writing-plans

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

Updated Jul 29, 2026
One-click install
npx skills add https://github.com/MaiconGambini/opencode-harness-guide --skill writing-plans-maicongambini
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/MaiconGambini/opencode-harness-guide/tree/main/skills/writing-plans
Command: npx skills add https://github.com/MaiconGambini/opencode-harness-guide --skill writing-plans-maicongambini

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 complete, step-by-step implementation plans that an engineer with zero project context can execute. ## Core Features & Use Cases - Bite-Sized Task Decomposition: Breaks work into 2-5 minute steps following TDD (failing test, minimal implementation, verification, commit) with exact file paths and commands. - No-Placeholder Enforcement: Requires complete code in every step and bans vague instructions like "add error handling" or "TBD". - Self-Review and Handoff: Includes a spec-coverage, placeholder, and type-consistency checklist, plus a reviewer subagent prompt template and PREVC execution handoff. - Use Case: Given a feature spec for a new API endpoint, produce a dated plan document in docs/superpowers/plans/ with checkbox tasks, exact test code, and expected command output for each step. ## Quick Start Ask the agent to use the writing-plans skill to turn your spec into a step-by-step TDD 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 spec before coding?

Provide the spec or requirements and invoke the writing-plans skill before touching code. It maps the file structure, decomposes work into bite-sized TDD tasks with exact paths and code, and saves the plan to docs/superpowers/plans/.

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 exact file paths, complete code blocks, and commands with expected output.

How does the plan review process work?

The skill runs a self-review checking spec coverage, placeholder patterns, and type consistency across tasks. It also ships a reviewer prompt template for dispatching a subagent that verifies completeness, spec alignment, and buildability.

When should a spec be split into multiple plans?

Split when the spec covers multiple independent subsystems. The skill routes the split decision to spec-lead and PREVC, and each resulting plan must produce working, testable software on its own.

What are the limitations of plan-driven TDD workflows?

Plans assume a skilled engineer who can follow exact steps, so they require complete code and commands upfront, which demands effort at planning time. Execution, validation, and commits are owned by PREVC, not the plan itself.