sup-writing-plans

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

13.4k|1.4k|Updated May 18, 2025
One-click install
npx skills add https://github.com/browseros-ai/BrowserOS --skill sup-writing-plans
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sup-writing-plans
Source: https://github.com/browseros-ai/BrowserOS/tree/main/.claude/skills/writing-plans
Command: npx skills add https://github.com/browseros-ai/BrowserOS --skill sup-writing-plans

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Turning a feature spec into code often fails because engineers lack context on the codebase, file structure, and testing conventions. This Skill converts a spec or requirements document into a complete, step-by-step implementation plan that an engineer with zero project context can execute without getting stuck.

Core Features & Use Cases

  • Bite-Sized Task Decomposition: Breaks work into 2-5 minute steps following TDD: write failing test, verify failure, implement, verify pass, commit.
  • No-Placeholder Enforcement: Requires exact file paths, complete code blocks, exact commands with expected output, and bans vague steps like "add error handling".
  • Self-Review and Handoff: Includes a spec-coverage and consistency self-review checklist, plus an execution handoff offering parallel or inline execution modes.
  • Use Case: Given a spec for a new API endpoint, produce a plan saved to .llm/plans/YYYY-MM-DD-feature.md with checkbox-tracked tasks covering file structure, tests, implementation code, and commit steps.

Quick Start

Ask the agent to use the writing-plans skill to create an implementation plan from your feature spec before writing any code.

Frequently Asked Questions about sup-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?

Provide the spec or requirements document 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 .llm/plans/ with a dated filename.

What makes a good implementation plan for AI coding agents?

A good plan assumes zero codebase context: exact file paths, complete code in every step, exact commands with expected output, and no placeholders like TODO or "add error handling". Each task should be self-contained and independently testable.

How granular should tasks be in an implementation plan?

Each step should be one action taking 2-5 minutes: write the failing test, run it to confirm failure, implement minimal code, run tests to confirm pass, then commit. This TDD rhythm keeps changes verifiable and reversible.

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 manageable and execution parallelizable.

Can the plan be executed in parallel after it is written?

Yes. After saving the plan, the skill offers two execution modes: parallel execution with a fresh worker per independent task plus review between tasks, or inline execution in the current session with checkpoints.