菜单
Guide for creating Claude Code slash commands. Use when the user wants to create a new slash command, custom prompt shortcut, or workflow automation command for Claude Code. Helps define command structure, frontmatter, arguments, and best practices.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Create, update, validate, diff, or export DESIGN.md files following the Google Stitch DESIGN.md spec and @google/design.md tooling. Use when the user asks to write/update DESIGN.md, create a design system document, generate design tokens, encode brand/UI guidelines, export a design system, or document UI consistency rules for AI agents. Do NOT use for ordinary UI implementation unless the user asks for DESIGN.md or design-system documentation.
Screens third-party project dependencies for known vulnerabilities and supply-chain risk before installation using a bundled check-deps.py script. Use when user asks to install, add, update, upgrade, or pin packages with npm, pnpm, yarn, bun, pip, uv, poetry, or cargo, or when deciding whether a package version is safe to install. Do NOT use for OS package managers such as apt, brew, yum, apk, or pacman.
Track decisions (AGD) with validation and indexing. Use when making design decisions, recording important choices, discussing trade-offs, or when user mentions AGD or decision record.
End-to-end workflow for developing, debugging, configuring, and shipping pi-coding-agent extensions and pi packages. Use when building or maintaining extensions, skills, prompt templates, themes, settings.json setups, provider integrations, or when updating this skill after pi releases. Do NOT use for general coding questions unrelated to pi extension development.
Fork the current pi session into a new tmux pane. Use when user says /tmux-fork, 'fork to tmux', 'open in new pane', or wants to branch the conversation into a separate tmux pane.
Create and improve Claude Code Skills following official best practices. Use when creating a skill, improving skill descriptions, fixing skill activation issues, or structuring skill directories.
| name | command-creator |
| description | Guide for creating Claude Code slash commands. Use when the user wants to create a new slash command, custom prompt shortcut, or workflow automation command for Claude Code. Helps define command structure, frontmatter, arguments, and best practices. |
Create effective Claude Code slash commands.
⚠️ IMPORTANT: Before creating any command, fetch the latest official guide: https://code.claude.com/docs/en/slash-commands#custom-slash-commands
If any guidance in this skill conflicts with the official documentation, follow the official guide unless the user explicitly requests otherwise.
Slash commands are Markdown files that provide reusable prompts triggered by /command-name. They transform frequently-used prompts into quick shortcuts.
/command-name$ARGUMENTS, $1, $2, etc.!command for bash output, @file for file content| Use Case | Solution |
|---|---|
| Frequently-used prompt | Slash Command |
| Multi-step workflow with resources | Skill |
| Quick automation trigger | Slash Command |
| Complex domain expertise | Skill |
Gather requirements:
| Scope | Location |
|---|---|
| Project (team-shared) | .claude/commands/ |
| Personal (all projects) | ~/.claude/commands/ |
Use subdirectories for namespacing: .claude/commands/frontend/component.md becomes /frontend/component
File Structure:
---
description: Brief description shown in /help
argument-hint: <arg1> [optional-arg]
allowed-tools: Tool1, Tool2(pattern:*)
model: claude-3-5-haiku-20241022
---
Your prompt content here.
Use $ARGUMENTS for all arguments.
Use $1, $2 for positional arguments.
Frontmatter Fields (all optional):
| Field | Purpose |
|---|---|
description | Shown in /help output |
argument-hint | Placeholder shown during autocomplete |
allowed-tools | Tools the command can use without prompting |
model | Override default model for this command |
See references/format.md for detailed syntax.
Keep commands focused - One command, one purpose. Combine with other commands for complex workflows.
Use clear descriptions - Help users understand what the command does from /help.
Specify minimal permissions - Only request tools the command actually needs.
Handle missing arguments - Provide sensible defaults or clear error messages.
Prefer imperative voice - "Analyze the code" not "This command analyzes the code".