Writing Plans

Adapted from obra/superpowers for Cursor IDE.

Overview

Write comprehensive implementation plans assuming the engineer has zero context for the codebase and questionable taste. Document everything they need: which files to touch, code, testing, docs, how to test. Give them the plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.

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

Save plans to: docs/plans/YYYY-MM-DD-<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:

markdown

# [Feature Name] Implementation Plan

**Goal:** [One sentence describing what this builds]
**Architecture:** [2-3 sentences about approach]
**Tech Stack:** [Key technologies/libraries]

Task Structure

Each task should include:

•Files: Create/Modify/Test paths
•Step 1: Write the failing test (with code)
•Step 2: Run test to verify it fails (with command + expected output)
•Step 3: Write minimal implementation (with code)
•Step 4: Run test to verify it passes (with command + expected output)
•Step 5: Commit (with exact commands)

Remember

•Exact file paths always
•Complete code in plan (not "add validation")
•Exact commands with expected output
•DRY, YAGNI, TDD, frequent commits

Execution Handoff

After saving the plan, offer execution choice:

1. Subagent-Driven (this session) - Dispatch fresh subagent per task via Cursor's Task tool, review between tasks

2. Batch Execution (this session) - Execute tasks in batches with checkpoints using the executing-plans skill

Which approach?

If Subagent-Driven: Use the subagent-driven-development skill. If Batch Execution: Use the executing-plans skill.