agentleFS
jaskirat1616jaskirat1616/grok-skills/skills/readme-generator/SKILL.md

readme-generator

Skill22 starsChanged 3 months agoMITView on GitHub

Generates polished, well-structured project READMEs with badges, a one-line tagline, quick-start, installation, usage examples, configuration tables, contribution guidelines, and a license section. Use this skill when the user asks to "write a README", "generate a README", "create README.md", "improve my README", "add badges", "document my project", "make a project description", or wants onboarding/landing-page docs for a library, CLI, web app, API, or repo.

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 8 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

  • 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

  • +7 more from vishalsachdev

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. 0 are common, 10 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Why: should I care? (key features / value)

    line 23
  2. Distinctive:

    How: do I install and run it? (quick start)

    line 24
  3. Distinctive:

    How: do I use it? (usage + examples)

    line 25
  4. Distinctive:

    How: do I contribute / get help / what license?

    line 26
  5. Distinctive:

    Follow these steps in order.

    line 30
  6. Very specific:

    Detect project type and facts: Run scripts/detect_project.py <repo> (or inspect manually) to identify language, package manager, entry …

    line 33
  7. Distinctive:

    Choose sections: Start from the canonical order below and drop sections that do not apply.

    line 42
  8. Very specific:

    Validate: Run scripts/lint_readme.py README.md to check for broken relative links, missing alt text, placeholder leftovers (TODO, FIXME, …

    line 61
  9. Very specific:

    Use shields.io. Place 4-7 badges max — relevant, not decorative.

    line 92
  10. Distinctive:

    Prefer tables for any list of options, flags, or environment variables.

    line 122
  11. Very specific:

    Use relative links for in-repo files (./CONTRIBUTING.md) and absolute for external resources.

    line 123
  12. Distinctive:

    Always include alt text on images for accessibility.

    line 125
  13. Distinctive:

    Keep the tagline under ~12 words.

    line 126
  14. Distinctive:

    Add a Table of Contents only when the document is long enough to need it.

    line 128

“Common” is measured: kept by at least 6 in 10 of the 29 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

Overview

This skill produces a complete, polished README.md that serves as a project's front door. It inspects the repository to ground the content in reality (real install commands, real scripts, real entry points) rather than inventing details, then assembles the appropriate sections in a conventional, scannable order.

Keywords: readme, README.md, project documentation, badges, shields.io, quick start, installation, usage, getting started, contributing, license, table of contents, project description, onboarding docs.

A great README answers five questions fast:

  1. What is this? (one sentence, above the fold)
  2. Why should I care? (key features / value)
  3. How do I install and run it? (quick start)
  4. How do I use it? (usage + examples)
  5. How do I contribute / get help / what license?

Workflow

Follow these steps in order. Do not skip the investigation step — accuracy beats fluff.

  1. Detect project type and facts. Run scripts/detect_project.py <repo> (or inspect manually) to identify language, package manager, entry points, scripts, license, and existing badges. This drives which sections apply. See references/section-catalog.md for the type→section mapping.
  2. Confirm the essentials. Gather (ask the user only for what you cannot infer): project name, one-line tagline, target audience, install command, minimal run/usage example, license, and repo URL (for badge slugs).
  3. Choose sections. Start from the canonical order below and drop sections that do not apply. Never include an empty or placeholder section.
  4. Draft the header block. Title (H1) → tagline (one line, no period needed) → badge row → optional hero image/demo → table of contents (only if the README is long, roughly 6+ H2 sections).
  5. Write Quick Start. The single most important section. A reader should be able to copy-paste their way to a running result in under a minute. Use a fenced code block with a language hint and real commands.
  6. Fill body sections (Features, Installation, Usage, Configuration, API, Examples, Roadmap) using concrete, copy-pasteable content. Prefer tables for options/flags/env vars.
  7. Add the closing block (Contributing, License, Acknowledgments). Link to CONTRIBUTING.md and CODE_OF_CONDUCT.md if they exist; otherwise inline a short contributing blurb.
  8. Validate. Run scripts/lint_readme.py README.md to check for broken relative links, missing alt text, placeholder leftovers (TODO, FIXME, <your-...>), heading hierarchy, and a present License section.
  9. Self-review against references/quality-checklist.md.

Canonical Section Order

# Project Name
> One-line tagline

[badges]
[hero image / demo gif]

## Table of Contents        (long READMEs only)
## Features                 (3-6 bullets, benefit-first)
## Quick Start              (copy-paste to a result)
## Installation             (all supported methods)
## Usage                    (common tasks + code)
## Configuration            (options table / env vars)
## API / Commands           (reference, if applicable)
## Examples                 (real scenarios)
## Roadmap                  (optional)
## Contributing             (link or short blurb)
## License
## Acknowledgments          (optional)

Badge Quickref

Use shields.io. Place 4-7 badges max — relevant, not decorative. Common patterns (replace OWNER/REPO):

![Build](https://img.shields.io/github/actions/workflow/status/OWNER/REPO/ci.yml)
![npm](https://img.shields.io/npm/v/PACKAGE)
![PyPI](https://img.shields.io/pypi/v/PACKAGE)
![License](https://img.shields.io/github/license/OWNER/REPO)
![Coverage](https://img.shields.io/codecov/c/github/OWNER/REPO)
![Stars](https://img.shields.io/github/stars/OWNER/REPO?style=social)

See references/badges.md for a full catalog (CI, coverage, version, downloads, language, code style, social, custom static badges) with the exact markdown and link-wrapping pattern.

Decision Heuristics

  • Library/package → emphasize Installation, API, and import/usage snippets.
  • CLI tool → emphasize Quick Start, Commands/flags table, examples.
  • Web app / service → emphasize screenshots/demo, env config, deploy steps.
  • Mono-repo → top-level overview + links to per-package READMEs.
  • Tiny project → collapse to Title, tagline, Quick Start, Usage, License.
  • Unsure of a fact → ask, or mark with a clearly-flagged TODO the user must fill — never silently fabricate version numbers, URLs, or commands.

Best Practices

  • Lead with value: the first screen must convey what and why.
  • Make every code block copy-pasteable and language-tagged.
  • Prefer tables for any list of options, flags, or environment variables.
  • Use relative links for in-repo files (./CONTRIBUTING.md) and absolute for external resources.
  • Always include alt text on images for accessibility.
  • Keep the tagline under ~12 words; keep Features to 3-6 benefit-driven bullets.
  • Show, don't tell: a real example beats a paragraph of description.
  • Add a Table of Contents only when the document is long enough to need it.

Common Pitfalls

  • Fabricated install commands or version numbers — always ground in the repo.
  • A wall of prose before the reader sees what the project is.
  • Badges that don't resolve (wrong slug) or purely decorative badge spam.
  • Multiple H1s (#) — there must be exactly one, the title.
  • Placeholder leftovers shipped to users (<your-name>, TODO, lorem ipsum).
  • Usage examples that don't actually run.
  • Missing License section (legally important, frequently forgotten).

Bundled Files

  • references/section-catalog.md — every section, what goes in it, when to include it, and the project-type matrix.
  • references/badges.md — full shields.io badge catalog with copy-paste markdown.
  • references/quality-checklist.md — final self-review checklist.
  • templates/README.template.md — fill-in template with guidance comments.
  • examples/cli-tool-readme.md — a complete worked example for a CLI project.
  • scripts/detect_project.py — inspects a repo and reports facts for grounding.
  • scripts/lint_readme.py — validates a finished README.

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.