writing-plans

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

Updated Dec 23, 2025
One-click install
npx skills add https://github.com/macintorsten/aurapod --skill writing-plans-macintorsten
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/macintorsten/aurapod/tree/main/.github/skills/writing-plans
Command: npx skills add https://github.com/macintorsten/aurapod --skill writing-plans-macintorsten

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Engineers often start coding multi-step features without a clear roadmap, leading to missed requirements, poor test coverage, and inconsistent execution. This Skill turns a spec or requirements document into a comprehensive, step-by-step implementation plan that any developer can follow without prior codebase context. ## Core Features & Use Cases - Bite-Sized Task Breakdown: Splits work into 2-5 minute steps following TDD: write failing test, verify failure, implement, verify pass, commit. - Standardized Plan Format: Produces plans with exact file paths, complete code snippets, exact commands with expected output, and a required header, saved to docs/plans/YYYY-MM-DD-<feature-name>.md. - Execution Handoff: Offers a choice between subagent-driven execution in the current session or parallel-session execution with an executing-plans skill. - Use Case: Given a feature spec for a new API endpoint, generate a plan where each task lists the files to create or modify, the failing test to write first, the minimal implementation, and the commit command. ## Quick Start Ask the AI to use the writing-plans skill to create an implementation plan for your 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?▼

Provide your spec or requirements and invoke the writing-plans skill. It produces a Markdown plan with a goal, architecture summary, tech stack, and bite-sized TDD tasks, saved to docs/plans/ with a dated filename.

What is a good task granularity for implementation plans?▼

Each step should be one action taking 2-5 minutes: write the failing test, run it to confirm failure, write the minimal implementation, run tests to confirm passing, then commit. This keeps progress verifiable and reversible.

How does test-driven development fit into implementation planning?▼

Every task in the plan starts with writing a failing test and running it to verify the failure before implementing code. The plan includes exact test commands and expected output so the engineer can confirm each stage.

Can I execute the plan with subagents after writing it?▼

Yes. After saving the plan, you choose between subagent-driven execution in the current session, where a fresh subagent handles each task with code review, or a parallel session using the executing-plans skill with batch checkpoints.

When should I not use a detailed implementation plan?▼

Skip detailed planning for trivial single-step changes, quick experiments, or exploratory spikes where requirements are unclear. The plan format is designed for multi-step tasks with a defined spec, not throwaway code.