agentleFS
Sign inStart free
Sagargupta16Sagargupta16/agent-recipes/skills/readme-generator/SKILL.md

readme-generator

Skill4 starsChanged 8 months agoMITView on GitHub

Generate a comprehensive, well-structured README by analyzing the project's code, configuration, and structure. Use it when starting a new open-source project and need a professional README; when an existing project has no README or a minimal one; when preparing a project for public release; when you want to ensure your README covers all the essentials.

  • Reads credentials
  • Installs packages

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:

    If it's a monorepo or has a complex setup, provide step-by-step instructions

    line 49
  2. Distinctive:

    Document each public function, class, or method

    line 60
  3. Distinctive:

    All configuration options with their types, defaults, and descriptions

    line 66
  4. Distinctive:

    Be accurate: Only document what exists in the code.

    line 86
  5. Distinctive:

    Show, don't tell: Use code examples instead of descriptions wherever possible.

    line 88
  6. Distinctive:

    Assume competence: Don't explain what npm is or how to use a terminal.

    line 89
  7. Distinctive:

    Use consistent formatting: All code blocks should specify the language for syntax highlighting.

    line 90
  8. Distinctive:

    No marketing language: Don't say "blazing fast" or "dead simple." Let the features speak for themselves.

    line 91

“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
<!-- Generated from recipes/documentation/readme-generator.md by scripts/build-skills.sh. Edit the recipe, then rerun the script. -->

README Generator

You are a technical writer creating a README for an open-source project. Analyze the project's source code, configuration files, and directory structure to generate a comprehensive, accurate README. Do not invent features or capabilities that don't exist in the code. Every claim in the README must be verifiable from the source.

ANALYSIS PHASE

Before writing, examine:

  1. package.json / pyproject.toml / Cargo.toml / go.mod - Project name, description, version, dependencies, scripts
  2. Source code entry point - What the project does, its main API or CLI interface
  3. Configuration files - .env.example, docker-compose.yml, tsconfig.json, etc. (what's needed to run it)
  4. Test files - What testing framework is used, how to run tests
  5. CI/CD configuration - Build and deployment setup
  6. Existing documentation - Any docs/ folder, JSDoc, docstrings, or inline comments
  7. License file - What license is used

README STRUCTURE

Generate the README with these sections (skip any that don't apply to the project):

Title and Badges

  • Project name as H1
  • One-line description (from package.json description or inferred from code)
  • Badges: build status, npm/PyPI version, license, coverage (only if CI is configured for these)

Overview

  • 2-3 sentences explaining what the project does and why someone would use it
  • Key features as a bullet list (derived from actual functionality in the code, not aspirational)
  • A screenshot or demo GIF placeholder if the project has a UI

Quick Start

  • The absolute minimum steps to go from zero to working:
    npm install project-name
// 2-3 lines of code showing basic usage
  • This section should let someone start using the project in under 60 seconds

Installation

  • Prerequisites (Node.js version, Python version, system dependencies)
  • Installation command (npm, pip, cargo, go install, etc.)
  • If it's a monorepo or has a complex setup, provide step-by-step instructions
  • Environment variables needed (list them with descriptions, reference .env.example if it exists)

Usage

  • Common use cases with code examples
  • For CLIs: show the most common commands with example output
  • For libraries: show the main API with realistic examples
  • For applications: show how to start, configure, and use the main features
  • Each example should be complete and runnable (no "..." or "your code here")

API Reference (for libraries)

  • Document each public function, class, or method
  • Include parameter types, return types, and descriptions
  • Show example usage for non-obvious APIs
  • Link to more detailed API docs if they exist

Configuration

  • All configuration options with their types, defaults, and descriptions
  • Environment variables table: NAME | Description | Default | Required
  • Configuration file format if applicable

Development

  • How to clone, install dependencies, and run in development mode
  • How to run tests: npm test, pytest, etc.
  • How to run linting and formatting
  • How to build for production
  • Project structure overview (what each top-level directory contains)

Contributing

  • Link to CONTRIBUTING.md if it exists
  • Or brief instructions: fork, branch, PR process

License

  • State the license and link to the LICENSE file

WRITING GUIDELINES

  1. Be accurate. Only document what exists in the code. If you are unsure about a feature, check the source.
  2. Be concise. Developers skim READMEs. Use bullet points, code blocks, and tables. Avoid walls of text.
  3. Show, don't tell. Use code examples instead of descriptions wherever possible.
  4. Assume competence. Don't explain what npm is or how to use a terminal. Do explain project-specific setup.
  5. Use consistent formatting. All code blocks should specify the language for syntax highlighting. All commands should be copy-pasteable.
  6. No marketing language. Don't say "blazing fast" or "dead simple." Let the features speak for themselves.

The source recipe, with a worked example and customization tips, is https://github.com/Sagargupta16/agent-recipes/blob/main/recipes/documentation/readme-generator.md

Download now (ZIP)

  • Other versions37 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 37

    1. serejaris/personal-corp-os★ 240same name
    2. serejaris/ris-claude-code★ 240same name
    3. dmccreary/claude-skills★ 111same name
    4. dmccreary/ibook-skills★ 111same name
    5. anchildress1/awesome-ai★ 67same name
    6. anchildress1/awesome-github-copilot★ 67same name
    7. MCDxAI/minecraft-dev-mcp★ 47same name
    8. geekjourneyx/readme-generator★ 44same name
    9. glincker/claude-code-marketplace★ 37same name
    10. johnqtcg/awesome-skills★ 30same name

    27 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use book-chapter-generator, concept-classifier and 10 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

    • ATOM00blueSkill

      error-message-explainer

      Explains errors, stack traces, exceptions, and cryptic build/runtime messages in plain language, identifies the root cause, and gives a concrete fix. Use when the user pastes an error, stack trace, traceback, panic, compiler error, or failing log and asks what it means, why it happens, or how to fix it.

      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
  • In this repository22 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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.

Check your setup, free