Agent skill
team
并行团队执行,N 个协调 Worker 协作
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/team-1molchuan-oh-my-ccg
SKILL.md
oh-my-ccg Team Mode
Coordinate N parallel workers for independent tasks.
Activation
Command: /oh-my-ccg:team N "task description" where N is worker count.
Or automatically triggered during impl phase when independent tasks detected.
Workflow
- Analyze tasks: Identify independent task groups from the plan
- Create team: TeamCreate with task list
- Spawn workers: Launch N executor agents
- Route tasks via MCP tools:
- Frontend tasks → workers call
ask_gemini(agent_role="designer")for prototypes before implementing - Backend tasks → workers call
ask_codex(agent_role="architect")for prototypes before implementing - General tasks → standard executor workers (no external model needed)
- Frontend tasks → workers call
- Monitor: Track completion via TaskList
- Verify: Run verifier on all completed work
- Fix loop: If issues found, assign fixes to available workers
- Cleanup: Shutdown workers, delete team
Worker MCP Access
Each worker can call the plugin's MCP tools:
ask_codex/ask_gemini— for domain-specific prototypes and reviewsrpi_state_read— to check current RPI progress- Workers should use
background: falsefor their MCP calls (each worker is already parallel)
Task Distribution
- Each worker claims one task at a time
- Workers prefer tasks in ID order (lowest first)
- When a task completes, worker claims next available
- Blocked tasks wait for dependencies to resolve
Parallel Guidelines
- Maximum 5 concurrent workers (configurable)
- Each worker gets its own executor agent
- Workers share state via task list
- Workers must not modify same files simultaneously
Cancellation
/oh-my-ccg:cancel sends shutdown to all workers.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?