Code
Coding workflow with planning, implementation, verification, and testing for clean software development.
Why use this skill?
Optimize your coding workflow with the OpenClaw Code skill. Features structured planning, verification templates, and local preference memory for clean code.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/lion504/code-1-0-4What This Skill Does
The Code skill is a specialized development workflow agent designed for the OpenClaw platform. It acts as a structured coding companion, prioritizing clean software architecture, rigorous verification, and user-centric planning. Unlike autonomous agents that might attempt to write and run code without oversight, the Code skill functions strictly as a facilitator that guides you through a multi-step engineering lifecycle. It manages task decomposition, tracks project-specific user preferences through local memory files, and ensures that every code change is testable and verified before completion. By creating a dedicated environment in ~/code/, it maintains a clear separation between your project source code and the assistant's metadata, ensuring that your coding environment remains clean and organized.
Installation
To integrate this skill into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/lion504/code-1-0-4
Once installed, the skill will initialize the necessary directory structure on its first use, creating the ~/code/ folder to manage your preferences and planning templates. No further configuration is required to begin.
Use Cases
- Complex Feature Development: When you have a large feature request, use this skill to break it down into atomic, testable chunks to prevent monolithic, buggy pull requests.
- Long-term Project Management: If you have specific architectural preferences (e.g., using TypeScript interfaces instead of classes or preferring functional programming patterns), this skill stores those in
~/code/memory.mdto ensure consistency across multiple sessions. - Refactoring Workflows: Use the skill to plan out a refactor, ensuring that verification and test suites are defined before any code is modified, minimizing regression risk.
- Structured Debugging: Utilize the planning and verification templates to isolate bugs and track the status of fixes in a shared state file.
Example Prompts
- "I need to build a user authentication module for my React project. Please help me plan the implementation steps and set up the
planning.mdfile." - "Remember that I prefer using Tailwind CSS for all my UI components and never want to use external styling libraries like Bootstrap. Add this to my memory."
- "I've finished the draft for the login function. Let's look at the
verification.mdfile to see how we should test this before I finalize it."
Tips & Limitations
- Safety First: This skill will NEVER execute code automatically. You remain the final authority on all actions. Always review the code generated by the agent before moving to the implementation phase.
- Keep Memory Updated: Regularly review
~/code/memory.mdto ensure the assistant's preferences align with your current project standards. - Don't Skip Verification: The skill is optimized for quality; skipping the verification steps in the workflow often leads to technical debt. Always prioritize test generation.
- Limitations: The skill has no network access and cannot install packages or deploy your code to remote servers. It is strictly a planning and guidance tool. It also does not access files outside of the
~/code/directory or your specific project working directory to ensure maximum security.
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-lion504-code-1-0-4": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write
Related Skills
language-learning
AI language tutor for learning ANY language through conversation, vocab drills, grammar lessons, flashcards, and immersive practice. Use when the user wants to: learn a new language, practice vocabulary, study grammar, do flashcard drills, translate phrases, practice conversation, prepare for travel, learn slang/idioms, or improve pronunciation. Supports ALL languages including Spanish, French, German, Japanese, Chinese (Mandarin/Cantonese), Korean, Arabic, Hindi, Bengali/Bangla, Portuguese, Russian, Italian, Turkish, Vietnamese, Thai, Swahili, Hebrew, Polish, Dutch, Greek, and 100+ more.
agent-browser-core
OpenClaw skill for the agent-browser CLI (Rust-based with Node.js fallback) enabling AI-friendly web automation with snapshots, refs, and structured commands.
gemini-deep-research
Perform complex, long-running research tasks using Gemini Deep Research Agent. Use when asked to research topics requiring multi-source synthesis, competitive analysis, market research, or comprehensive technical investigations that benefit from systematic web search and analysis.
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.