AgentSkillsCN

implement-claude-extensions

通过对比钩子、技能、子代理、代理团队与插件打包模式,选择并实施合适的Claude扩展类型。

SKILL.md
--- frontmatter
name: implement-claude-extensions
description: Choose and implement the right Claude extension type by comparing hooks, skills, sub-agents, agent teams, and plugin packaging patterns.

Implement Claude Extensions

Use this umbrella skill to choose the correct extension type and route implementation to the appropriate component skill.

Core Principle: Start simple. Use the decision framework to score task complexity (0-10) and match to the simplest component type that meets requirements.

Complexity-Based Selection

ScoreComponent TypeWhen to Use
1-3Simple SkillSingle deterministic task, no branching logic
4-6Workflow SkillMulti-step with some conditional logic
7-8Sub-AgentModel-driven decisions, flexible approach needed
9-10Agent TeamMultiple specialized domains, complex coordination

See references/decision-framework.md for detailed scoring guide.

Comparison

Extension TypeBest ForPrimary ArtifactsComponent Skill
HooksEvent-driven automation/guardrailshooks/hooks.json, hook scripts../implement-hooks/SKILL.md
Agent SkillsReusable task playbooksskills/<name>/SKILL.md../implement-agent-skills/SKILL.md
Sub-AgentsSpecialized delegated rolesagents/*.md../implement-sub-agents/SKILL.md
Agent TeamsCoordinated multi-agent executionteam config + coordination docs../implement-agent-teams/SKILL.md
PluginsPackaging/distribution + wiring.claude-plugin/plugin.json../implement-plugin/SKILL.md

Workflow

  1. Assess complexity: Score task complexity using decision framework (0-10)
  2. Start simple: Choose simplest component type that meets requirements
  3. Validate choice: Ask "Can this be done more simply?"
  4. Identify constraints: Determine specific requirements and boundaries
  5. Plan evaluations: Define 20-50 test cases for validation
  6. Route implementation: Hand off to appropriate component skill
  7. Apply lifecycle checks: Follow design → implement → evaluate → verify

Progressive Disclosure

Best Practices (Anthropic Guidelines)

  • Core principles: ../../docs/ANTHROPIC_BEST_PRACTICES.md
    • Central hub with links to detailed references:
      • Complexity scoring & decision framework: references/decision-framework.md
      • Context management patterns: references/context-management.md
      • Evaluation strategy: references/evaluation-strategy.md

Component Selection

  • Extension comparison details: references/extension-types.md
  • Decision guide: references/when-to-use.md
  • Cross-component patterns: references/cross-component-patterns.md
  • Lifecycle from design to verification: references/extension-lifecycle.md

Component Skills

  • ../implement-hooks/SKILL.md
  • ../implement-agent-skills/SKILL.md
  • ../implement-sub-agents/SKILL.md
  • ../implement-agent-teams/SKILL.md
  • ../implement-plugin/SKILL.md

Sources