writing-plans

PedroGiudice's avatarfrom PedroGiudice

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

⭐1stars🔀1forks📁View on GitHub🕐Updated Dec 16, 2025

When & Why to Use This Skill

The Writing Plans skill is a specialized developer tool designed to bridge the gap between high-level design and technical execution. It generates exhaustive, step-by-step implementation roadmaps that allow engineers—or AI subagents—to build complex features with zero prior codebase context. By enforcing Test-Driven Development (TDD), exact file pathing, and bite-sized task granularity, it ensures high-quality code output and minimizes architectural drift during the development lifecycle.

Use Cases

  • Technical Task Breakdown: Transforming a completed feature design into a sequence of actionable, 5-minute coding tasks to streamline the development workflow.
  • Zero-Context Engineering: Providing external contributors or new team members with precise instructions, including exact code snippets and terminal commands, to implement features without requiring deep domain expertise.
  • AI Agent Orchestration: Creating structured, machine-readable plans that allow AI subagents to execute code changes autonomously while maintaining rigorous testing and documentation standards.
  • Standardizing TDD Practices: Enforcing a 'test-first' methodology across a project by generating plans that mandate failing tests before any functional code is written.
namewriting-plans
descriptionUse 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:

# [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

### 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"

## 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

**MANDATORY: Subagent-Driven Development**

After saving the plan, execution MUST be via subagent-driven development (same session).

**Announce:** "Plan saved. Starting subagent-driven execution."

**Execution Protocol:**
- **REQUIRED SUB-SKILL:** Use superpowers:subagent-driven-development
- Stay in this session
- Fresh subagent per task
- Code review between tasks
- Fast iteration with user visibility

**DO NOT offer parallel session option.** This project mandates subagent-driven execution for all plans.