writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
Why use this skill?
Master your coding workflow with the OpenClaw writing-plans skill. Generate structured, TDD-compliant implementation plans for consistent, high-quality development.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/zlc000190/writing-plansWhat This Skill Does
The writing-plans skill is an essential framework for OpenClaw AI agents, designed to bridge the gap between abstract requirements and production-ready code. It enforces a rigorous, TDD-centric methodology by guiding the agent to generate highly structured, granular, and actionable implementation plans. By forcing the agent to break down features into 2-5 minute tasks—each including specific file paths, code snippets, and verification commands—it minimizes developer overhead and ensures that every change is validated against a failing test before implementation.
Installation
You can install this skill by running: clawhub install openclaw/skills/skills/zlc000190/writing-plans
Use Cases
- Complex Feature Development: When building multi-file features that require careful architecture design.
- Onboarding/Knowledge Transfer: Standardizes documentation so that an engineer or AI agent unfamiliar with the codebase can execute tasks with clear, step-by-step instructions.
- Legacy Refactoring: Safely updating older, untested code by first writing the plan and the corresponding test suite.
- Team Consistency: Enforces a strict DRY (Don't Repeat Yourself) and YAGNI (You Ain't Gonna Need It) philosophy across all development work.
Example Prompts
- "I need to implement a user authentication module with JWT. Use the writing-plans skill to draft a plan that includes token validation, database schema updates, and integration tests."
- "We have a requirements document for the API v2 migration. Please analyze this doc and create an implementation plan using the writing-plans skill, prioritizing test coverage."
- "Plan the refactoring of our data processing pipeline. Ensure the plan uses TDD, saves the output to the docs/plans folder, and breaks the tasks down into bite-sized 5-minute steps."
Tips & Limitations
- Context is Key: Always run this skill in a dedicated worktree initialized by the brainstorming skill to ensure a clean slate.
- Granularity Matters: If a step takes longer than 5 minutes to complete, you have likely made the tasks too broad; refine them into smaller logical chunks.
- Validation: The skill is most effective when paired with the
executing-plansskill. Always follow the header requirements exactly as specified to ensure the execution handoff phase functions correctly. It is not designed for one-off script generation but for lifecycle management of software features.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-zlc000190-writing-plans": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read
Related Skills
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always