{
  "markdown": "# Giskard Skills\nAgent skills to streamline adoption and usage of Giskard products — compatible with any coding agent, including Claude Code, Cursor, and others.\n\n## Prerequisites\n\n- Node.js with `npx`\n\n## Available Skills\n\n<table>\n  <thead>\n    <tr>\n      <th width=\"20%\">Skill</th>\n      <th width=\"40%\">Install Command</th>\n      <th width=\"40%\">When to Use</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <td>scenario-generator</td>\n      <td><code>npx skills add Giskard-AI/giskard-skills --skill scenario-generator</code></td>\n      <td>Use when a user describes their AI agent and wants to create adversarial test scenarios, red-team their AI, generate evaluation suites, or build checks using the <code>giskard.checks</code> library. Triggers on phrases like \"create scenarios\", \"test my agent\", \"evaluate my chatbot\", \"red-team my AI\", or \"generate checks\".</td>\n    </tr>\n    <tr>\n      <td>rag-evaluator</td>\n      <td><code>npx skills add Giskard-AI/giskard-skills --skill rag-evaluator</code></td>\n      <td>Use when a user wants to evaluate a RAG (Retrieval-Augmented Generation) system or a Q&amp;A bot grounded in documents. Covers groundedness, answer relevance, retrieval quality, hallucination, citation accuracy, and out-of-scope refusal. Triggers on phrases like \"evaluate my RAG\", \"test my retrieval\", \"check groundedness\", \"build a RAG eval suite\", or \"test if my agent hallucinates\". Quality-focused; for adversarial / red-teaming use <code>scenario-generator</code> instead.</td>\n    </tr>\n    <tr>\n      <td>giskard-to-collibra</td>\n      <td><code>npx skills add Giskard-AI/giskard-skills --skill giskard-to-collibra</code></td>\n      <td>Use when a user wants to export, push, or sync Giskard Hub scan results into Collibra AI Governance. Creates or updates the AI Agent asset hierarchy in Collibra (re-runs are idempotent) and pushes per-probe pass/fail metrics to the Quality tab. Triggers on phrases like \"export my scan to Collibra\", \"push results to Collibra\", or \"send the latest scan of this project to Collibra\". Requires a Collibra instance with AI Governance.</td>\n    </tr>\n  </tbody>\n</table>\n\n## Install as a Claude Code Plugin\n\nThis repository can also be used as a [Claude Code plugin](https://code.claude.com/docs/en/plugins). Clone the repo and start Claude with the `--plugin-dir` flag pointing at it:\n\n```bash\nclaude --plugin-dir ./giskard-skills\n```\n\nOnce Claude Code is running, use the `/giskard-skills` command to list the available skills.\n",
  "bytes": 2495,
  "sha": "52584071d0ec517854032ddd1d4abca9f5cadee5d142f41f8eec2f8e2011c60e",
  "repo_slug": "giskard-ai/giskard-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_giskard_ai_giskard_skills_giskard_skills_ea2c0052/readme"
}