writing-plans

Writes detailed implementation plans with bite-sized TDD tasks before any code is touched.

1|Updated Dec 11, 2025
One-click install
npx skills add https://github.com/HarmAalbers/claude-requirements-framework --skill writing-plans-harmaalbers
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/HarmAalbers/claude-requirements-framework/tree/main/plugins/requirements-framework/skills/writing-plans
Command: npx skills add https://github.com/HarmAalbers/claude-requirements-framework --skill writing-plans-harmaalbers

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When a spec or requirements exist for a multi-step task, jumping straight into code leads to missed steps, vague plans, and rework. This Skill produces a comprehensive implementation plan that an engineer with zero codebase context can execute task by task. ## Core Features & Use Cases - Bite-sized TDD tasks: Breaks work into 2-5 minute steps (write failing test, verify failure, implement, verify pass, commit) with exact file paths, complete code, and expected command output. - Lazy-Dev Ladder: Applies YAGNI and minimal-code reasoning to every task, preferring standard library and platform features over new dependencies. - Execution handoff: After saving the plan to docs/plans/, offers subagent-driven execution in the current session or parallel-session execution, and auto-satisfies the plan_written requirement gate. - Use Case: Given a feature spec for a new API endpoint, generate a dated plan document listing every file to create or modify, the failing tests to write first, and the exact commit commands, then hand it off for task-by-task implementation. ## Quick Start Ask the AI to use the writing-plans skill to create an implementation plan for your feature spec before writing 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 before coding a feature?▼

Invoke the writing-plans skill with your spec or requirements. It produces a plan document with a goal, architecture summary, and bite-sized TDD tasks, each containing exact file paths, complete code snippets, test commands with expected output, and commit steps.

What is a good task granularity for implementation plans?▼

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 granularity keeps progress verifiable and mistakes cheap to revert.

Where are implementation plan documents saved?▼

Plans are saved to docs/plans/YYYY-MM-DD-<feature-name>.md or to .claude/plans/. Every plan starts with a required header stating the goal, architecture, tech stack, and a pointer to the executing-plans sub-skill.

Can the plan be executed automatically after it is written?▼

Yes. After saving, the skill offers two options: subagent-driven execution in the current session with a fresh subagent per task, or a parallel session using the executing-plans skill for batch execution with checkpoints.

When should I not write a full implementation plan?▼

Skip detailed planning for trivial single-step changes or speculative features that fail the YAGNI check. The Lazy-Dev Ladder explicitly favors not writing code or plans for work that does not need to exist yet.