generate-readme
Skill0 starsChanged 4 months agoMITView on GitHub
Generates or refreshes a repository's README.md by scanning the codebase for its purpose, structure, entry points, setup steps, and key workflows. Use when a repo has no README, a stub README, or the README is stale after significant changes. Trigger phrases: "generate the readme", "refresh the readme", "write a readme for this repo".
8 other projects use a version of this.
Adopted by
Most recently taken up by
- kool7/claude-skillstheir own version, first seen Nov 1, 2026
- juanitourquiza/shipframetheir own version, first seen Oct 23, 2026
- microsoft/Agent365-Samplestheir own version, first seen Oct 20, 2026
- kostiantyn-matsebora/canopy-examplestheir own version, first seen Oct 11, 2026
- Jay-1409/skillstheir own version, first seen Oct 3, 2026
- eddmann/agent-toolkittheir own version, first seen Sep 22, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- microsoft/Agent365-Samples★ 113same name
- gricha/dangerous-skills★ 38same name
- juanitourquiza/shipframe★ 4same name
- eddmann/agent-toolkit★ 2same name
- Jay-1409/skills★ 2same name
- kool7/claude-skills★ 0same name
- kostiantyn-matsebora/canopy-examples★ 0same name
- tranviet0710/agent-skills★ 0same name
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.
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- adapters/claude.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- review-changesSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
After architecture changes (new entry points, services, commands, config).
- Distinctive: line 18
When onboarding notes are out of date.
- Very specific: line 32
Add a diagram when structure is non-trivial: Prefer a Mermaid flowchart or sequenceDiagram.
- Distinctive: line 37
Never paste secret values.
- Distinctive: line 39
Keep the quick start truly runnable — no assumed globals.
“Common” is measured: kept by at least 6 in 10 of the 8 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.
Files
generate-readme
Produce a clear, human-facing README.md grounded in what the code actually does — not a generic template.
When to use
- New repo with no or stub README.
- After architecture changes (new entry points, services, commands, config).
- When onboarding notes are out of date.
Process
- Scan for signal (do not guess):
- Manifest / build files (
package.json,pyproject.toml,pom.xml,go.mod,Cargo.toml, etc.) for name, scripts, deps. - Entry points, CLI commands, exported modules.
- Config and environment files (redact secret values; list the keys).
- Existing docs, comments, and tests for intent.
- Manifest / build files (
- Draft these sections (skip any that don't apply):
- One-line description (what + who it's for).
- Quick start (install -> run -> verify), copy-paste, minimal.
- Key concepts / architecture (a diagram if the structure is non-trivial).
- Configuration (keys, not secret values).
- How to contribute / run tests.
- Add a diagram when structure is non-trivial. Prefer a Mermaid
flowchartorsequenceDiagram. Keep node names free of spaces. - Write the file and summarize what you inferred so the human can correct it.
Rules
- Ground every claim in something you found in the repo. If unsure, ask or mark it
TODO. - Never paste secret values. List config keys only.
- Match the project's existing tone if one exists.
- Keep the quick start truly runnable — no assumed globals.
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.