writing-plans

Generates detailed implementation plans with bite-sized TDD tasks from feature specifications.

Updated Mar 17, 2026
One-click install
npx skills add https://github.com/AveryRen/WarpTalk-TestPayment --skill writing-plans-averyren
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/AveryRen/WarpTalk-TestPayment/tree/main/agent/.agents/skills/writing-plans
Command: npx skills add https://github.com/AveryRen/WarpTalk-TestPayment --skill writing-plans-averyren

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Engineers often start coding multi-step features without a clear roadmap, leading to missed requirements, poor task decomposition, and inconsistent execution. This Skill turns a spec or requirements document into a complete, step-by-step implementation plan that any engineer can follow without prior codebase context. ## Core Features & Use Cases - Structured Plan Generation: Produces plans with exact file paths, complete code snippets, exact test commands, and expected outputs for every step. - Bite-Sized TDD Tasks: Breaks work into 2-5 minute steps following the write-failing-test, implement, verify, commit cycle with checkbox tracking. - Plan Review Loop: Dispatches a reviewer subagent using a dedicated prompt template to verify completeness and spec alignment before execution. - Use Case: After brainstorming a new payment feature spec, use this Skill to produce a dated plan document in docs/superpowers/plans/ that an engineer or subagent can execute task by task. ## Quick Start Use the writing-plans skill to create an implementation plan from my feature 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 before coding a feature?

Start from a spec or requirements document, map out which files will be created or modified, then decompose the work into bite-sized tasks. Each task lists exact file paths, a failing test, minimal implementation, verification commands, and a commit step.

What is the best task granularity for AI coding agents?

Each step should be a single action taking 2-5 minutes, such as writing one failing test, running it, implementing minimal code, or committing. Fine-grained steps keep agents on track and make progress easy to verify and review.

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 scope focused and execution reliable.

How do I review an implementation plan before executing it?

Dispatch a plan-document-reviewer subagent with the plan path and spec path, checking completeness, spec alignment, task decomposition, and buildability. Fix flagged issues and re-review, surfacing to a human if the loop exceeds three iterations.

Where are implementation plan documents saved?

Plans are saved to docs/superpowers/plans/ with filenames in the format YYYY-MM-DD-feature-name.md. User preferences for plan location override this default path.