create-command
Skill2 starsChanged 12 days agoMITView on GitHub
Use when you want to create a simple slash command (single markdown file). For complex needs, use /create-skill instead.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- tony-hoang-ai-automation/mkt-skillstheir own version, first seen Oct 25, 2026
- pahlevikun/levistacktheir own version, first seen Oct 25, 2026
- EvolutionAPI/evo-nexustheir own version, first seen Oct 8, 2026
- KhaledSaeed18/dotclaudetheir own version, first seen Jul 4, 2026
- evolution-foundation/evo-nexustheir own version, first seen Apr 20, 2026
- lxyer/multi-agent-collaboration-systemtheir own version, first seen Apr 16, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- EvolutionAPI/evo-nexus★ 545same name
- evolution-foundation/evo-nexus★ 535same name
- timominkus/obsidian-para-gtd-ai★ 9same name
- KhaledSaeed18/dotclaude★ 5same name
- tony-hoang-ai-automation/mkt-skills★ 4same name
- lxyer/multi-agent-collaboration-system★ 1same name
- pahlevikun/levistack★ 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 repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- claude-docsSkill
- create-agentSkill
- create-skillSkill
- demoSkill
- design-e2eSkill
- execute-e2e-testsSkill
- fix-github-issueSkill
- telegramSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
4
Distinctive
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
- Distinctive: line 37
After gathering requirements (or parsing arguments), ask:
- Very specific: line 44
Read the shared template: ${CLAUDE_SKILL_DIR}/../../templates/command-template.md
- Distinctive: line 45
Read 2-3 existing commands from the target category for style matching
- Distinctive: line 48
Ask: "Approve, edit, or cancel?"
- Very specific: line 56
Always end the prompt body with $ARGUMENTS so user input is passed through
- Very specific: line 58
If the user's needs are complex (supporting files, tool restrictions, auto-invocation), suggest upgrading to a skill via /create-skill …
- Distinctive: line 59
Keep commands focused — one clear purpose per command
“Common” is measured: kept by at least 6 in 10 of the 7 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 command generator for Claude Code. You create well-structured legacy slash commands following the patterns established in this configuration repo.
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 command file with TODO placeholders
→ If text follows --scaffold, use it as the command 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 command 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 command categories and files:
!ls -R ${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}/../../commands/<category>/- Local: writes to
.claude/commands/<category>/
Generation Flow
- Read the shared template:
${CLAUDE_SKILL_DIR}/../../templates/command-template.md - Read 2-3 existing commands from the target category for style matching
- Generate the command content following template structure and existing conventions
- Display the complete generated file content for review
- Ask: "Approve, edit, or cancel?"
- On approve: write the file to the chosen location, confirm the path
- On edit: ask what to change, regenerate, and display again
- On cancel: abort without writing
Important Rules
- Command files are plain markdown with an optional YAML frontmatter
- Always end the prompt body with
$ARGUMENTSso user input is passed through - Match the persona/style of existing commands in the same category
- If the user's needs are complex (supporting files, tool restrictions, auto-invocation), suggest upgrading to a skill via
/create-skillinstead - Keep commands focused — one clear purpose per command
$ARGUMENTS
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.