claude-world/director-mode-lite / skills/agents
agents
VerifiedList all available agents (core, expert, self-evolving). Use when the user asks what agents are available or runs /agents.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.3 KB |
SKILL.md
View on GitHub---
name: agents
description: List all available agents (core, expert, self-evolving). Use when the user asks what agents are available or runs /agents.
user-invocable: true
---
# 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](../evolving-loop/SKILL.md) 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
1. **Auto-activate** based on context
2. **Follow specific methodologies**
3. **Provide structured output**
4. **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
```markdown
---
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`
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Unverified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |