Eval Skills is a collection of instructions for coding agents that helps teams create evaluations for specific AI products, rather than tests of general-purpose foundation models. AI developers and evaluation teams use it to audit pipelines, analyze traces, generate test data, write code-based checks, and assess language-model judges. The catalogue includes nine skills and one plugin from this collection.
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 ai-evals-course/evals-skills --skill eval-auditgit clone --depth 1 https://github.com/ai-evals-course/evals-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/ai-evals-course/evals-skills/eval-audit)<a href="https://agentmods.dev/skills/ai-evals-course/evals-skills/eval-audit"><img src="https://agentmods.dev/badge/skills/ai-evals-course/evals-skills/eval-audit/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/ai-evals-course/evals-skills/eval-audit"><img src="https://agentmods.dev/badge/skills/ai-evals-course/evals-skills/eval-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00086 | $0.02058 |
| Opus 5.5 | $0.00034 | $0.00823 |
| Sonnet 5.5 | $0.00017 | $0.00412 |
| Haiku 4.5 | $0.00009 | $0.00206 |
Grade A, and why
eval-audit 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.
This is a copy
97% identical to eval-audit — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval Audit
Inspect an LLM eval pipeline and produce a prioritized list of problems with concrete next steps.
Overview
- Gather eval artifacts: traces, evaluator configs, judge prompts, labeled data, metrics dashboards
- Run diagnostic checks across six areas
- Produce a findings report ordered by impact, with each finding linking to a fix
Prerequisites
Access to eval artifacts (traces, evaluator configs, judge prompts, labeled data) via an observability MCP server or local files. If none exist, skip to "No Eval Infrastructure."
Connecting to Eval Infrastructure
Check whether the user has an observability MCP server connected (Phoenix, Braintrust, LangSmith, Truesight or similar). If available, use it to pull traces, evaluator definitions, and experiment results. If not, ask for local files: CSVs, JSON trace exports, notebooks, or evaluation scripts.
Diagnostic Checks
Work through each area below. Inspect available artifacts, determine whether the problem exists, and record a finding if it does.
Prioritize findings by impact on the user's product. Present the most impactful findings first.
1. Error Analysis
Check: Has the user done systematic error analysis on real or synthetic traces?
Look for: labeled trace datasets, failure category definitions, notes from trace review. If evaluators exist but no documented failure categories, error analysis was likely skipped.
Finding if missing: Evaluators built without error analysis measure generic qualities ("helpfulness", "coherence") instead of actual failure modes. Start with error-discovery, or generate-synthetic-data first if no traces exist.
See: Your AI Product Needs Evals, LLM Evals FAQ
Check: Were failure categories brainstormed or observed?
Generic labels borrowed from research ("hallucination score", "toxicity", "coherence") suggest brainstorming. Application-grounded categories ("missing query constraints", "wrong client tone", "fabricated property features") suggest observation.
What ships with it
1 file 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 Changed 9f4b23dfe06f
- 1mo ago First seen · 184 lines · 86 tokens per session scan A c11338900d88
eval-audit is a skill published in the GitHub repository ai-evals-course/evals-skills (1,561 stars, last pushed yesterday), licensed Apache-2.0. It adds 86 tokens to every session and 2,058 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to eval-audit, differing in 12 lines, and is treated as a copy.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.