/shipyard-writing-plans

name: shipyard-writing-plans
description: Use when you have a spec, requirements, or design for a multi-step task — before touching code. Also triggers on "plan this", "break this down", "create tasks", "decompose this feature", or when a task clearly needs more than 2-3 steps to implement. If you're about to start building without a plan, or writing vague tasks like "implement feature X" without file paths and verification commands, this skill applies.

<!-- TOKEN BUDGET: 290 lines / ~870 tokens -->

Writing Plans

<activation>

When This Skill Activates

• You have a spec, requirements, or design for a multi-step implementation task
• You need to break work into bite-sized, executable tasks before touching code
• You are preparing work for builder agents or a parallel execution session

**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`

Natural Language Triggers

• "write a plan", "create a plan", "plan this feature", "break this down into tasks"

</activation>

<instructions>

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.

Shipyard Plan Format

Shipyard plans use XML-structured tasks with verification criteria. Each task includes:

<task id="1" name="Component Name">
  <description>What this task accomplishes</description>
  <files>
    <create>exact/path/to/file.py</create>
    <modify>exact/path/to/existing.py:123-145</modify>
    <test>tests/exact/path/to/test.py</test>
  </files>
  <steps>
    <step>Write the failing test</step>
    <step>Run test to verify it fails</step>
    <step>Write minimal implementation</step>
    <step>Run test to verify it passes</step>
    <step>Commit</step>
  </steps>
  <verification>
    <command>pytest tests/path/test.py::test_name -v</command>
    <expected>PASS</expected>
  </verification>
</task>

This structured format enables `/shipyard:build` to parse and execute tasks systematically, and `/shipyard:status` to track progress.

Task Granularity Guide

| Size | Example | Action | |------|---------|--------| | **Too big** | "Implement authentication system" | Split — no single commit for a whole system | | **Right size** | "Add JWT token validation middleware" | Keep — one TDD cycle, one commit | | **Too small** | "Add import statement" | Merge with its parent task |

**Target:** Each task = one TDD cycle (write test → fail → implement → pass → commit). If a task needs more than one commit, split it.

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

Coupling Detection

Before ordering tasks, check for dependencies. Tasks that must share state or touch the same file need sequencing:

| Dependency Type | Example | Resolution | |----------------|---------|------------| | Same file | Tasks A and B both modify `auth.py` | Sequence them; never parallelize | | Import dependency | Task B imports what Task A creates | B blocks on A | | Interface contract | Task B depends on Task A's return type | Define interface in Task A, implement in B | | Shared utility | Both tasks call a helper that doesn't exist yet | Create helper as Task 0 |

**Red flag:** Two tasks listed as parallelizable that both modify the same file — this will produce merge conflicts.

Mid-Phase Adaptation

When reality diverges from the plan during execution:

• **Minor divergence** (file path changed, one extra step) — adapt in place, note in SUMMARY.md
• **Major divergence** (wrong architecture, missing component) — pause, update plan, re-approve before continuing
• **Blocker** (dependency missing, API changed) — stop, document in SUMMARY.md as blocker, escalate

Do not silently adapt major changes. The plan is a contract; changes need acknowledgment.

Plan Document Header

**Every plan MUST start with this header:**

# [Feature Name] Implementation Plan

> **For Claude:** REQUIRED SUB-SKILL: Use shipyard:shipyard-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

### 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

**Step 4: Run test to verify it passes**

Run: `pytest tests/path/test.py::test_name -v` Expected: PASS

**Step 5: Commit**

git add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"

</instructions>

<examples>

## Example: Well-Written vs Poorly-Written Plan Task

<example type="good" title="Clear, executable task with exact paths and code">
### Task 2: Add Email Validation

**Files:**
- Create: `src/validators/email.py`
- Test: `tests/validators/test_email