GSD Claw
Spec-driven development with built-in verification for substantial projects. Use when user wants to plan a project, scope a feature, build something with structure, or says "GSD mode", "let's plan", "scope out", "spec-driven". Workflow is Discuss → Plan → Execute → Verify. Based on glittercowboy's GSD system (MIT license). NOT for quick questions or simple tasks.
Why use this skill?
Master your project workflow with GSD Claw, a spec-driven development agent that uses the GSD methodology to plan, execute, and verify your complex coding tasks.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/rubenaquispe/gsd-clawWhat This Skill Does
GSD Claw is a rigorous, spec-driven development framework designed to transform ambiguous project ideas into high-quality, verified, and functional code. Based on the proven methodology by Lex Christopherson, this skill mandates a strict four-phase workflow—Discuss, Plan, Execute, and Verify—to eliminate context rot and minimize developer "theater." By forcing the creation of executable specifications rather than vague documents, GSD Claw ensures that every line of code written has a clear purpose, defined constraints, and measurable success criteria.
Installation
To integrate GSD Claw into your environment, run the following command in your terminal:
clawhub install openclaw/skills/skills/rubenaquispe/gsd-claw
Ensure you have the latest version of OpenClaw installed to maintain compatibility with the sub-agent orchestration required for the research phases.
Use Cases
This tool is specifically architected for substantial, multi-faceted projects. It is ideal for:
- Architectural Scoping: Defining the structure of a new repository or feature set before writing code.
- Complex Feature Implementation: Breaking down features that involve multiple API endpoints, front-end states, and complex data flows.
- Refactoring & Migration: Planning the systematic replacement or upgrade of legacy modules while maintaining verification integrity.
- GSD Mode: When you need a focused, disciplined "Get Sh*t Done" session to overcome analysis paralysis.
Example Prompts
- "GSD mode: I want to build a real-time collaborative dashboard using Supabase and React; let's start by scoping the data model."
- "Let's plan the migration of our authentication service to Auth0. I need to define the error handling and session management specs first."
- "I have a rough idea for a file-processing CLI tool. Please scope out the project and help me define the initial verification criteria."
Tips & Limitations
- Focus on Clarity: The quality of the output is directly proportional to the clarity of the discussion phase. Do not rush to coding.
- Respect the Workflow: Skipping the verification phase leads to technical debt. Always ensure your
<verify>block is executable. - Context Limits: Keep individual task plans constrained to 2-3 items. If a plan feels too large, split it into smaller, manageable sub-tasks.
- Limitations: This is not a magic wand for simple bugs or trivial requests; it is a heavy-duty tool for project-level development. Do not use this for quick questions or simple script modifications.
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-rubenaquispe-gsd-claw": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution
Related Skills
sandwrap
Run untrusted skills safely with soft-sandbox protection. Wraps skills in multi-layer prompt-based defense (~85% attack prevention). Use when: (1) Running third-party skills from unknown sources, (2) Processing untrusted content that might contain prompt injection, (3) Analyzing suspicious files or URLs safely, (4) Testing new skills before trusting them. Supports manual mode ('run X in sandwrap') and auto-wrap for risky skills.
skill-auditor
Security scanner that catches malicious skills before they steal your data. Detects credential theft, prompt injection, and hidden backdoors. Works immediately with zero setup. Optional AST dataflow analysis traces how your data moves through code.
frankenstein
Combine the best parts of multiple skills into one. Searches ClawHub, GitHub, skills.sh, skillsmp.com and other AI skill repos. Analyzes each safely, compares features, and builds a combined 'Frankenstein' skill with the best of each. Uses skill-auditor for security scanning and sandwrap for safe analysis. Use when: (1) Multiple skills exist for same purpose, (2) Want best-of-breed combination, (3) Building a comprehensive skill from fragments.
token-saver
Reduce OpenClaw AI costs with model-aware optimization. Features dynamic compaction presets based on your model's context window, intelligent file compression, and robust model detection with fallback. Supports Claude, GPT-4, Gemini, DeepSeek, and more.