NVIDIA/SkillEvaluator is a framework for checking and evaluating AI-agent skills, which are instruction folders that extend an agent's behavior. Skill authors and agent developers use it to validate quality and security, detect overlap, generate evaluation data, and measure skills through live agent tests. The catalogue entries are skills for running these evaluation workflows.
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 NVIDIA/SkillEvaluator --skill create-custom-gradergit clone --depth 1 https://github.com/NVIDIA/SkillEvaluatorWrote 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/nvidia/skillevaluator/create-custom-grader)<a href="https://agentmods.dev/skills/nvidia/skillevaluator/create-custom-grader"><img src="https://agentmods.dev/badge/skills/nvidia/skillevaluator/create-custom-grader/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/nvidia/skillevaluator/create-custom-grader"><img src="https://agentmods.dev/badge/skills/nvidia/skillevaluator/create-custom-grader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector 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 | $0.00035 | $0.01960 |
| Opus 5.5 | $0.00014 | $0.00784 |
| Sonnet 5.5 | $0.00007 | $0.00392 |
| Haiku 4.5 | $0.00003 | $0.00196 |
Grade A, and why
create-custom-grader 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Custom Grader
Convert team-owned benchmark definitions into runnable SkillEvaluator custom graders and, when needed, native Harbor tasks.
Purpose
Help an agent author valid SkillEvaluator BYOG/BYOT files from a user's benchmark instead of leaving the user with empty grader templates.
When To Use
Use this skill when the user wants to:
- bring an existing benchmark into SkillEvaluator
- turn a rubric into
evals/grader.pyorevals/grader.sh - add custom metrics beside the default evaluator metrics
- convert task files such as
task.yaml,task.json, pytest checks, or shell verifiers into BYOG or BYOT - prove a team can run its own benchmark through SkillEvaluator
Do not use this skill for ordinary evals/evals.json authoring when no custom
grading logic is needed. Use the normal dataset authoring workflow for that.
Instructions
- Read the target skill, existing
evals/, benchmark prompts, fixtures, and any verifier code. - Choose
default_plus_customwhen custom metrics should complement default evaluator scoring. - Choose
custom_onlyonly when the user wants the custom grader to own pass/fail semantics. - Write or update
evals/grader.pyorevals/grader.sh, then validate the Harbor contract.
Examples
skillevaluator init-custom-grader <skill-dir> --language python --mode default_plus_custom
skillevaluator tier3 validate <skill-dir>
Prerequisites
- The target skill directory should contain
SKILL.md. - The SkillEvaluator CLI should be available as
skillevaluator. - Full E2E evaluation may need agent credentials, sandbox access, GPU access, or service credentials depending on the benchmark.
Core Choice
Choose one path before writing files:
| User need | Evaluator shape |
|---|---|
Existing evals.json task plus extra domain checks |
Top-level BYOG: evals/grader.py or evals/grader.sh |
| Existing benchmark prompt/rubric that can run in the generated workspace | Top-level BYOG plus evals/evals.json and evals/files/ |
| Benchmark owns task layout, setup, service lifecycle, or verifier harness | Native BYOT/BYOG: evals/harbor/<case>/... |
| User wants only custom reward/pass criteria | grading.mode: custom_only |
| User wants default evaluator dimensions plus custom metrics | grading.mode: default_plus_custom |
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 First seen · 219 lines · 35 tokens per session scan A 3fa1e016b4ea
create-custom-grader is a skill published in the GitHub repository NVIDIA/SkillEvaluator (585 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 1,960 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
generate-tests
Generate EvalView test cases — either from a SKILL.md file using LLM-powered generation, or by capturing real agent interactions through a proxy.
run-eval
Run EvalView regression checks against golden baselines to detect regressions in AI agent behavior after code, prompt, or model changes.
watch
Start EvalView watch mode to automatically re-run regression checks whenever project files change.
lime-quality-workflow
A set of validation rules for the Lime project. It selects appropriate checks for changes involving the graphical interface, commands or bridges, configuration, versions, and pull-request readiness.
skill-authoring
Create, revise, or remove reusable procedural and interactive skills; use memorystore for facts and preferences.
archetype-lint
This skill should be used when the user asks to "lint an archetype", "validate an archetype", "check archetype compliance", "check archetype rules compliance", or "run archetype rules". Applies 24 normative lint rules with ERROR/WARNING/INFO severity. Supports STRICT and PERMISSIVE modes. Reports violations only — it…