agentleFS
viasrijanviasrijan/crazy-skills/skills/docs/readme-generation/SKILL.md

readme-generation

Skill0 starsChanged 3 months agoMITView on GitHub

Use when writing, rewriting, or auditing a GitHub README.md — generate high-converting README with badges, SVG logo, and 2026 best-practice audit.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

README Generation

High-converting GitHub README generator. Composite of d-o-hub/github-template-ai-agents readme-best-practices + github/awesome-copilot readme-blueprint-generator.

When to use

  • User asks to "write the README", "improve README", "add badges", "make repo look professional"
  • Creating a new repo and need first README
  • Auditing an existing README for 2026 best practices

Workflow

  1. Analyze repo — cat package.json (or pyproject.toml), detect stack, list features, check existing README.md, .github/ docs.
  2. Generate — Hero: one-line SEO description + 4 badges (license, build, version, stars) + optional SVG logo (light/dark GitHub themes). Quick Start: zero-config, copy-paste runnable. Sections: Features table, Project Structure, Key Features, Development Workflow, Testing, Contributing, License.
  3. Audit — Before finalizing, verify:
    • Logo renders both themes
    • Badges URLs valid
    • Quick Start works with zero API keys
    • Code blocks have language specifier
    • TOC anchors match headings, internal links exist
    • Description matches GitHub repo "About" field
    • Install commands cover every interface

Verification

  • README has hero + 4 badges + Quick Start in first viewport
  • Badges valid, logo renders both themes
  • Quick Start copy-paste runnable, all code blocks have language tag
  • TOC anchors and internal links valid, description matches About

References

  • Source: d-o-hub/github-template-ai-agents readme-best-practices, github/awesome-copilot readme-blueprint-generator

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.