readme
Skill2 starsChanged 2 months agoMITView on GitHub
Create, rewrite, audit, or update repository and GitHub profile README files. Use when a README must be grounded in the current project, when setup or usage documentation is stale, or when the repository landing page needs a clearer audience path.
32 other projects use a version of this.
Adopted by
Most recently taken up by
- Xia-Ataraxia/craft-skillstheir own version, first seen Nov 8, 2026
- harlan-zw/brundleflytheir own version, first seen Nov 8, 2026
- alexcristea/ship-plugintheir own version, first seen Nov 1, 2026
- knowttl/bstacktheir own version, first seen Nov 1, 2026
- robinbril/claude-code-harnesstheir own version, first seen Nov 1, 2026
- lawless-m/claude-skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use favicon, build and 3 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.
cpiprintSkillfavicon
Generate favicons from a source image
Also in 3 projects that use this
Microsoft AzureSkillbuild
Build the TypeSpec Rust emitter from source. Run this after cloning the repo, after pulling changes, or when TypeScript source files have been modified.
Also in 3 projects that use this
GitHubSkillrefactor
Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.
Also in 3 projects that use this
SentrySkillcommit
Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.
Also in 3 projects that use this
NVIDIASkillresearch
Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.
Also in 3 projects that use this
Other versions32 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 32
- getkyo/kyo★ 820same name
- statelyai/skills★ 48same name
- sampleXbro/agentsmesh★ 27same name
- wpgaurav/WordPress-skills★ 19same name
- danvega/skills★ 15same name
- kasperjunge/agent-resources-legacy★ 9same name
- harlan-zw/brundlefly★ 7same name
- lawless-m/claude-skills★ 6same name
- ephemerallyCaden/write-readme★ 5same name
- sinedied/agent-skills★ 4same name
22 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.
In this repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- humanizer-zhSkill
- backend-patternsSkill
- frontend-patternsSkill
- security-reviewSkill
- fastapiSkill
- python-projectSkill
- ts-backendSkill
- ts-frontendSkill
- codebase-designSkill
- code-reviewSkill
- coding-standardsSkill
- domain-modelingSkill
- fixSkill
- grillingSkill
- living-docs-governanceSkill
- planSkill
- prototypeSkill
- publish-ticketsSkill
- resilienceSkill
- session-handoffSkill
- specSkill
- systematic-debuggingSkill
- tddSkill
- verificationSkill
The file
We split this skill into the rules it gives an agent
12 rules. 0 are common, 11 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 32 edited versions we read keep these.
11
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 13
Write the shortest README that lets its intended reader understand the project and reach a verified first success.
- Very specific: line 26
Read references/archetypes.md when choosing an outline or handling a profile, internal, config, or curated repository.
- Distinctive: line 42
Gate: every feature, prerequisite, command, compatibility statement, and status claim in the draft has repository evidence or explicit user …
- Distinctive: line 52
Add later sections only when they answer a real reader question.
- Distinctive: line 60
Use GitHub Flavored Markdown and the repository's established language and tone.
- Distinctive: line 65
Use examples that match real interfaces and current names.
- Distinctive: line 66
Add badges, screenshots, diagrams, tables, admonitions, and a table of contents only when they improve a reader decision.
- Distinctive: line 70
When evidence is missing, write a visible placeholder or ask for the fact.
- Distinctive: line 74
Run the narrowest available checks:
- Distinctive: line 77
verify relative links, referenced paths, image targets, and heading anchors.
- Distinctive: line 78
run the repository's Markdown formatter or linter when configured.
- Distinctive: line 82
If a command requires credentials, external infrastructure, payment, publishing, or destructive state, verify its syntax and prerequisites …
“Common” is measured: kept by at least 6 in 10 of the 32 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
README
Write the shortest README that lets its intended reader understand the project and reach a verified first success. Treat the repository as the source of truth; treat existing prose as a claim to verify.
Workflow
1. Fix the scope
Determine:
- the requested operation: create, rewrite, update, or audit;
- the README path and whether it is a repository README or GitHub profile README;
- the primary audience and the action they should take next;
- the project archetype.
Read references/archetypes.md when choosing an outline or handling a profile, internal, config, or curated repository. Ask the user only when the audience, scope, or desired outcome cannot be inferred from the repository or request.
Gate: state one primary audience, one desired next action, and one archetype before drafting.
2. Build an evidence ledger
Inspect the current README and the smallest set of authoritative project surfaces needed to support its claims:
- manifests, lockfiles, entry points, and package metadata;
- executable help, scripts, task runners, and CI configuration;
- examples, tests, screenshots, and deployed documentation;
- environment templates and configuration schemas;
LICENSE, contribution guides, changelogs, and security or support policies.
Record each important README claim with its source and status: verified, needs clarification, or omit. Prefer current machine-readable configuration and successful command output over stale prose. Preserve useful existing content, links, and project voice.
Gate: every feature, prerequisite, command, compatibility statement, and status claim in the draft has repository evidence or explicit user confirmation.
3. Design the reader path
Lead with:
- project name;
- a direct statement of what it does and who it helps;
- the shortest verified path to first success.
Add later sections only when they answer a real reader question. Link to canonical docs instead of duplicating their content. Keep architecture, API reference, operations, contribution policy, changelog, and license detail in their existing dedicated files when those files exist.
For profile READMEs or README-adjacent GitHub presentation such as About text and topics, read references/github-presentation.md.
Gate: the outline puts the primary audience's first-success path before background and maintainer detail.
4. Draft from evidence
Use GitHub Flavored Markdown and the repository's established language and tone.
- Make headings descriptive and links explicit.
- Make setup commands copy-pasteable from a stated working directory.
- Explain placeholders, required credentials, and destructive effects before the command that uses them.
- Use examples that match real interfaces and current names.
- Add badges, screenshots, diagrams, tables, admonitions, and a table of contents only when they improve a reader decision.
- Give every meaningful image useful alt text.
- Mark unstable, experimental, generated, or platform-specific behavior precisely.
When evidence is missing, write a visible placeholder or ask for the fact; do not convert inference into documentation.
5. Prove the README
Run the narrowest available checks:
- execute quickstart or usage commands when safe and practical;
- verify relative links, referenced paths, image targets, and heading anchors;
- run the repository's Markdown formatter or linter when configured;
- compare the final diff against the evidence ledger;
- reread only the rendered reader path: identity → value → first success → next steps.
If a command requires credentials, external infrastructure, payment, publishing, or destructive state, verify its syntax and prerequisites without performing the side effect. State that limitation in the report.
Gate: report each check as passed, failed, or not run with a reason. A README with unsupported claims or broken local references is not complete.
Deliverable
Return:
- the README change or audit findings;
- the audience and archetype used;
- evidence inspected;
- checks run and their results;
- unresolved facts or unverified external steps.
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.

