Writing Plans

{
  "sections": {
    "Execution Handoff": "After saving the plan, offer execution choice:\r\n\r\n**\"Plan complete and saved to `docs/plans/<filename>.md`. Two execution options:**\r\n\r\n**1. Subagent-Driven (this session)** - I dispatch fresh subagent per task, review between tasks, fast iteration\r\n\r\n**2. Parallel Session (separate)** - Open new session with executing-plans, batch execution with checkpoints\r\n\r\n**Which approach?\"**\r\n\r\n**If Subagent-Driven chosen:**\r\n- **REQUIRED SUB-SKILL:** Use superpowers:subagent-driven-development\r\n- Stay in this session\r\n- Fresh subagent per task + code review\r\n\r\n**If Parallel Session chosen:**\r\n- Guide them to open new session in worktree\r\n- **REQUIRED SUB-SKILL:** New session uses superpowers:executing-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.\r\n\r\nAssume 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.\r\n\r\n**Announce at start:** \"I'm using the writing-plans skill to create the implementation plan.\"\r\n\r\n**Context:** This should be run in a dedicated worktree (created by brainstorming skill).\r\n\r\n**Save plans to:** `docs/plans/YYYY-MM-DD-<feature-name>.md`",
    "Plan Document Header": "> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task.\r\n\r\n**Goal:** [One sentence describing what this builds]\r\n\r\n**Architecture:** [2-3 sentences about approach]\r\n\r\n**Tech Stack:** [Key technologies/libraries]\r\n\r\n---\r\n```",
    "Remember": "- Exact file paths always\r\n- Complete code in plan (not \"add validation\")\r\n- Exact commands with expected output\r\n- Reference relevant skills with @ syntax\r\n- DRY, YAGNI, TDD, frequent commits",
    "Task Structure": "```markdown\r\n### Task N: [Component Name]\r\n\r\n**Files:**\r\n- Create: `exact/path/to/file.py`\r\n- Modify: `exact/path/to/existing.py:123-145`\r\n- Test: `tests/exact/path/to/test.py`\r\n\r\n**Step 1: Write the failing test**\r\n\r\n```python\r\ndef test_specific_behavior():\r\n    result = function(input)\r\n    assert result == expected\r\n```\r\n\r\n**Step 2: Run test to verify it fails**\r\n\r\nRun: `pytest tests/path/test.py::test_name -v`\r\nExpected: FAIL with \"function not defined\"\r\n\r\n**Step 3: Write minimal implementation**\r\n\r\n```python\r\ndef function(input):\r\n    return expected\r\n```\r\n\r\n**Step 4: Run test to verify it passes**\r\n\r\nRun: `pytest tests/path/test.py::test_name -v`\r\nExpected: PASS\r\n\r\n**Step 5: Commit**\r\n\r\n```bash\r\ngit add tests/path/test.py src/path/file.py\r\ngit commit -m \"feat: add specific feature\"\r\n```\r\n```",
    "Bite-Sized Task Granularity": "**Each step is one action (2-5 minutes):**\r\n- \"Write the failing test\" - step\r\n- \"Run it to make sure it fails\" - step\r\n- \"Implement the minimal code to make the test pass\" - step\r\n- \"Run the tests and make sure they pass\" - step\r\n- \"Commit\" - step"
  },
  "content": "**Every plan MUST start with this header:**\r\n\r\n```markdown",
  "id": "writing-plans_obra",
  "name": "writing-plans",
  "description": "Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge"
}

---
name: writing-plans
description: Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge
---

# 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:**

```markdown
# [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]

---
```

## 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**

```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"
```
```

## 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