Skip to content
GitHubDiscord

Agent Skills

Giskard Agent Skills are drop-in workflows for coding agents (Claude Code, Cursor, and more), installable via the skills CLI. Once installed, a skill teaches your agent how to handle Giskard-specific tasks without elaborate custom prompts.

Turns your coding agent into an expert red-teamer for Giskard Checks. Describe your agent and the failure modes you worry about, and the skill produces a complete, runnable giskard.checks test suite with adversarial scenarios and layered checks.

Terminal window
npx skills add Giskard-AI/giskard-skills --skill scenario-generator

It activates on prompts like “create test scenarios for my bot”, “red-team my RAG system”, or “generate checks for prompt injection”. For example:

Sample prompt
My customer support bot available on @support_bot.py must never leak customer PII or discuss competitors. Generate a red-team suite.

Source on GitHub ↗

Turns your coding agent into an expert RAG evaluation engineer for Giskard Checks. Describe a Q&A bot grounded in documents and the skill produces a quality-focused giskard.checks evaluation suite covering groundedness, answer relevance, retrieval quality, hallucination, citation accuracy, and out-of-scope handling.

Terminal window
npx skills add Giskard-AI/giskard-skills --skill rag-evaluator

It activates on prompts like “evaluate my RAG”, “test my retrieval”, “check groundedness”, or “test if my agent hallucinates”. For example:

Sample prompt
My knowledge-base assistant in @assistant.py answers questions from documents under ./docs. Build a RAG eval suite that checks groundedness and retrieval quality.

This skill is quality-focused. For adversarial or red-teaming evaluation, use Scenario Generator instead. The two are complementary and most RAG projects benefit from both.

Source on GitHub ↗

Exports Giskard Hub scan results into Collibra AI Governance ↗. The skill finds the scan in Giskard Hub, 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. It requires a Collibra instance with AI Governance.

Terminal window
npx skills add Giskard-AI/giskard-skills --skill giskard-to-collibra

It activates on prompts like “export my scan to Collibra”, “push results to Collibra”, or “send the latest scan of this project to Collibra”. For example:

Sample prompt
Retrieve the latest scan of the Zephyr project and send it to Collibra.

Source on GitHub ↗

The repository also works as a Claude Code plugin ↗. Clone it and start Claude Code with the --plugin-dir flag:

Terminal window
git clone https://github.com/Giskard-AI/giskard-skills
claude --plugin-dir ./giskard-skills

Once Claude Code is running, use the /giskard-skills command to list the available skills.