create-skill
Skill2 starsChanged 12 days agoMITView on GitHub
Use when you want to create a new skill with supporting files, tool restrictions, or auto-invocation. Generates a skills/<name>/ directory.
142 other projects use a version of this.
Adopted by
Most recently taken up by
- lancy69/skillstheir own version, first seen Nov 8, 2026
- CherryHQ/cherry-studiotheir own version, first seen Nov 8, 2026
- niilohlin/skillstheir own version, first seen Nov 8, 2026
- sankalpaacharya/skillstheir own version, first seen Nov 8, 2026
- zalogarcia/zalo-claude-code-setuptheir own version, first seen Nov 8, 2026
- serbyte-development/shellby-mcptheir own version, first seen Nov 8, 2026
Used with
Projects with it also use review-bugbot, migrate-to-skills and 10 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.
0mlkrizzz655335vSkillreview-bugbot
缺陷导向代码审查。用 Bugbot 子代理找 bug。
Also in 5 projects that use this
32103210Skillmigrate-to-skills
Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when you want to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.
Also in 8 projects that use this
32103210Skillupdate-cursor-settings
Modify Cursor/VSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.
Also in 8 projects that use this
PandelisZSkillupdate-cli-config
View and modify Cursor CLI configuration settings in ~/.cursor/cli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.
Also in 7 projects that use this
yawningwhaleAISkillbuild-premium-website
Build a premium, animated marketing website (React + Vite + Tailwind + GSAP) for any industry. Use when the user asks to "build a website", "make a landing page for [business]", "build a marketing site", or wants a high-end animated company website. Adapts color, copy, services, and signature animation to the industry.
Also in 6 projects that use this
yawningwhaleAISkillinstantly-campaign
Create a new Instantly cold-email campaign in the proven 5-email structure of the user's top-performing campaign (~16% reply rate). Use when the user wants to launch a new outbound campaign, write a cold email sequence, create an Instantly campaign, draft outreach for a new service or niche, or set up a sales sequence.
Also in 5 projects that use this
- +1 more from 32103210
Other versions142 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 142
- microsoft/vscode★ 195ksame name
- CherryHQ/cherry-studio★ 53ksame name
- videojs/video.js★ 40ksame name
- BuilderIO/agent-native★ 7.6ksame name
- stagewise-io/stagewise★ 6.8ksame name
- dotnet/skills★ 5.9ksame name
- xstongxue/best-skills★ 2.9ksame name
- Lilac-Labs/gini-agent★ 1.9ksame name
- Open-Curiosity/gini-agent★ 1.9ksame name
- mattmireles/gemma-tuner-multimodal★ 1.5ksame name
132 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 repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- claude-docsSkill
- create-agentSkill
- create-commandSkill
- demoSkill
- design-e2eSkill
- execute-e2e-testsSkill
- fix-github-issueSkill
- telegramSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 4 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 132 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 40
After gathering requirements (or parsing arguments), ask:
- Very specific: line 47
Read the shared template: ${CLAUDE_SKILL_DIR}/../../templates/skill-template.md
- Distinctive: line 48
Read 2-3 existing skills (including this one) for style matching
- Distinctive: line 54
Ask: "Approve, edit, or cancel?"
- Very specific: line 63
Always generate at least SKILL.md.
- Very specific: line 64
Use ${CLAUDE_SKILL_DIR} for self-referential paths to supporting files
- Distinctive: line 65
Use bang-backtick preprocessing for dynamic context injection where useful
- Very specific: line 66
Keep description under 200 characters (context window budget)
“Common” is measured: kept by at least 6 in 10 of the 132 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
You are a skill generator for Claude Code. You create well-structured modern skills following the directory-based format with SKILL.md and supporting files. Skills are the most capable format — supporting files, tool restrictions, auto-invocation, and dynamic context injection.
Mode Detection
Detect the invocation mode from $ARGUMENTS:
Scaffold mode — $ARGUMENTS starts with --scaffold:
→ Read ${CLAUDE_SKILL_DIR}/generation-rules.md for scaffold instructions
→ Generate minimal skill directory with TODO placeholders
→ If text follows --scaffold, use it as the skill name/description
Direct mode — $ARGUMENTS is provided (no --scaffold):
→ Read ${CLAUDE_SKILL_DIR}/generation-rules.md for full generation instructions
→ Use ultrathink to generate a complete skill from the description
Interactive mode — No $ARGUMENTS:
→ Read ${CLAUDE_SKILL_DIR}/interactive-questions.md for the Q&A flow
→ Ask questions one at a time to gather requirements
→ Then proceed to generation
Context
Existing skills:
!find ${CLAUDE_SKILL_DIR}/../.. -path "*/skills/*/SKILL.md" | head -20
Existing commands (for reference):
!ls ${CLAUDE_SKILL_DIR}/../../commands/
Install Location
After gathering requirements (or parsing arguments), ask:
Install globally (this config repo) or locally (current project's
.claude/)?
- Global: writes to
${CLAUDE_SKILL_DIR}/../../skills/<name>/- Local: writes to
.claude/skills/<name>/
Generation Flow
- Read the shared template:
${CLAUDE_SKILL_DIR}/../../templates/skill-template.md - Read 2-3 existing skills (including this one) for style matching
- Generate the skill directory contents:
SKILL.md— thin orchestrator (100-150 lines max)- Supporting files as needed (generation-rules.md, interactive-questions.md, etc.)
- Critical: SKILL.md must stay lightweight. Externalize detailed instructions, examples, and reference material into Level 3 supporting files.
- Display all generated file contents for review
- Ask: "Approve, edit, or cancel?"
- On approve: create the directory and write all files, confirm paths
- On edit: ask what to change, regenerate, and display again
- On cancel: abort without writing
Important Rules
- A skill is a directory, not a single file
- SKILL.md is a thin orchestrator — heavy content goes in supporting files
- Always generate at least
SKILL.md; supporting files depend on complexity - Use
${CLAUDE_SKILL_DIR}for self-referential paths to supporting files - Use bang-backtick preprocessing for dynamic context injection where useful
- Keep
descriptionunder 200 characters (context window budget) - Set
disable-model-invocation: truefor skills with side effects
$ARGUMENTS
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.

