跳到正文
cccskills
免费在 GitHub 公开

slash-commands

Create reusable Claude Code prompts that users invoke with slash commands. Explains project and personal command files, arguments, file references, and Bash output so recurring tasks such as code reviews and commit message drafting have reusable templates.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Create and use Claude Code slash commands - quick prompts, bash execution, file references

查看安装方法

适用场景

  • Turning repeated requests into slash commands
  • Creating shared project review templates
  • Drafting commit messages from Git changes
  • Adding arguments and file references to command templates

包含的文件(1)

  • SKILL.md3.8 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Slash Commands Reference

Create and use user-triggered prompts with /command-name syntax.

When to Use

  • "How do I create a slash command?"
  • "What slash commands are available?"
  • "Add bash to my command"
  • "Use file references in commands"
  • "Slash commands vs skills"

Built-in Commands

CommandPurpose
/clearClear conversation history
/compactCompact conversation with focus
/configOpen settings interface
/costShow token usage
/agentsManage sub-agents
/mcpManage MCP servers
/memoryEdit CLAUDE.md files
/modelSelect AI model
/reviewRequest code review
/resumeResume session
/helpGet usage help

Creating Commands

Project Commands

mkdir -p .claude/commands
cat > .claude/commands/optimize.md << 'EOF'
---
description: Analyze code for performance issues
---

Review this code for:
- Performance bottlenecks
- Memory leaks
- Caching opportunities
EOF

Personal Commands

mkdir -p ~/.claude/commands
cat > ~/.claude/commands/review.md << 'EOF'
---
description: Security-focused code review
---

Check for vulnerabilities:
- Input validation
- SQL injection
- XSS risks
EOF

Command File Format

---
description: Brief description for /help
allowed-tools: [Bash, Read, Write]  # Optional
argument-hint: "[file] [type]"       # Optional
---

Your markdown instructions here.
Use $1, $2 for arguments or $ARGUMENTS for all.

Bash Execution

Run bash before loading prompt with ! prefix:

---
allowed-tools: Bash(git:*), Bash(grep:*)
description: Git commit helper
---

Current status: !`git status`
Staged changes: !`git diff --staged`
Recent commits: !`git log --oneline -5`

Based on these changes, suggest a commit message.

Rules:

  • Must declare allowed-tools: Bash(...) in frontmatter
  • Use backticks: !`command`
  • Output is included in Claude's context

File References

Include files with @ prefix:

Review against @.claude/STYLE_GUIDE.md

Compare:
- @src/old.js
- @src/new.js

Refactor files matching @src/**/*.util.ts

Arguments

---
argument-hint: "[pr-number] [priority]"
---

Review PR #$1 with priority: $2

# Or use all arguments:
Fix issue #$ARGUMENTS

Usage:

/review-pr 456 high
# $1 = "456", $2 = "high"

Namespacing

Organize with subdirectories:

.claude/commands/
├── frontend/
│   └── component.md    → /component (project:frontend)
└── backend/
    └── endpoint.md     → /endpoint (project:backend)

MCP Slash Commands

MCP servers expose prompts as commands:

/mcp__github__list_prs
/mcp__github__pr_review 456
/mcp__jira__create_issue "Bug" high

Slash Commands vs Skills

AspectSlash CommandsSkills
InvocationExplicit: /commandAuto-discovered
FilesSingle .md fileDirectory with SKILL.md
Use CaseQuick promptsComplex workflows

Use slash commands for: Frequently typed prompts, simple templates Use skills for: Complex workflows, multiple files, auto-discovery

Example: Complete Git Commit Command

---
description: Generate semantic commit message
allowed-tools: Bash(git:*), Read
argument-hint: "[type]"
---

# Semantic Commit Generator

Staged files: !`git diff --name-only --cached`

Diff preview:
!`git diff --cached | head -100`

Generate a conventional commit message.
Type: $1 (feat/fix/docs/style/refactor/perf/test/chore)

Format: `<type>(<scope>): <subject>`

Usage: /commit feat

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Coordinate background agents through saved files, keeping lengthy work transcripts out of the main conversation. It defines how to pass results between agents, monitor progress, and verify completed work with tests.

中文简介正在准备中。当前显示英语简介。

  • Keeping long agent transcripts out of the main conversation
  • Passing research and plans between agents through files
  • Checking for stalled background agents
parcadei/Continuous-Claude-v339462026年1月27日 更新

Delegate implementation, file reading, and testing to separate agents, then bring concise summaries back to the main conversation. The rules explain when delegation helps and when a small edit is better handled directly.

中文简介正在准备中。当前显示英语简介。

  • Implementing a feature across multiple files
  • Completing a specific phase of an implementation plan
  • Delegating feature development and testing
parcadei/Continuous-Claude-v339462026年1月27日 更新

Organize implementation work across research, planning, validation, implementation, and review agents. Each stage passes files to the next, while implementation starts with failing tests and the main conversation coordinates the workflow.

中文简介正在准备中。当前显示英语简介。

  • Dividing implementation work among specialized agents
  • Checking a plan against research before implementation
  • Writing failing tests before implementing changes
parcadei/Continuous-Claude-v339462026年1月27日 更新

Connect Agentica SDK agents to Claude Code CLI through a proxy, an intermediary server. Use setup and debugging guidance to address file permissions, streamed responses, result formatting, and agents reporting success without performing the requested operations.

中文简介正在准备中。当前显示英语简介。

  • Connecting Agentica agents to Claude Code tools
  • Investigating file write and edit permission errors
  • Debugging streaming and REPL response formats
parcadei/Continuous-Claude-v339462026年1月27日 更新

Consult Agentica APIs when building workflows where multiple AI agents cooperate. This reference covers eleven coordination patterns, agent tracking, shared state, handoffs, and ways to combine results, with pointers to detailed API specifications.

中文简介正在准备中。当前显示英语简介。

  • Choose a coordination pattern for multiple agents
  • Check pattern constructors and methods
  • Implement custom coordination patterns
parcadei/Continuous-Claude-v339462026年1月27日 更新

Write clearer instructions for Agentica and REPL agents by specifying roles, file operations, and output formats. Includes templates for dividing research, coordinating specialists, reviewing solutions, and passing results between agents through files.

中文简介正在准备中。当前显示英语简介。

  • Clarifying instructions for reading and editing files
  • Dividing research among multiple agents
  • Passing findings and plans between agents
parcadei/Continuous-Claude-v339462026年1月27日 更新

查看 parcadei 的全部技能

报告此技能的问题