writing-plans

Write implementation plans with bite-sized tasks, exact file paths, and complete code.

Updated Jun 5, 2026
One-click install
npx skills add https://github.com/xu1713/openhorse --skill writing-plans-xu1713
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/xu1713/openhorse/tree/main/openhorse/openhorse/skills/software-development/writing-plans
Command: npx skills add https://github.com/xu1713/openhorse --skill writing-plans-xu1713

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Vague or incomplete implementation plans cause bugs, wasted effort, and failed handoffs when developers or subagents lack context about a codebase. This Skill produces detailed implementation plans where every task is small, explicit, and verifiable, so execution becomes obvious. ## Core Features & Use Cases - Bite-Sized Task Breakdown: Splits features into 2-5 minute tasks, each with exact file paths, complete copy-pasteable code, and verification commands. - TDD-Structured Tasks: Every coding task follows the full test-driven development cycle: failing test, minimal implementation, passing verification, and commit. - Execution Handoff: Saved plans integrate with subagent-driven-development for task-by-task execution with spec compliance and code quality reviews. - Use Case: Before building a multi-step authentication feature, generate a plan that decomposes it into tasks like creating the User model, adding password hashing, and writing tests, each with exact commands and expected output. ## Quick Start Ask the agent to write an implementation plan for your feature, breaking it into small TDD tasks with exact file paths and complete 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 for a new feature?

Start by understanding requirements and exploring the codebase, then design the approach and write sequential tasks. Each task should take 2-5 minutes and include exact file paths, complete code, test commands with expected output, and a commit step.

How granular should tasks be in an implementation plan?

Each task should represent 2-5 minutes of focused work, such as writing one failing test or implementing one minimal function. Avoid broad tasks like building an entire authentication system in a single step.

Should I write a plan even for simple features?

Yes. Assumptions cause bugs even in simple features, and a written plan guides future you or any subagent executing the work. The plan documents context that would otherwise be lost.

What should each task in an implementation plan include?

Each task needs an objective, exact file paths to create or modify, a failing test, the minimal implementation code, exact run commands with expected output, and a git commit step following the TDD cycle.

When should I not skip writing an implementation plan?

Never skip it before multi-step features, complex requirement breakdowns, or subagent delegation. Plans are also valuable when working alone, since documentation prevents context loss between sessions.