readme-writer
Skill4 starsChanged 27 days agoMITView on GitHub
Use when writing a README, improving or rewriting an existing README.md, documenting a project for new users or contributors, or preparing a repository to be published or open-sourced.
- Reads credentials
23 other projects use a version of this.
Adopted by
Most recently taken up by
- sandrinodm/skillstheir own version, first seen Nov 8, 2026
- vigneshm1995personal/skillgatetheir own version, first seen Nov 8, 2026
- andymartinezot/claude-skillstheir own version, first seen Nov 1, 2026
- nseney1/Soma-Governancetheir own version, first seen Nov 1, 2026
- OneByJorah/VirtOfficetheir own version, first seen Nov 1, 2026
- vrodokanakis/claude-skillstheir own version, first seen Oct 25, 2026
Other versions23 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 23
- event-driven-io/emmett★ 562same name
- OneByJorah/offivo★ 24same name
- OneByJorah/VirtOffice★ 24same name
- sandrinodm/skills★ 11same name
- nseney1/Aegis-Guardrails★ 4same name
- nseney1/Soma-Governance★ 4same name
- shimo4228/claude-harness★ 4same name
- guihai24/openskills★ 2same name
- IdkwhatImD0ing/hackathonstarterkit★ 2same name
- brpaz/agent-skills★ 1same name
13 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 repository30 other files it gives its agents.
- accessibility-auditSkill
- api-design-reviewSkill
- api-test-writerSkill
- architecture-diagramSkill
- bug-debuggerSkill
- bug-report-writerSkill
- changelog-writerSkill
- codebase-onboardingSkill
- code-reviewSkill
- database-schema-designSkill
- dependency-upgradeSkill
- design-handoff-specSkill
- design-reviewSkill
- dockerize-appSkill
- figma-design-compareSkill
- flaky-test-fixerSkill
- git-commit-writerSkill
- github-actions-ciSkill
- playwright-e2e-testsSkill
- prd-writerSkill
- proof-of-done-liteSkill
- refactor-plannerSkill
- security-auditSkill
- seo-auditSkill
- test-case-generatorSkill
- test-plan-writerSkill
- test-writerSkill
- ux-research-synthesisSkill
- ux-writingSkill
- web-performance-auditSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 18 edited versions we read keep these.
2
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 14
Collect facts from the code: before writing a word:
- Very specific: line 23
Mark unknowns: If a fact cannot be found (deployment URL, support channel), leave a clearly marked TODO: or ask.
- Distinctive: line 36
When improving an existing README, keep correct content, fix what is wrong or stale, and list the changes you made.
“Common” is measured: kept by at least 6 in 10 of the 18 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 Writer
Overview
A README answers, in order: what is this, why should I care, how do I run it in five minutes, and where do I go next. Every fact comes from the codebase. Nothing is invented.
Method
- Collect facts from the code before writing a word:
- Manifests:
package.json,pyproject.toml,pom.xml,go.mod,Cargo.toml— name, description, scripts, engines/versions. - Entry points, CLI flags (
--helpoutput if runnable), exported API. - Configuration:
.env.example, config files, required environment variables. - Setup steps hidden in scripts, Dockerfiles, Makefiles and CI workflows.
- License file, contributing guide, existing docs.
- Manifests:
- Verify every command you will document exists (script name, binary, flag). Do not document
npm run devunless the script is there. - Pick the audience: users of a library or CLI, operators of a service, or contributors. Lead with what that audience needs.
- Write using template.md. Drop sections that have no real content.
- Mark unknowns. If a fact cannot be found (deployment URL, support channel), leave a clearly marked
TODO:or ask; never guess.
Rules
| Rule | Why |
| First two lines say what it is and who it is for | Readers decide in seconds |
| Quickstart works copy-paste on a clean machine | Prerequisites and versions listed first |
| Show one real usage example with real output | Examples beat feature lists |
| Configuration table: variable, required, default, description | Most setup failures are config |
| No badges, links, screenshots or features that do not exist | Broken trust is hard to win back |
Keep it short; link to docs/ for depth | Long READMEs are skimmed, not read |
When improving an existing README, keep correct content, fix what is wrong or stale, and list the changes you made.
Common mistakes
- Generic filler ("This project is a powerful, scalable solution...").
- Install steps that skip a required environment variable or service (database, API key).
- Documenting scripts or flags that were renamed or never existed.
- Copying the whole API reference into the README.
- Wrong license name compared with the LICENSE file.
Made by Wageesha Tripathi · LinkedIn · Email · More skills
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.