writing-plans

Generates detailed multi-step implementation plans with TDD tasks from feature specifications.

3|1|Updated May 29, 2026
One-click install
npx skills add https://github.com/mambo-wang/CodingHub --skill writing-plans-mambo-wang
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/mambo-wang/CodingHub/tree/main/.qoder/skills/writing-plans
Command: npx skills add https://github.com/mambo-wang/CodingHub --skill writing-plans-mambo-wang

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a feature specification into working code often fails because engineers lack context, skip tests, or receive vague instructions. This Skill converts a spec into a complete, step-by-step implementation plan that an engineer with zero codebase context can execute without getting stuck. ## Core Features & Use Cases - Granular Task Breakdown: Splits work into 2-5 minute steps following TDD (write failing test, verify failure, implement, verify pass, commit), each with exact file paths, code blocks, commands, and expected output. - Placeholder-Free Enforcement: Forbids vague instructions like "add error handling" or "TODO"—every step must contain the actual code and commands an engineer needs. - Self-Review Checklist: Verifies spec coverage, scans for placeholder red flags, and checks type/name consistency across tasks before handoff. - Use Case: After brainstorming a new feature spec, use this Skill to produce a plan document saved to docs/superpowers/plans/, then execute it via subagent-driven development or inline execution with checkpoints. ## Quick Start Use the writing-plans skill to turn my feature specification into a step-by-step TDD implementation plan saved under docs/superpowers/plans.

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 before coding a feature?▼

Start from a feature specification, define the file structure and responsibilities first, then break work into small TDD tasks. Each task lists exact files to create or modify, a failing test, the minimal implementation, verification commands, and a commit step.

What is a good task granularity for AI coding agents?▼

Each step should be a single 2-5 minute action: write a failing test, run it to confirm failure, implement minimal code, run it to confirm pass, then commit. Fine-grained steps keep agents verifiable and prevent large unreviewable changes.

How do I make sure a plan covers the entire specification?▼

After writing the plan, re-read the spec section by section and map each requirement to a task. Also scan for placeholders like TODO or vague steps, and check that type and method names stay consistent across tasks.

When should a spec be split into multiple implementation plans?▼

Split when the spec spans multiple independent subsystems. Each plan should independently produce working, testable software, ideally separated during the brainstorming phase into sub-project specs.

What are the limitations of plan-driven development?▼

Plans assume a stable specification; major requirement changes mid-execution require plan revisions. They also depend on accurate upfront file-structure decisions, so poorly understood codebases may need exploratory work first.