)

Use shields.io. Common, accurate badges:

![Build](https://github.com/OWNER/REPO/actions/workflows/ci.yml/badge.svg)
![npm](https://img.shields.io/npm/v/PACKAGE)
![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)

Don't add badges for services the project doesn't use.

Example skeleton (CLI tool)

# wc-rs

> A fast, drop-in `wc` replacement written in Rust.

![Build](https://github.com/me/wc-rs/actions/workflows/ci.yml/badge.svg)
![Crates.io](https://img.shields.io/crates/v/wc-rs)
![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)

`wc-rs` counts lines, words, and bytes 4–6x faster than GNU `wc` on large files,
with the same flags you already know.

## Features
- Drop-in compatible flags (`-l`, `-w`, `-c`, `-m`)
- Parallel processing for multiple files
- Zero dependencies, single static binary

## Installation
\`\`\`bash
cargo install wc-rs
\`\`\`

## Usage
\`\`\`bash
wc-rs -l README.md
#   42 README.md
\`\`\`

## License
MIT — see [LICENSE](LICENSE).

Common edge cases

  • Library vs application: libraries lead with install + import + a minimal code snippet; apps lead with run instructions and a screenshot.
  • Monorepo: keep a top-level README that orients, plus a focused README per package.
  • Existing README: improve in place — preserve accurate content and structure; don't discard project-specific details.
  • Sparse repo: ask for or infer the missing pieces (purpose, audience) rather than fabricating features.

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.