writing-plans

Generates detailed multi-task implementation plans with TDD steps from a spec.

Updated Jun 9, 2026
One-click install
npx skills add https://github.com/gyc-12/Archipelago --skill writing-plans-gyc-12
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/gyc-12/Archipelago/tree/main/modules/collaboration-runtime/src-tauri/experts/skills/writing-plans
Command: npx skills add https://github.com/gyc-12/Archipelago --skill writing-plans-gyc-12

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a spec or requirements document into an actionable implementation plan is error-prone: tasks end up too vague, files are missed, and engineers without codebase context get stuck. This Skill produces a complete, bite-sized task plan that an engineer with zero project context can execute directly. ## Core Features & Use Cases - Bite-Sized Task Decomposition: Breaks work into 2-5 minute steps following a strict TDD cycle (failing test, minimal implementation, verification, commit). - No-Placeholder Enforcement: Requires exact file paths, complete code blocks, and exact commands with expected output in every step. - Self-Review and Handoff: Includes a spec-coverage and consistency self-review checklist, plus an execution handoff offering subagent-driven or inline execution. - Use Case: After brainstorming a feature spec, use this Skill to produce a dated plan document in docs/superpowers/plans/ that a fresh engineer or subagent can implement task-by-task. ## Quick Start Ask the AI to use the writing-plans skill to turn your feature spec into a step-by-step 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 from a feature spec?

Provide the spec and invoke the writing-plans skill before touching code. It maps out the file structure, decomposes work into bite-sized TDD tasks with exact file paths and 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 complete code and exact commands, never placeholders like TODO or add error handling.

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 focused and independently executable.

How is a finished plan executed after writing it?

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.

What are common mistakes in AI-generated implementation plans?

Common failures include placeholder text like TBD, vague steps without code, references to undefined functions, and inconsistent naming across tasks. The skill's self-review checklist catches spec gaps, placeholders, and type inconsistencies before handoff.