writing-plans

Generates detailed multi-task implementation plans from specs with TDD steps and exact file paths.

Updated Jul 15, 2026
One-click install
npx skills add https://github.com/em411/supercodex --skill writing-plans-em411
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/em411/supercodex/tree/main/skills/writing-plans
Command: npx skills add https://github.com/em411/supercodex --skill writing-plans-em411

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 vague, placeholders slip in, and engineers (or AI subagents) without codebase context get stuck. This Skill produces a complete, bite-sized implementation plan that an engineer with zero project context can execute task by task. ## Core Features & Use Cases - Structured Plan Generation: Creates plan documents with a mandatory header (goal, architecture, tech stack, global constraints) and per-task blocks listing exact files to create or modify, interfaces consumed and produced, and checkbox steps. - TDD Bite-Sized Steps: Each task is broken into 2-5 minute steps following test-driven development: write the failing test, verify it fails, implement minimal code, verify it passes, commit. - Placeholder Prevention & Self-Review: Enforces a no-placeholder policy (no TODOs or vague instructions) and runs a self-review checklist covering spec coverage, placeholder scan, and type consistency across tasks. - Use Case: After brainstorming a feature spec, use this Skill to produce a plan saved to docs/superpowers/plans/, then hand it off to subagent-driven-development or executing-plans for task-by-task implementation with review gates. ## Quick Start Ask Claude to use the writing-plans skill to turn your feature spec into a step-by-step implementation plan with tests and commits.

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?

Start with a header covering goal, architecture, tech stack, and global constraints, then decompose the work into tasks with exact file paths and interfaces. Each task contains bite-sized TDD steps: failing test, verification, minimal implementation, passing test, and commit.

What makes a good task breakdown for AI coding agents?

Each task should be the smallest unit with its own test cycle and an independently testable deliverable. Include exact file paths, complete code in every step, exact commands with expected output, and an Interfaces block so implementers seeing only one task know the signatures neighbors use.

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 reviewable and executable.

What are common mistakes in AI-generated implementation plans?

Common failures include placeholders like TODO or 'add error handling', steps describing what to do without showing code, references to undefined types, and inconsistent naming across tasks. A self-review pass checking spec coverage, placeholders, and type consistency catches these.

How is a finished plan executed after writing it?

The plan offers two execution paths: subagent-driven development, which dispatches a fresh subagent per task with review between tasks, or inline execution with batch processing and checkpoints. Both consume the checkbox-formatted plan document.