菜单
List all available skills grouped by category. Use when the user asks what skills are available or runs /skills.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/claude-world/director-mode-lite --skill skills命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Direct substantial repository work across Claude Code, Codex CLI, or Grok Build with a concise brief, parallel agents, evidence-based completion, and optional cross-CLI continuation. Use for project onboarding, multi-step implementation, agent coordination, verification planning, low-interruption setup, or deciding how another CLI should take over. Do not use it as a permission gate or mandatory workflow.
Continue a task in Claude Code through a portable Director handoff packet. Use when work started in Codex CLI or Grok Build should move to Claude, or when a fresh Claude session needs the current decisions and verification evidence.
Continue a task in OpenAI Codex CLI through a portable Director handoff packet. Use when the user asks Codex to take over, wants an independent Codex implementation or review, or needs to preserve decisions and verification while changing CLIs.
基于 SOC 职业分类
正在显示 SKILL.md
| name | skills |
| description | List all available skills grouped by category. Use when the user asks what skills are available or runs /skills. |
| user-invocable | true |
List all skills available in Director Mode Lite.
Slash-prefixed names (/name) are user-invocable commands. Bare names are internal — Claude runs them automatically when relevant.
| Skill | Function |
|---|---|
/workflow | Complete 5-step development flow (research, plan, implement, test, review) |
/plan | Break a task into a detailed execution plan |
/focus-problem | Deep problem analysis using Explore agents |
/test-first | Test-Driven Development (Red-Green-Refactor) |
/smart-commit | Conventional Commits with pre-commit quality checks |
| Skill | Function |
|---|---|
/auto-loop | Autonomous TDD loop with checkpoint recovery |
/evolving-loop | Self-evolving loop that generates and evolves its own skills |
/evolving-status | View evolving-loop session status, history, and memory |
/changelog | View and manage the runtime observability changelog |
| Skill | Function |
|---|---|
/getting-started | Guided 5-minute onboarding for Director Mode Lite |
/project-init | Expert-guided project setup (6 phases) |
/project-health-check | Full project health audit (7 checks) |
/check-environment | Verify the development environment is ready |
/agents | List all available agents |
/skills | List all available skills |
| Skill | Function |
|---|---|
/claude-md-check | Validate CLAUDE.md structure and completeness |
/agent-check | Validate agent file format and structure |
/skill-check | Validate skill/command file format and structure |
/hooks-check | Validate hooks configuration and scripts |
/mcp-check | Validate MCP configuration |
| Skill | Function |
|---|---|
/claude-md-template | Generate a CLAUDE.md for the current project |
/agent-template | Generate a custom agent from template |
/skill-template | Generate a custom skill/command from template |
/hook-template | Generate a hook script from template |
| Skill | Function |
|---|---|
/handoff-claude | Delegate to another authorized Claude Code account/profile via claude -p |
/handoff-codex | Delegate bulk mechanical tasks to OpenAI Codex CLI (codex exec) |
/handoff-grok | Prepare or explicitly launch work with xAI Grok Build CLI |
/handoff-gemini | Delegate long-context analysis to Google Gemini CLI (gemini -p) |
/session-relay | Continue unfinished work in a new Claude, Codex, or Grok native session |
/director-mode | Define a concise outcome, context, constraints, and evidence brief |
Not slash commands — Claude activates these automatically when it judges them relevant.
| Skill | Function |
|---|---|
code-reviewer | Reviews code for quality, security, and best practices |
debugger | Root-cause analysis and problem resolution |
doc-writer | Writes README, API docs, and code comments |
test-runner | Runs tests and ensures coverage |
interop-router | Suggests Claude, Codex, or Grok when another CLI may fit; never executes it |
---
name: my-skill
description: What this skill does
user-invocable: true
---
# Skill Name
## Purpose
## Workflow
## Output
Save to .claude/skills/my-skill/SKILL.md