Loading...
Loading...
Use when you have specs or requirements for a multi-step task to break it down into detailed tasks, before executing it
npx skill4agent add davidkiss/smart-ai-skills task-breakdowndocs/YYYY-MM-DD-<feature-name>-tasks.md# [Task Name] Task Breakdown
> **For Claude:** REQUIRED SUB-SKILL: Use executing-plan skill to execute this task breakdown task-by-task.
**Goal:** [One sentence describing what this achieves]
**Approach:** [2-3 sentences about approach]
**Skills:** [List of skills to use]
**Tech Details:** [Key tools, services, technologies/libraries to use]
---### Task N: [Component Name]
**Files:**
- Create: `exact/path/to/file.py`
- Modify: `exact/path/to/existing.py:123-145`
- Test: `tests/exact/path/to/test.py`
**Step 1: Write the failing test**
```python
def test_specific_behavior():
result = function(input)
assert result == expectedpytest tests/path/test.py::test_name -vdef function(input):
return expectedpytest tests/path/test.py::test_name -vgit add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"
## Remember
- Exact file paths always
- For coding tasks, complete code in task breakdown (not "add validation")
- Exact commands with expected output
- Reference relevant skills with @ syntax
- DRY, YAGNI, TDD
## Execution Handoff
After saving the task breakdown, offer task execution:
**"Task breakdown complete and saved to `docs/YYYY-MM-DD-<feature-name>-tasks.md`.**
**Subagent-based task execution (this session)** - I dispatch fresh subagent per task, review between tasks, fast iteration
- **REQUIRED SUB-SKILL:** Use subagent-task-execution
- Stay in this session
- Fresh subagent per task + code review