writing-plans

Generates detailed bite-sized implementation plans from specs before writing code.

Updated Jul 9, 2026
One-click install
npx skills add https://github.com/ByronWilliamsCPA/plugin --skill writing-plans-byronwilliamscpa
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/ByronWilliamsCPA/plugin/tree/main/plugins/wff-code/skills/writing-plans
Command: npx skills add https://github.com/ByronWilliamsCPA/plugin --skill writing-plans-byronwilliamscpa

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Engineers often jump from a spec straight into code, producing inconsistent implementations, missed requirements, and rework. This Skill turns a spec or requirements document into a complete, task-by-task implementation plan that an engineer with zero codebase context can follow. ## Core Features & Use Cases - Codebase Discovery: Runs a read-only exploration pass to verify referenced files exist on the base branch, confirm claimed patterns, and validate spec-provided fixtures before planning. - Bite-Sized Task Decomposition: Breaks work into 2-5 minute TDD steps (failing test, run, implement, verify, commit) with exact file paths, complete code, and expected command output. - Self-Review Checklist: Audits the finished plan for spec coverage at clause level, placeholder content, type consistency, and cross-requirement conflicts. - Use Case: Given a feature spec for a new API endpoint, produce a dated plan document in docs/superpowers/plans/ with ordered tasks, exact test code, and commit steps ready for subagent-driven or inline execution. ## Quick Start Ask the AI to use the writing-plans skill to create an implementation plan from your spec file before touching any 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 from a spec before coding?▼

Run the writing-plans skill with your spec or requirements document. It performs a codebase discovery pass, maps the file structure, and decomposes the work into bite-sized TDD tasks with exact file paths, complete code, and commit steps.

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 verifiable.

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. Larger steps hide errors and make review harder.

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; if one subsystem does not depend on another's output, it deserves a separate plan.

Why verify spec claims before writing plan tasks?▼

Specs describe repository state at authoring time, which may be stale or wrong. Verifying file existence on the base branch, claimed patterns, and fixture validity prevents building tasks on broken assumptions that multiply rework across every dependent task.