agent-skill-mapping
Skillの割当表(agent -> skills)を作るときのルール集。skill-assigner が mapping を更新するときに参照する。
When & Why to Use This Skill
This Claude skill provides a comprehensive framework and governance model for managing agent-to-skill mappings. It streamlines the orchestration of multi-agent systems by defining clear rules for skill assignment, reducing redundancy, and managing dependencies. By automating the generation of activation rules and mapping files, it ensures that agents are triggered accurately and operate within safe, well-defined boundaries.
Use Cases
- Multi-Agent Architecture Optimization: Use the redundancy rules to ensure that specific procedural skills are not duplicated across multiple agents, maintaining a lean and efficient system.
- Automated Skill Mapping: Automatically update and verify the `.claude/agent-skill-map.yaml` file to ensure all agents have the correct tool access without manual configuration errors.
- Safety and Risk Management: Implement the 'Dangerous Operation Isolation' rule to separate high-risk tasks into dedicated agents that require human review, enhancing system security.
- Dependency Enforcement: Ensure that implementation-focused skills are always paired with validation skills (like linting or testing) to maintain high output quality across the agent ecosystem.
| name | agent-skill-mapping |
|---|---|
| description | Skillの割当表(agent -> skills)を作るときのルール集。skill-assigner が mapping を更新するときに参照する。 |
Agent-Skill Mapping Rules
Inputs
.claude/agents/*.md.claude/skills/*/SKILL.md
Outputs
.claude/agent-skill-map.yaml.claude/agent-activation-rules.md
Rules
- 重複を減らす:同じ手順系Skillを複数agentへ持たせない
- 依存関係を明示:impl-* は検証(tests/lint)とセットにする
- 危険操作は隔離:必要なら専用agent + human review 必須
Verification
agent-skill-map.yamlがスキル名のタイポなしで参照していることactivation rulesに「どの入力でどのagentを起動するか」が書かれていること
Evidence
- N/A (bootstrap skill)