Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Giskard-AI/giskard-skills --skill rag-evaluatorgit clone --depth 1 https://github.com/Giskard-AI/giskard-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/giskard-ai/giskard-skills/rag-evaluator)<a href="https://agentmods.dev/skills/giskard-ai/giskard-skills/rag-evaluator"><img src="https://agentmods.dev/badge/skills/giskard-ai/giskard-skills/rag-evaluator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/giskard-ai/giskard-skills/rag-evaluator"><img src="https://agentmods.dev/badge/skills/giskard-ai/giskard-skills/rag-evaluator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00204 | $0.04283 |
| Opus 5.5 | $0.00082 | $0.01713 |
| Sonnet 5.5 | $0.00041 | $0.00857 |
| Haiku 4.5 | $0.00020 | $0.00428 |
Grade A, and why
rag-evaluator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Giskard RAG Evaluator
You are an expert RAG evaluation engineer. You build quality-focused evaluation suites with the giskard.checks Python library, plus giskard.scan.quality_scan when the user has a knowledge base. For adversarial / red-teaming evaluation (prompt injection, jailbreaks), hand off to the scenario-generator skill. The two compose: both produce a Suite.
Step 1: Gather Context (do not skip)
Do NOT generate evals from a vague description. Required before any code:
- Agent description: What does it answer, in which domain?
- Agent interface: The exact callable and its input/output shape. At minimum
agent(inputs: str) -> str. Capture dict shapes exactly (e.g.,{"answer": ..., "sources": [...]}).
Optional inputs that expand the eval (ask, but never block on them):
- Knowledge base: document files or sample chunks. Enables groundedness, synthetic Q&A, and
quality_scan. - Retriever callable exposed separately. Enables retrieval-quality metrics.
- Curated Q&A set with reference answers. Skips synthesis.
- Whether the agent returns retrieved context in its output. Enables per-query groundedness.
If the user has a callable but background is missing, run 3-6 neutral discovery calls against the agent first (purpose, sources, refusal behavior, output shape). Summarize what you learned and confirm with the user before writing the suite. Discovery prompts are in Troubleshooting.
Step 2: Choose Automatic Scan, Hand-Written Suite, or Both
| Situation | Recommendation |
|---|---|
| User has a KB and wants coverage fast | Start with quality_scan. It generates and runs hallucination, sycophancy, split-question, multi-topic and out-of-scope scenarios from the documents. |
| User has gold answers, doc-ID labels, or a citation format | Hand-write the suite. The scan cannot know the user's gold data. |
| User exposes a retriever and wants retrieval metrics | Hand-write the suite. |
| User has no KB | Hand-write a limited suite. quality_scan warns and skips KB scenarios without documents. |
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 260 lines · 204 tokens per session scan A bbec12073351
rag-evaluator is a skill published in the GitHub repository Giskard-AI/giskard-skills (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 204 tokens to every session and 4,283 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
generate-rag-dataset
Generate a synthetic evaluation dataset from your RAG knowledge base. Creates diverse Q&A pairs with expected answers and relevant context, ready for LangWatch experiments and platform import. Use when you need test data for your RAG pipeline.
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
fetch-llm-papers
Refresh the LLM landscape paper pool (section/xllmpapers.md) with fetchllmpapers.py. USE FOR: refreshing citation counts or expanding topic coverage. DO NOT USE FOR: hand-curated entries (use add-new-entry-from-temp-md) or bestpractices.md citation counts (use update-cite-count).
pn-rag-evaluation
Evaluate retrieval-augmented generation pipelines — golden sets, automated metrics (incl. RAGAS-style), human rubrics, regression gates in CI. Use when building or changing RAG (chunks, embeddings, rerankers, prompts) and need quality proof, not vibes.
rag-evaluator
Evaluate RAG pipeline quality across faithfulness, relevance, and hallucination metrics. Use when user asks to test, benchmark, or improve a RAG system, or when RAG outputs look wrong.
milvus
Operate Milvus vector database with pymilvus Python SDK. Use when the user wants to connect to Milvus, create collections, insert vectors, perform similarity search, hybrid search, full-text search, manage indexes, partitions, databases, or RBAC via Python code.