eval-dataset

eval-dataset is a skill for Claude Code from opendatahub-io/agent-eval-harness. It costs 145 tokens per session (4,205 once invoked), scanned A, original, Apache-2.0.

A tool for creating test cases from an eval.yaml file, which defines how an AI agent should be evaluated. Cases can come from skill analysis, generated prompts, or MLflow production traces, a record of real system runs.

In plain words
What is it for?
Create a starter evaluation dataset, expand an existing one, learn from an earlier evaluation run, or produce Harbor task packages.
Why use it?
It provides test data for evaluating an agent and can add cases where an existing dataset has gaps.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool; mentions AGENTS.md.

Part of the agent-eval-harness plugin — 10 skills shipped together

Good fit Create a starter evaluation dataset, expand an existing one, learn from an earlier evaluation run, or produce Harbor task packages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/opendatahub-io/agent-eval-harness/eval-dataset
Install

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.

Any agent
npx skills add opendatahub-io/agent-eval-harness --skill eval-dataset
Clone the repo
git clone --depth 1 https://github.com/opendatahub-io/agent-eval-harness

Made for: Claude Code.

Or install agent-eval-harness, the plugin that ships this one along with the rest of its 10 skills.

Wrote 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.

agentmods badge for eval-dataset

README.md
[![agentmods](https://agentmods.dev/badge/skills/opendatahub-io/agent-eval-harness/eval-dataset/github.svg)](https://agentmods.dev/skills/opendatahub-io/agent-eval-harness/eval-dataset)
Your own site
<a href="https://agentmods.dev/skills/opendatahub-io/agent-eval-harness/eval-dataset"><img src="https://agentmods.dev/badge/skills/opendatahub-io/agent-eval-harness/eval-dataset/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.

agentmods 80×15 button for eval-dataset

Your own site · 80×15
<a href="https://agentmods.dev/skills/opendatahub-io/agent-eval-harness/eval-dataset"><img src="https://agentmods.dev/badge/skills/opendatahub-io/agent-eval-harness/eval-dataset.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,205 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 255
    Data is uploaded to cloud storage (S3 / GCS / Azure Blob). This may be a legitimate backup or exfiltration to an external bucket. Manual review is recommended.
    Fix: Verify the destination bucket is trusted and owned by you. Never upload credentials, secrets, or workspace contents to external or unverified cloud storage.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00145 $0.04205
Opus 5 $0.00072 $0.02103
Sonnet 5 $0.00029 $0.00841
Haiku 4.5 $0.00015 $0.00421

Measured 10d ago against content hash 946dd98363a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

eval-dataset 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 10d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/export_s3.py, scripts/generate_synthetic.py, scripts/harbor.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/eval-dataset/SKILL.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You generate evaluation test cases for an eval.yaml. Case provenance comes from generation.strategy (see Step 1.5): the agent authors cases from the skill analysis (skill, the default), a script synthesizes them from generation prompts (synthetic), or they are extracted from MLflow production traces (from-traces). In every case the goal is giving /eval-run something meaningful to test against, matching the dataset schema.

Step 0: Parse Arguments

Argument Required Default Description
--config <path> no auto-discover Path to eval config
--count <N> no 5 Number of cases to generate
--run-id <id> no Prior eval run to learn from when augmenting existing cases
--harbor no Also generate Harbor task packages (Step 8)
--image <image> with --harbor Container image for Harbor task packages

Provenance is in the config, not a flag. generation.strategy selects where cases come from: skill (default — agent authors from skill analysis), synthetic (LLM generates from generation.seeds), or from-traces (extracted from MLflow production traces). There is no --strategy flag: whether to create a fresh set or augment an existing one is derived from the current dataset state (Step 3), and --run-id informs the augment case.

--count applies to the skill and from-traces paths. synthetic is fully declarative — case counts come from each seed's count in generation.seeds, so --count is ignored there; resize a synthetic dataset by editing seed counts in eval.yaml.

Config Discovery

If --config was explicitly provided, use that path directly. Otherwise, auto-discover:

python3 ${CLAUDE_SKILL_DIR}/../../scripts/discover.py
  • 1 config found: auto-select it as <config>
  • Multiple configs found: present the list and ask the user which eval's dataset to populate
  • No configs found: suggest running /eval-analyze first

Read the full file on GitHub · 269 lines

Files

What ships with it

7 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.

Changes

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.

  1. 10d ago First seen · 269 lines · 145 tokens per session scan A 946dd98363a6

Subscribe to this mod's changes

eval-dataset is a skill published in the GitHub repository opendatahub-io/agent-eval-harness (41 stars, last pushed 7d ago), licensed Apache-2.0. It adds 145 tokens to every session and 4,205 once invoked, about $0.0007 per session on Opus 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 2026-08-30.

Related

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.

davila7/claude-code-templates · 43 tokens

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".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

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.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens