writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
When & Why to Use This Skill
The writing-plans skill is a specialized tool for transforming high-level technical specifications into granular, actionable implementation plans. It bridges the gap between requirements and execution by generating a structured roadmap that emphasizes Test-Driven Development (TDD), DRY principles, and atomic commits, ensuring high-quality code delivery even in complex or unfamiliar codebases.
Use Cases
- Technical Roadmap Generation: Converting a product requirement document (PRD) or feature spec into a step-by-step technical execution plan with specific file paths and logic.
- Enforcing TDD Workflows: Automatically defining failing test cases and minimal implementation steps to ensure code quality and test coverage from the start.
- Developer Onboarding and Handoff: Creating comprehensive documentation for tasks that allows developers with zero context to implement features correctly by following bite-sized instructions.
- Complex Refactoring Management: Breaking down large-scale code changes into 2-5 minute atomic tasks to minimize errors and facilitate frequent, clean git commits.
- Subagent Orchestration: Preparing structured plans that can be handed off to specialized subagents for automated parallel execution and review.
| name | writing-plans |
|---|---|
| description | Use when you have a spec or requirements for a multi-step task, before touching code |
| author | obra |
| version | "1.0" |
Writing Plans
Overview
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."
Context: This should be run in a dedicated worktree (created by brainstorming skill).
Save plans to: docs/plans/YYYY-MM-DD-<feature-name>.md
Bite-Sized Task Granularity
Each step is one action (2-5 minutes):
- "Write the failing test" - step
- "Run it to make sure it fails" - step
- "Implement the minimal code to make the test pass" - step
- "Run the tests and make sure they pass" - step
- "Commit" - step
Plan Document Header
Every plan MUST start with this header:
# [Feature Name] Implementation Plan
> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task.
**Goal:** [One sentence describing what this builds]
**Architecture:** [2-3 sentences about approach]
**Tech Stack:** [Key technologies/libraries]
---
```text
## Task Structure
```markdown
### 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
def function(input):
return expected
```text
### 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"
## Remember
- Exact file paths always
- Complete code in plan (not "add validation")
- Exact commands with expected output
- Reference relevant skills with @ syntax
- DRY, YAGNI, TDD, frequent commits
## Execution Handoff
After saving the plan, offer execution choice:
**"Plan complete and saved to `docs/plans/<filename>.md`. Two execution options:**
**1. Subagent-Driven (this session)** - I dispatch fresh subagent per task, review between tasks, fast iteration
**2. Parallel Session (separate)** - Open new session with executing-plans, batch execution with checkpoints
**Which approach?"**
**If Subagent-Driven chosen:**
- **REQUIRED SUB-SKILL:** Use superpowers:subagent-driven-development
- Stay in this session
- Fresh subagent per task + code review
**If Parallel Session chosen:**
- Guide them to open new session in worktree
- **REQUIRED SUB-SKILL:** New session uses superpowers:executing-plans