AgentSkillsCN

writing-subagents

为.claude/agents/创建Claude Code子代理配置。定义拥有独立上下文的专用代理。当您需要为代码审查、测试，或特定领域的任务打造专属代理时，可使用此技能。

SKILL.md
--- frontmatter
name: writing-subagents
description: Creates Claude Code subagent configurations for .claude/agents/. Defines specialized agents with isolated contexts. Use when creating dedicated agents for code review, testing, or domain-specific tasks.

Subagent Creator

Create specialized subagents that run in isolated contexts via the Task tool.

Core Principles

  1. •Isolated Context - Each subagent has its own context window
  2. •Specialized Role - One clear responsibility per subagent
  3. •Minimal Tools - Grant only necessary tool access
  4. •Clear Trigger - Description must indicate when to use

Subagent Structure

code
.claude/agents/
├── code-reviewer.md      # Project-level
├── test-runner.md
└── domain-expert.md

User-level agents go in ~/.claude/agents/.

File Format

yaml
---
name: agent-name
description: What this agent does. Use proactively when [triggers].
tools: Read, Grep, Glob, Bash
model: sonnet
skills: skill1, skill2
permissionMode: default
---

System prompt for the agent.

## Role
[Clear description of the agent's role]

## Process
[Steps the agent should follow]

## Output Format
[Expected output structure]

Configuration Fields

FieldRequiredDescription
nameYesLowercase with hyphens: code-reviewer
descriptionYesInclude "Use proactively when..." for auto-invoke
toolsNoCSV list; omit to inherit all tools
modelNosonnet, opus, haiku, or inherit
skillsNoAuto-load skills when invoked
permissionModeNodefault, acceptEdits, bypassPermissions, plan

Model Selection

ModelUse Case
haikuFast exploration, simple tasks
sonnetBalanced capability (default)
opusComplex reasoning, architecture
inheritUse main conversation's model

Tool Recommendations

Subagent TypeRecommended Tools
Code reviewerRead, Grep, Glob, Bash
Test runnerRead, Bash, Grep
ExplorerRead, Glob, Grep, Bash
WriterRead, Edit, Write, Bash

Trigger Patterns

For automatic invocation, include in description:

  • •"Use proactively when..."
  • •"Use immediately after..."
  • •"MUST BE USED when..."

For manual invocation, omit proactive triggers.

Validation Checklist

  • • Name is lowercase with hyphens
  • • Description has clear trigger
  • • Tools are minimal and appropriate
  • • No overlapping responsibility with other agents
  • • System prompt is focused and actionable

References