Agent skill
Task Layering
Breaks down specs into complexity-stratified tasks. Use when organizing tasks, assigning work to agents, or when user mentions task layering, task stratification, or parallel task execution.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/task-layering
SKILL.md
Task Layering
This skill provides task stratification by complexity and agent assignment for parallel execution.
What This Skill Provides
1. Complexity Stratification
- Trivial (0): < 5 minutes, simple changes
- Simple (1): < 30 minutes, straightforward implementation
- Moderate (2): < 2 hours, requires thought
- Complex (3): > 2 hours, architectural decisions
2. Agent Assignment Strategy
- @claude: Complex (3), security, architecture
- @copilot: Trivial (0), Simple (1)
- @qwen: Performance optimization
- @gemini: Documentation
- @codex: Testing, TDD
3. Layer Organization
- Foundation Layer: Must complete first (dependencies)
- Parallel Layer: Can execute simultaneously
- Integration Layer: Combines parallel work
4. Output Files
layered-tasks.md- All tasks stratified by complexityclaude-tasks.md- Tasks assigned to Claudecopilot-tasks.md- Tasks assigned to Copilotqwen-tasks.md- Tasks for performance workgemini-tasks.md- Documentation taskscodex-tasks.md- Testing tasks
Instructions
Stratifying Tasks
When user wants to layer tasks from a spec:
-
Read the spec's tasks.md file
-
Analyze each task for:
- Estimated time to complete
- Required expertise level
- Dependencies on other tasks
- Appropriate agent assignment
-
Create layered-tasks.md with format:
markdown# Layered Tasks: [Spec Name] ## Foundation Layer (Sequential) - [Complex] Task 1 (@claude) - Requires arch decisions - [Moderate] Task 2 (@claude) - Core implementation ## Parallel Layer (Concurrent) - [Simple] Task 3 (@copilot) - UI component - [Simple] Task 4 (@copilot) - Data model - [Moderate] Task 5 (@qwen) - Query optimization ## Integration Layer (Sequential) - [Moderate] Task 6 (@claude) - Integrate components - [Simple] Task 7 (@codex) - Integration tests -
Create agent-specific task files for distribution
Task Complexity Analysis
Trivial (0) Examples:
- Update constant value
- Fix typo
- Add simple validation
Simple (1) Examples:
- Create CRUD component
- Add new API endpoint
- Write unit test
Moderate (2) Examples:
- Implement authentication flow
- Optimize database queries
- Refactor module structure
Complex (3) Examples:
- Design system architecture
- Implement security layer
- Create caching strategy
Layered Tasks Format
# Layered Tasks: Feature Name
## Summary
- Total tasks: 15
- Foundation: 3 tasks
- Parallel: 10 tasks
- Integration: 2 tasks
## Foundation Layer
Must complete in order before parallel work:
### 1. [Complex] Design Data Schema (@claude)
**Dependencies**: None
**Estimate**: 3 hours
**Description**: Design database schema and relationships
## Parallel Layer
Can execute simultaneously:
### 2. [Simple] Create User Model (@copilot)
**Dependencies**: Task 1
**Estimate**: 20 minutes
### 3. [Simple] Create Auth Component (@copilot)
**Dependencies**: Task 1
**Estimate**: 30 minutes
## Integration Layer
Combine parallel work:
### 15. [Moderate] Integration Testing (@codex)
**Dependencies**: All parallel tasks
**Estimate**: 1 hour
Success Criteria
- ✅ Tasks are stratified by realistic complexity
- ✅ Dependencies are identified correctly
- ✅ Agent assignments match expertise
- ✅ Layers enable maximum parallelization
- ✅ Output files are complete and actionable
Plugin: 04-iterate Skill Type: Analysis + Organization Auto-invocation: Yes (via description matching)
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?