メニュー
Use after an approved design/spec or clear requirements exist and before implementing a multi-step task; creates a task-by-task implementation plan before code changes.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use after completing an implementation task or major feature, and before claiming ready/merge, to verify the work meets requirements via a focused reviewer subagent.
Use after an implementation plan exists and it contains independent tasks that can be delegated to fresh subagents in the current session.
Use after planning/brainstorming when implementation begins for any feature or bugfix, before writing production code; requires tests first and red-green verification.
Use after making code changes, before committing, or when the user asks to "simplify", "clean up", or "review" recent edits — runs three parallel review agents (reuse, quality, efficiency) over the diff and fixes the findings.
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or evaluating a plan/design. Relentlessly explores user intent, requirements, trade-offs, and decision branches before implementation.
| name | writing-plans |
| description | Use after an approved design/spec or clear requirements exist and before implementing a multi-step task; creates a task-by-task implementation plan before code changes. |
Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.
Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.
Announce at start: "I'm using the writing-plans skill to create the implementation plan."
Save plans to: docs/pi/plans/YYYY-MM-DD-<feature-name>.md
If the spec covers multiple independent subsystems, it should have been broken into sub-project specs during brainstorming. If it wasn't, suggest breaking this into separate plans — one per subsystem. Each plan should produce working, testable software on its own.
Before defining tasks, map out which files will be created or modified and what each one is responsible for. This is where decomposition decisions get locked in.
This structure informs the task decomposition. Each task should produce self-contained changes that make sense independently.
Each step is one action (2-5 minutes):
Every plan MUST start with this header:
# [Feature Name] Implementation Plan
> **For agentic workers:** REQUIRED SUB-SKILL: Use subagent-driven-development to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
**Goal:** [One sentence describing what this builds]
**Architecture:** [2-3 sentences about approach]
**Tech Stack:** [Key technologies/libraries]
---
### 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 == expected
```
- [ ] **Step 2: Run test to verify it fails**
Run: `pytest tests/path/test.py::test_name -v`
Expected: FAIL with "function not defined"
- [ ] **Step 3: Write minimal implementation**
```python
def function(input):
return expected
```
- [ ] **Step 4: Run test to verify it passes**
Run: `pytest tests/path/test.py::test_name -v`
Expected: PASS
- [ ] **Step 5: Commit**
```bash
git add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"
```
Every step must contain the actual content an engineer needs. These are plan failures — never write them:
After writing the complete plan, look at the spec with fresh eyes and check the plan against it. This is a checklist you run yourself — not a subagent dispatch.
1. Spec coverage: Skim each section/requirement in the spec. Can you point to a task that implements it? List any gaps.
2. Placeholder scan: Search your plan for red flags — any of the patterns from the "No Placeholders" section above. Fix them.
3. Type consistency: Do the types, method signatures, and property names you used in later tasks match what you defined in earlier tasks? A function called clearLayers() in Task 3 but clearFullLayers() in Task 7 is a bug.
If you find issues, fix them inline. No need to re-review — just fix and move on. If you find a spec requirement with no task, add the task.
After self-review passes, dispatch a fresh-context reviewer subagent using ./plan-document-reviewer-prompt.md (resolve relative to this SKILL.md):
subagent({ agent: "reviewer", task: <filled template>, context: "fresh" })
Fill [PLAN_FILE_PATH] with the written plan path and [SPEC_FILE_PATH] with the source spec path. If no separate spec file exists, use the user's original request or the closest requirements document as the spec reference.
If the reviewer returns Issues Found, fix every blocking issue and repeat self-review plus reviewer pass. Treat recommendations as advisory; apply them only when they materially improve implementation readiness.
After saving the plan, offer execution handoff:
**"Plan complete and saved to docs/pi/plans/<filename>.md.
If you want, I can execute it now with subagent-driven-development: fresh subagent per task plus two-stage review (spec compliance, then code quality). Want me to start?"**
If user says yes: