# Writing Plans

> Write a practical implementation plan when multi-step work needs task boundaries, dependencies, and acceptance checks.

- Skill: `seaworld008/writing-plans` (Agent Skill)
- Install (CLI): `npx skillmds add seaworld008/writing-plans`
- Raw SKILL.md: https://api.skillmd.com/api/skills/seaworld008/writing-plans/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: seaworld008 (https://skillmd.com/u/seaworld008)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/seaworld008/writing-plans

---


# Writing Plans

## Overview

Write comprehensive implementation plans for an engineer who needs the relevant repository context. 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.

Describe the constraints and interfaces that matter; rely on the implementer's judgment for routine coding details.

**Announce at start:** "I'm using the writing-plans skill to create the implementation plan."

**Context:** Reuse the current task workspace; isolate it when existing changes or parallel work require that.

**Save plans to:** `docs/plans/YYYY-MM-DD-<feature-name>.md`

## Bite-Sized Task Granularity

**Use coherent, independently verifiable tasks; the following test cycle is useful for behavior changes:**
- "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
- Describe interfaces, behavior, and acceptance criteria; include code only to resolve ambiguity
- Exact commands with expected output
- Reference relevant skills with @ syntax
- DRY, YAGNI, TDD, frequent commits

## Execution Handoff

After saving the plan, continue implementation if already requested. Offer the following choices only when the user has not selected an execution path:

**"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