Agent skills to streamline adoption and usage of Giskard products — compatible with any coding agent, including Claude Code, Cursor, and others.
- Node.js with
npx
| Skill | Install Command | When to Use |
|---|---|---|
| scenario-generator | npx skills add Giskard-AI/giskard-skills --skill scenario-generator |
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 giskard.checks library. Triggers on phrases like "create scenarios", "test my agent", "evaluate my chatbot", "red-team my AI", or "generate checks". |
| rag-evaluator | npx skills add Giskard-AI/giskard-skills --skill rag-evaluator |
Use when a user wants to evaluate a RAG (Retrieval-Augmented Generation) system or a Q&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 scenario-generator instead. |
This repository can also be used as a Claude Code plugin. Clone the repo and start Claude with the --plugin-dir flag pointing at it:
claude --plugin-dir ./giskard-skillsOnce Claude Code is running, use the /giskard-skills command to list the available skills.