code-standards
Skill1 starsChanged 4 months agoMITView on GitHub
Setup universal code quality standards in your project. Use when the user wants to generate coding standards files (CLAUDE.md, AGENTS.md, GEMINI.md, etc.) or mentions 'code standards', 'code review setup', or similar intent in any language.
17 other projects use a version of this.
Adopted by
Most recently taken up by
- turkeryildirim/ai-skillstheir own version, first seen Nov 1, 2026
- Bobagi/claude-skillstheir own version, first seen Oct 29, 2026
- meowdiocre/meowpitheir own version, first seen Oct 27, 2026
- tiago-oliveira-ca/zenodotus-harnesstheir own version, first seen Oct 25, 2026
- Fullstack-Rocks/skillstheir own version, first seen Oct 25, 2026
- Vivswan/skillstheir own version, first seen Oct 16, 2026
Used with
Projects with it also use code-review.
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.
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 3 projects that use this
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- ryanthedev/code-foundations★ 381same name
- tamdogood/parler-protocol★ 15same name
- metraton/gaia★ 4same name
- saitarrun/Devforge-ai★ 4same name
- thejordanleopold/claude-code-skills-distilled★ 4same name
- turkeryildirim/ai-skills★ 4same name
- digitaldreams/tuhin★ 3same name
- meowdiocre/meowpi★ 3same name
- Fullstack-Rocks/skills★ 2same name
- onejaejae/skills★ 2same name
7 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 repository6 other files it gives its agents.
- daily-newsSkill
- env-syncSkill
- macos-disk-cleanupSkill
- pr-review-loopSkill
- shipSkill
- video-downloaderSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 14 edited versions we read keep these.
1
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
- Very specific: line 28
All other languages → references/code-standards-en.md
- Distinctive: line 46
Write the template content directly.
“Common” is measured: kept by at least 6 in 10 of the 14 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
Code Standards — Universal AI Tool Configuration Generator
Generate code standards files based on Linus Torvalds' "Good Taste" philosophy. Auto-detects AI tools in your project and creates the appropriate configuration files in the user's language.
When to Use
- User wants to set up coding standards for a project
- User wants to sync code quality rules across AI coding tools
- User mentions "code standards", "init claude md", "code review", or equivalent in any language
Instructions for Agent
Step 1: Detect Language & Read Template
Detect the user's language. Read the matching template from this skill's references/ directory:
- Simplified Chinese →
references/code-standards-zh-CN.md - Traditional Chinese →
references/code-standards-zh-TW.md - Japanese →
references/code-standards-ja.md - All other languages →
references/code-standards-en.md
Step 2: Detect AI Tools
PROJECT_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
[ -d "$PROJECT_ROOT/.cursor" ] && echo "CURSOR"
[ -f "$PROJECT_ROOT/AGENTS.md" ] || [ -d "$PROJECT_ROOT/.codex" ] && echo "CODEX"
[ -f "$PROJECT_ROOT/GEMINI.md" ] || [ -d "$PROJECT_ROOT/.gemini" ] && echo "GEMINI"
[ -d "$PROJECT_ROOT/.github" ] && echo "COPILOT"
[ -d "$PROJECT_ROOT/.windsurf" ] || [ -f "$PROJECT_ROOT/.windsurfrules" ] && echo "WINDSURF"
[ -f "$PROJECT_ROOT/.aider.conf.yml" ] && echo "AIDER"
[ -d "$PROJECT_ROOT/.clinerules" ] || [ -d "$PROJECT_ROOT/.roo" ] && echo "CLINE"Step 3: Generate Files
Write the template content directly. No confirmation needed — the user invoked this skill, that IS the intent.
Always generate: CLAUDE.md
For each detected tool, also generate:
| Tool | File | Notes |
| Cursor | .cursor/rules/code-standards.mdc | Prepend ---\ndescription: "Linus Torvalds code standards"\nalwaysApply: true\n---\n |
| Codex | AGENTS.md | Same content |
| Gemini | GEMINI.md | Same content |
| Copilot | .github/copilot-instructions.md | mkdir -p .github first |
| Windsurf | .windsurfrules | Same content |
| Aider | CONVENTIONS.md | Same content |
| Cline/Roo | .clinerules/code-standards.md | mkdir -p .clinerules first |
Step 4: Report
Report created files in the user's language. Keep it brief.
Response Guidelines
- Execute immediately — No confirmation, no "shall I proceed?". Just write.
- Unconditionally overwrite existing files — Always overwrite CLAUDE.md and other config files without asking. The invocation is explicit intent to replace.
- Respond in user's language — Match the language they used to invoke.
- No extra commentary — Detect, write, report. Done.
Error Handling
| Situation | Action |
| Not in a git repo | Use current directory as root |
| No tools detected | Only generate CLAUDE.md |
| Permission denied | Report error with path |
| Template not found | Fall back to English |
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.

