mcp-chain-of-thought/src/prompts/templates_en/executeTask/subtaskEvaluation.md

Chain of Thought is a tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavi

## Subtask Evaluation

⚠️ **IMPORTANT: You MUST complete this evaluation step before proceeding** ⚠️

### Assessment Criteria

Based on the complexity assessment of this task, determine if it should be split into smaller subtasks:

1. **Task Size Evaluation**:
   - Is the task description unusually long and detailed?
   - Does the task involve multiple distinct components or features?
   - Would the implementation require changes to multiple parts of the codebase?

2. **Scope Boundaries**:
   - Are there natural boundaries where the task can be divided?
   - Can independent modules or features be identified?
   - Could multiple people work on different parts simultaneously?

3. **Risk Management**:
   - Would failures in one part of the task endanger the entire implementation?
   - Would splitting the task make testing and verification more manageable?
   - Would smaller subtasks reduce the overall complexity and risk?

### Decision Process

{complexityBasedGuidance}

### How to Split Tasks

If you determine that splitting is necessary:

1. Identify logical boundaries for subtasks
2. Ensure each subtask is independently executable
3. Define clear dependencies between subtasks
4. Use the `split_tasks` tool to create the subtasks with:
   - Clear individual descriptions
   - Defined dependencies between subtasks
   - Proper sequencing for execution

Document your evaluation conclusion before proceeding with task execution or splitting.