Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
中文简介正在准备中。当前显示原文说明。
claude-world/director-mode-lite802026年8月31日 更新
免费在 GitHub 公开
agents
List all available agents (core, expert, self-evolving). Use when the user asks what agents are available or runs /agents.
中文简介正在准备中。当前显示原文说明。
查看安装方法包含的文件（1）
- SKILL.md2.3 KB
SKILL.md（原文）
安装前可以查看交给 AI 代理的指令内容。
Available Agents
List all agents available in Director Mode Lite.
Core Agents
| Agent | Purpose |
|---|---|
code-reviewer | Reviews code for quality, security, and best practices after changes or on PRs |
debugger | Root-cause analysis for errors, test failures, and unexpected behavior |
doc-writer | Creates and maintains README, API docs, and code comments |
Expert Agents
| Agent | Purpose |
|---|---|
claude-md-expert | CLAUDE.md design patterns, best practices, and project configuration |
mcp-expert | MCP server configuration, troubleshooting, and discovery |
agents-expert | Creating, configuring, and using custom agents |
skills-expert | Creating, configuring, and managing custom skills and commands |
hooks-expert | Designing and troubleshooting PreToolUse/PostToolUse hooks |
Self-Evolving Agents
Used by /evolving-loop to run the autonomous development cycle.
| Agent | Purpose |
|---|---|
evolving-orchestrator | Coordinates the loop phases and manages memory; returns brief summaries |
requirement-analyzer | Extracts acceptance criteria, complexity, and implementation strategy |
skill-synthesizer | Generates tailored executor, validator, and fixer skills |
completion-judge | Evaluates validation results and decides continue / evolve / ship |
experience-extractor | Analyzes successes and failures to extract improvement suggestions |
skill-evolver | Applies learning insights to produce improved skill versions |
How Agents Work
- Auto-activate based on context
- Follow specific methodologies
- Provide structured output
- Can be explicitly invoked
Using Agents
"Use code-reviewer to check src/auth/"
"I need the debugger - tests are failing"
"Have doc-writer update the API docs"
Creating Custom Agents
---
name: my-agent
description: What this agent does, and when to use it
color: blue
tools:
- Read
- Grep
- Glob
- Bash
model: sonnet
---
# Agent Name
## When to Activate
## Process
## Output Format
Save to .claude/agents/my-agent.md
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。
同一仓库的技能
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.
中文简介正在准备中。当前显示原文说明。
claude-world/director-mode-lite802026年8月31日 更新
TDD-based autonomous development loop with checkpoint recovery and observability changelog
中文简介正在准备中。当前显示原文说明。
claude-world/director-mode-lite802026年8月31日 更新
View and manage the runtime changelog for observability
中文简介正在准备中。当前显示原文说明。
claude-world/director-mode-lite802026年8月31日 更新
Track development session events in a daily markdown changelog, including file changes, test results, and key decisions.
中文简介正在准备中。当前显示原文说明。
claude-world/director-mode-lite802026年8月31日 更新
Verify Claude, Codex, and Grok availability plus Director guidance, relay, agents, and skills. Audit optional hooks only when selected. Use after installation or when a native surface misbehaves.
中文简介正在准备中。当前显示原文说明。
claude-world/director-mode-lite802026年8月31日 更新