readme-skill
llms.txt2 starsChanged 4 months agoMITView on GitHub
A cited, maintained knowledge base of state-of-the-art README practices for GitHub projects, packaged as a Claude Code skill that generates or reviews READMEs. Every rule traces to a source with a last-verified date. Use this file to locate the knowledge base. Each linked file is clean markdown. The reference files carry the guidance; the templates are per-project-type skeletons; sources.md is the bibliography every rule keys into. Links point at the main branch as raw markdown.
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- refresh-researchSkill
- readmeSkill
The file
We split this llms.txt into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- Distinctive: line 7
Use this file to locate the knowledge base.
≈ “Common” is an estimate: at least 1 in 5 of the 3,727 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
# readme-skill > A cited, maintained knowledge base of state-of-the-art README practices for > GitHub projects, packaged as a Claude Code skill that generates or reviews > READMEs. Every rule traces to a source with a last-verified date. Use this file to locate the knowledge base. Each linked file is clean markdown. The reference files carry the guidance; the templates are per-project-type skeletons; sources.md is the bibliography every rule keys into. Links point at the `main` branch as raw markdown. ## Knowledge base - [anatomy](https://raw.githubusercontent.com/albertogrande/readme-skill/main/skills/readme/references/anatomy.md): canonical section order and the required/recommended matrix per project type - [section-guide](https://raw.githubusercontent.com/albertogrande/readme-skill/main/skills/readme/references/section-guide.md): per-section authoring rules, sourced - [badges](https://raw.githubusercontent.com/albertogrande/readme-skill/main/skills/readme/references/badges.md): which badges earn a place, ordering, syntax, anti-patterns - [checklist](https://raw.githubusercontent.com/albertogrande/readme-skill/main/skills/readme/references/checklist.md): the scored review rubric - [anti-patterns](https://raw.githubusercontent.com/albertogrande/readme-skill/main/skills/readme/references/anti-patterns.md): named README failure modes and fixes - [ai-readers](https://raw.githubusercontent.com/albertogrande/readme-skill/main/skills/readme/references/ai-readers.md): README vs AGENTS.md vs llms.txt in the agent era - [project-types](https://raw.githubusercontent.com/albertogrande/readme-skill/main/skills/readme/references/project-types.md): how to classify a repo and pick a template - [sources](https://raw.githubusercontent.com/albertogrande/readme-skill/main/skills/readme/references/sources.md): annotated bibliography behind every rule ## Templates - [library](https://raw.githubusercontent.com/albertogrande/readme-skill/main/skills/readme/templates/library.md): library / package - [cli-tool](https://raw.githubusercontent.com/albertogrande/readme-skill/main/skills/readme/templates/cli-tool.md): command-line tool - [web-app](https://raw.githubusercontent.com/albertogrande/readme-skill/main/skills/readme/templates/web-app.md): web app / self-hosted service - [api-service](https://raw.githubusercontent.com/albertogrande/readme-skill/main/skills/readme/templates/api-service.md): API / service / framework - [research-data](https://raw.githubusercontent.com/albertogrande/readme-skill/main/skills/readme/templates/research-data.md): research / data project - [minimal](https://raw.githubusercontent.com/albertogrande/readme-skill/main/skills/readme/templates/minimal.md): tiny project ## How the skill works - [SKILL.md](https://raw.githubusercontent.com/albertogrande/readme-skill/main/skills/readme/SKILL.md): the generate/review routing the agent follows ## Optional - [README](https://raw.githubusercontent.com/albertogrande/readme-skill/main/README.md): human-facing overview and install - [research log (2026-07-20)](https://raw.githubusercontent.com/albertogrande/readme-skill/main/research/log/2026-07-20-initial-research.md): raw findings behind the initial knowledge base
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
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.

