Tools Improve

For detailed information beyond this file:

• references/claude-md-reference.md - CLAUDE.md include/exclude criteria, review checklist, @import syntax, modular organization
• references/skills-reference.md - Invocation control, context budget, hooks, progressive disclosure, testing, troubleshooting
• references/subagents-reference.md - Built-in agents, permission modes, hook events, MCP access, memory, resume
• references/agent-teams-reference.md - Team orchestration, task coordination, display modes, troubleshooting

Decision: Skill vs Subagent

Use SUBAGENT when:

• Task produces high-volume output (tests, logs, exploration)
• Need parallel execution (concurrent research tasks)
• Need strict tool restrictions with validation hooks
• Work is self-contained and returns a summary

Use SKILL when:

• Reusable instructions/knowledge for main conversation
• Side effects user must control → disable-model-invocation: true
• Background knowledge Claude should apply → user-invocable: false
• Quick reference or style guides

Default to skill - simpler, runs in main context.

When a skill needs parallel workers, it can orchestrate an agent team internally. See "Agent Teams in Skills" under Best Practices and references/agent-teams-reference.md for the full guide.

Templates

Skill Template

Create .claude/skills/<name>/SKILL.md (project-level) or skills/<name>/SKILL.md (plugin-level):

---