describe-design
Research a codebase and create architectural documentation describing how features or systems work. Use when the user asks to: (1) Document how a feature works, (2) Create an architecture overview, (3) Explain code structure for onboarding or knowledge transfer, (4) Research and describe a system's design. Produces markdown documents with Mermaid diagrams and stable code references suitable for humans and AI agents.
Why use this skill?
Use describe-design to research your codebase and generate professional, structured architectural documentation and diagrams automatically with OpenClaw.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/ziad-hsn/describe-designWhat This Skill Does
The describe-design skill is an advanced architectural analysis tool for the OpenClaw AI agent. It allows developers to generate comprehensive, structured documentation directly from their existing source code. By automating the extraction of system architecture, dependency graphs, and code interaction patterns, this skill bridges the gap between raw implementation and high-level documentation. It follows a rigorous four-stage workflow—Scope Definition, Initial Exploration, Deep Research, and Documentation Draft—ensuring that the generated outputs are technically accurate, maintainable, and readable for both human engineers and automated AI agents.
Installation
To integrate this skill into your environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/ziad-hsn/describe-design
Ensure that your OpenClaw environment has sufficient file read permissions for the target repository you intend to document.
Use Cases
- Onboarding: Automatically generate architectural guides for new team members to shorten the learning curve.
- Refactoring: Create baseline documentation before initiating a large-scale refactor to identify potential risks.
- Knowledge Transfer: Maintain up-to-date documentation for legacy systems where technical debt is high and documentation is sparse.
- AI Context Injection: Create structured, agent-readable markdown files that can be fed back into OpenClaw or other AI assistants to improve context-aware code generation.
Example Prompts
- "I need to document the authentication flow of our backend. Please research the
auth/directory and create an architecture overview." - "Describe the design of our data processing pipeline. Include a Mermaid diagram showing how data moves from the ingestion endpoint to our database."
- "Create a technical documentation file for the payment gateway integration. Focus on the error handling logic and external API boundaries."
Tips & Limitations
- Tips: Start with a narrow scope. If your codebase is large, document specific features rather than the entire repository at once to maintain high accuracy.
- Limitations: The skill is designed to capture architecture; it is not meant for line-by-line code explanation or debugging. It relies on the AI agent's ability to traverse code, so extremely obfuscated or undocumented codebases may require more manual guidance during the 'Deep Research' stage.
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-ziad-hsn-describe-design": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read