Agent skill
cook-parallel
[Implementation] Parallel implementation - multiple tasks simultaneously
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/cook-parallel
SKILL.md
[IMPORTANT] Use
TaskCreateto break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI may ask user whether to skip.
Prerequisites: MUST READ .claude/skills/shared/understand-code-first-protocol.md before executing.
Skill Variant: Variant of
/cook— parallel multi-task implementation with subagents.
Quick Summary
Goal: Implement multiple independent tasks simultaneously using parallel fullstack-developer subagents.
Workflow:
- Plan — Create plan with parallel phases and strict file ownership
- Dispatch — Launch fullstack-developer subagents per phase
- Merge — Integrate all changes and verify
- Review — Run code-simplifier and review-changes
Key Rules:
- Phases must have non-overlapping file ownership
- User approval required before dispatching subagents
- Break work into todo tasks; add final self-review task
Execute these tasks in parallel for maximum efficiency: $ARGUMENTS
Mode: PARALLEL - Multiple subagents working concurrently.
Workflow
1. Task Decomposition
- Analyze tasks for independence
- Group into parallelizable work units
- Identify dependencies between units
- Create dependency graph
- External Memory: Write task analysis to
.ai/workspace/analysis/{task-name}.analysis.md. Re-read before parallel dispatch.
2. Parallel Research (if needed)
Launch multiple researcher subagents simultaneously:
Task A research ──┐
Task B research ──┼──► Synthesis
Task C research ──┘
3. Parallel Planning
- Use
plannersubagent with synthesized research - Create plan with parallel-safe phases
- Mark file ownership boundaries (prevent conflicts)
4. Parallel Implementation
Launch multiple fullstack-developer subagents:
Phase 1 (Backend API) ──┐
Phase 2 (Frontend UI) ──┼──► Integration
Phase 3 (Tests) ──┘
Critical: Each subagent must stay within file ownership boundaries.
5. Integration & Testing
- Merge parallel outputs
- Use
testersubagent for integration tests - Use
debuggerif integration issues found
6. Review & Report
- Use
code-reviewerfor final review - Consolidate all changes
- Report to user
Parallelization Rules
| Rule | Description |
|---|---|
| File Ownership | Each subagent owns specific files - no overlap |
| Dependency Order | Respect dependency graph |
| Max Concurrent | 3 subagents max to prevent conflicts |
| Sync Points | Integration checkpoints between phases |
When to Use
- Multi-component features (backend + frontend)
- Large refactoring across independent modules
- Parallel test writing
- Documentation updates alongside code
Example Task Split
"Add user authentication with login UI"
├── Backend API (subagent 1)
│ ├── auth-controller.ts
│ └── auth-service.ts
├── Frontend UI (subagent 2)
│ ├── login-page.component.ts
│ └── login-form.component.ts
└── Tests (subagent 3)
├── auth.spec.ts
└── login.e2e.ts
Trade-offs
| Aspect | Parallel | Sequential |
|---|---|---|
| Speed | ~2-3x faster | Baseline |
| Coordination | Higher complexity | Simple |
| Conflicts | Risk of merge issues | None |
| Context | Split across agents | Unified |
IMPORTANT Task Planning Notes (MUST FOLLOW)
- Always plan and break work into many small todo tasks
- Always add a final review todo task to verify work quality and identify fixes/enhancements
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?