writing-plans

Generates detailed multi-task implementation plans with test-driven steps from a specification.

Updated Aug 20, 2026
One-click install
npx skills add https://github.com/Pega88/agy-superpowers --skill writing-plans-pega88
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/Pega88/agy-superpowers/tree/main/.agents/plugins/superpowers/skills/writing-plans
Command: npx skills add https://github.com/Pega88/agy-superpowers --skill writing-plans-pega88

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, placeholders slip in, and engineers without codebase context get stuck. This Skill produces a complete, bite-sized task breakdown that an engineer (or subagent) with zero project context can execute directly. ## Core Features & Use Cases - Structured Plan Documents: Generates plans with a mandatory header (goal, architecture, tech stack, spec reference, global constraints) saved to docs/superpowers/plans/. - Bite-Sized TDD Tasks: Decomposes work into tasks with exact file paths, interface contracts (consumes/produces), and 2-5 minute steps following the write-failing-test, implement, verify, commit cycle. - Placeholder Prevention & Self-Review: Enforces a no-placeholder policy (no TODOs or vague steps) and runs a self-review checklist for spec coverage, placeholder scans, and type consistency. - Execution Handoff: Offers subagent-driven or inline execution paths, with a reviewer prompt template for dispatching a plan-review subagent. - Use Case: After brainstorming a feature spec, invoke this Skill to produce a dated plan file with checkbox-tracked tasks that a fresh subagent can implement one by one. ## Quick Start Ask the agent to use the writing-plans skill to create an implementation plan from your spec document 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?

Invoke the writing-plans skill with your spec or requirements document. It produces a plan saved to docs/superpowers/plans/ with a goal, architecture, tech stack, global constraints, and tasks broken into test-first steps an engineer can execute directly.

How to break a software feature into small tasks for AI agents?

Decompose the feature so each task has one clear deliverable with its own test cycle, and each step is a 2-5 minute action like writing a failing test or committing. Include exact file paths and interface signatures so agents see only their own task.

What makes an implementation plan fail during execution?

Plans fail when they contain placeholders like TODO or vague steps such as add error handling, reference undefined types, or have inconsistent naming across tasks. The skill's self-review checklist catches spec gaps, placeholders, and type mismatches before handoff.

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 reviewable.

How are completed plans executed after writing them?

After saving the plan, you choose subagent-driven development, which dispatches a fresh subagent per task with reviews between tasks, or inline execution with the executing-plans skill using batched checkpoints.