readme-style
Skill1 starsChanged 7 months agoMITView on GitHub
Redesign README.md files with modern GitHub styling — badges, icons, tables, ASCII diagrams, and anchor navigation. Use when asked to restyle, modernize, or redesign a README with shields.io badges, section icons, or visual improvements.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- fulldecent/agent-skillstheir own version, first seen Nov 8, 2026
- caikiji/skills-labtheir own version, first seen Sep 7, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- caikiji/skills-lab★ 4same name
- fulldecent/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 repository3 other files it gives its agents.
- dev-plan-generatorSkill
- parallel-devSkill
- plan-eng-reviewSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Read the existing README and project root files (package.json, pyproject.toml, go.mod, Cargo.toml, Makefile, LICENSE*).
- Very specific: line 16
Check for existing docs (CHANGELOG, CONTRIBUTING, docs/) to link.
- Very specific: line 18
Write the README following the style guide in references/readme-style-guide.md.
- Distinctive: line 19
Verify all file paths, commands, and feature descriptions match the actual project.
- Distinctive: line 23
Only include badges for technologies actually present in the project.
- Distinctive: line 24
Do not fabricate CI, npm, or PyPI badges if no pipeline or package exists.
- Distinctive: line 26
Use ASCII box diagrams over Mermaid for workflow visualization.
- Distinctive: line 27
Prefer tables over bullet lists for structured information.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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 Style
Overview
Analyze a project and rewrite its README.md with modern GitHub visual styling. The goal is a README that renders well on GitHub, communicates project purpose at a glance, and follows current open-source conventions.
Workflow
- Read the existing README and project root files (
package.json,pyproject.toml,go.mod,Cargo.toml,Makefile,LICENSE*). - Identify the tech stack, build tools, test tools, and project structure.
- Check for existing docs (
CHANGELOG,CONTRIBUTING,docs/) to link. - Decide which sections apply to this project — do not add sections for features that do not exist.
- Write the README following the style guide in
references/readme-style-guide.md. - Verify all file paths, commands, and feature descriptions match the actual project.
Rules
- Only include badges for technologies actually present in the project.
- Do not fabricate CI, npm, or PyPI badges if no pipeline or package exists.
- Preserve all essential information from the original README.
- Use ASCII box diagrams over Mermaid for workflow visualization.
- Prefer tables over bullet lists for structured information.
- Scale README length to project size: small tools ~80 lines, libraries ~150, large projects 200+.
- Match the language of the existing README (Korean, English, or mixed).
- Technical terms (commands, file paths, function names) are always in English regardless of document language.
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.

