writing-plans

Writes detailed implementation plans with bite-sized TDD tasks and exact file paths.

Updated Mar 24, 2026
One-click install
npx skills add https://github.com/AarushiShah/coding-agents-databricks-apps --skill writing-plans-aarushishah
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/AarushiShah/coding-agents-databricks-apps/tree/main/.claude/skills/writing-plans
Command: npx skills add https://github.com/AarushiShah/coding-agents-databricks-apps --skill writing-plans-aarushishah

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Engineers often start coding multi-step features without a clear roadmap, leading to missed requirements, inconsistent structure, and lost context. This Skill turns a spec or requirements into a comprehensive implementation plan that any engineer can execute without prior codebase knowledge. ## Core Features & Use Cases - Bite-Sized Task Breakdown: Splits work into 2-5 minute steps following TDD: write failing test, verify failure, implement, verify pass, commit. - Exact File and Command Specification: Every task lists exact file paths to create or modify, complete code snippets, and commands with expected output. - Execution Handoff: After saving the plan to docs/plans/, offers subagent-driven execution in the current session or a parallel session with an executing-plans skill. - Use Case: Given a feature spec for a new API endpoint, produce a dated plan document where each task includes the failing test, minimal implementation, pytest command, and git commit step. ## Quick Start Ask the agent 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?

Provide your spec or requirements and invoke the writing-plans skill. It produces a markdown plan with a goal, architecture summary, tech stack, and tasks broken into TDD steps: failing test, verification, minimal implementation, and commit.

How granular should tasks be in an implementation plan?

Each step should be a single 2-5 minute action, such as writing one failing test, running it to confirm failure, implementing minimal code, or committing. This granularity keeps progress verifiable and commits frequent.

Where are implementation plans saved?

Plans are saved as markdown files under docs/plans/ using the naming pattern YYYY-MM-DD-feature-name.md. Each plan starts with a header containing the goal, architecture, and tech stack.

Can the plan be executed automatically after it is written?

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

When should I not use a written implementation plan?

Skip formal plans for trivial single-file changes or exploratory spikes where requirements are unclear. The plan format assumes a defined spec and multi-step work; overhead is not justified for one-line fixes.