writing-plans

Generates detailed TDD implementation plans with bite-sized tasks from approved specs.

Updated May 22, 2026
One-click install
npx skills add https://github.com/viniciuscs84/sdd-toolkit --skill writing-plans-viniciuscs84
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/viniciuscs84/sdd-toolkit/tree/main/skills/writing-plans
Command: npx skills add https://github.com/viniciuscs84/sdd-toolkit --skill writing-plans-viniciuscs84

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Engineers and AI agents often jump from a spec straight into code, producing inconsistent implementations with missing requirements and vague steps. This Skill turns an approved spec into a complete, self-contained implementation plan that an engineer with zero codebase context can execute task by task. ## Core Features & Use Cases - Bite-Sized Task Decomposition: Breaks work into 2-5 minute steps following TDD (failing test, minimal implementation, verification, commit) with exact file paths and complete code. - Placeholder-Free Plans: Enforces concrete content in every step, banning TODOs, vague instructions, and undefined references. - Self-Review and Execution Handoff: Runs a spec-coverage, placeholder, and type-consistency checklist, then offers subagent-driven or inline execution of the saved plan. - Use Case: After a feature spec is approved, use this Skill to produce a dated plan document in docs/superpowers/plans/ that a fresh subagent can implement task by task without additional context. ## Quick Start Ask the AI to use the writing-plans skill to create an implementation plan from your approved spec before writing any code.

Frequently Asked Questions about writing-plans

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write an implementation plan from a spec before coding?

Provide the approved spec and invoke the writing-plans skill. It maps the file structure, decomposes work into bite-sized TDD tasks with exact paths and complete code, and saves the plan to docs/superpowers/plans/ with a dated filename.

What makes a good task breakdown for AI coding agents?

Each step should be one 2-5 minute action: write the failing test, run it to confirm failure, implement minimal code, verify it passes, then commit. Every step needs exact file paths, complete code blocks, and exact commands with expected output.

When should a spec be split into multiple implementation plans?

Split when the spec covers multiple independent subsystems. Each plan should produce working, testable software on its own, so one plan per subsystem keeps tasks self-contained and independently executable.

What are common mistakes in AI-generated implementation plans?

Common failures include placeholders like TODO or 'add error handling', steps without actual code, references to undefined functions, and inconsistent naming across tasks. The skill's self-review checklist catches spec gaps, placeholders, and type inconsistencies.

How is a finished plan executed after it is written?

The skill offers two options: subagent-driven development, which dispatches a fresh subagent per task with review between tasks, or inline execution using the executing-plans skill with batched checkpoints.