quality-judge

AISecurityAssurance/ai-sec

Evaluate LLM benchmark outputs against quality rubrics for STPA-Sec analysis. Use when comparing model outputs, assessing component extraction quality, UCA analysis correctness, or scenario generation completeness.

0 stars

0 forks

4 views

View on GitHub Add to Favorites

Installation

Option 1: Use slash command in Claude Code

/install-skill https://github.com/AISecurityAssurance/ai-sec/tree/main/.claude/skills/quality-judge

Option 2: Clone to skills directory

# Global (all projects)

git clone https://github.com/AISecurityAssurance/ai-sec/tree/main/.claude/skills/quality-judge ~/.claude/skills/ai-sec

# Project-specific

git clone https://github.com/AISecurityAssurance/ai-sec/tree/main/.claude/skills/quality-judge .claude/skills/ai-sec

Add MCP server to .cursor/mcp.json:

{
  "mcpServers": {
    "skillz": {
      "command": "npx",
      "args": ["-y", "skillz-mcp", "https://github.com/AISecurityAssurance/ai-sec/tree/main/.claude/skills/quality-judge"]
    }
  }
}

Restart Cursor after adding the configuration.

Option 1: Use Gemini CLI command

gemini extensions install https://github.com/AISecurityAssurance/ai-sec/tree/main/.claude/skills/quality-judge

Option 2: Clone to extensions directory

git clone https://github.com/AISecurityAssurance/ai-sec/tree/main/.claude/skills/quality-judge ~/.gemini/extensions/ai-sec