writing-plans

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

Updated Jun 20, 2026
One-click install
npx skills add https://github.com/dchavez3395/Puchica-hydrogen --skill writing-plans-dchavez3395
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/dchavez3395/Puchica-hydrogen/tree/main/docs/superpowers/skills/openclaw-ports/writing-plans
Command: npx skills add https://github.com/dchavez3395/Puchica-hydrogen --skill writing-plans-dchavez3395

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a spec or requirements document into an actionable implementation plan is error-prone: engineers miss requirements, write vague tasks, or produce plans with placeholders that stall execution. This Skill converts a spec into a complete, bite-sized task plan that an engineer with zero codebase context can execute task by task. ## Core Features & Use Cases - Structured Plan Format: Enforces a mandatory plan header (goal, architecture, tech stack, global constraints) plus 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 a test-driven cycle: write the failing test, verify it fails, implement minimal code, verify it passes, commit. - No-Placeholder Enforcement & Self-Review: Bans vague steps like "add error handling" and includes a self-review checklist covering spec coverage, placeholder scans, and type consistency across tasks. - Use Case: Given a feature spec for a new checkout flow, produce a dated Markdown plan in docs/superpowers/plans/ with exact file paths, complete code snippets, test commands with expected output, and commit messages for every task. ## Quick Start Ask the agent to use the writing-plans skill to turn your spec document into a step-by-step implementation plan saved as a dated Markdown file.

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?▼

Start with a plan header covering goal, architecture, tech stack, and global constraints copied verbatim from the spec. Then decompose the work into tasks, each with exact files to create or modify, interfaces consumed and produced, and bite-sized TDD steps ending in a commit.

How to break a coding task into bite-sized steps?▼

Make each step a single 2-5 minute action: write the failing test, run it to confirm failure, write the minimal implementation, run the test to confirm it passes, then commit. Fold setup and scaffolding into the task whose deliverable needs them.

What makes an implementation plan fail during execution?▼

Plans fail when they contain placeholders like TBD or "add appropriate error handling", reference undefined types or functions, or use inconsistent names across tasks. Every step must show actual code, exact commands, and expected output.

When should a spec be split into multiple 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 reviewable and independently executable.

Where are implementation plans saved?▼

Plans are saved as dated Markdown files named YYYY-MM-DD-feature-name.md. The default location is the workspace plans directory, with project conventions like docs/superpowers/plans/ overriding the default when specified.