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 calculatorgit 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/calculator)<a href="https://agentmods.dev/skills/nvidia/skillevaluator/calculator"><img src="https://agentmods.dev/badge/skills/nvidia/skillevaluator/calculator.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00419 |
| Opus 5 | $0.00016 | $0.00210 |
| Sonnet 5 | $0.00006 | $0.00084 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
calculator 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 7d 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.
What it actually says
Calculator
Evaluate math expressions and perform unit conversions from the command line.
Purpose
Provide a safe, sandboxed calculator for arithmetic expressions and common
unit conversions without relying on eval() or external services.
Agent Instructions
- Read this SKILL.md to understand capabilities.
- Run
scripts/calc.pywith the user's expression or conversion. - Return the computed result to the user.
Examples
Usage
# Arithmetic expressions
python scripts/calc.py "2 + 3 * 4"
python scripts/calc.py "(100 - 25) / 3"
python scripts/calc.py "2 ** 10"
# Percentage calculations
python scripts/calc.py "15% of 200"
# Unit conversions
python scripts/calc.py "100 celsius to fahrenheit"
python scripts/calc.py "5 miles to km"
python scripts/calc.py "10 kg to lbs"
Output
A single line with the result, e.g.:
Result: 14
For conversions:
100 celsius = 212.0 fahrenheit
Limitations
- No symbolic algebra (no variables, no equations).
- Only supports basic arithmetic operators:
+,-,*,/,**,%, parentheses. - Unit conversions are limited to: celsius/fahrenheit, miles/km, kg/lbs, meters/feet.
Troubleshooting
| Problem | Fix |
|---|---|
Invalid expression |
Check for unsupported operators or variables |
Unknown conversion |
Use supported units: celsius, fahrenheit, miles, km, kg, lbs, meters, feet |
What ships with it
2 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.
- 7d ago First seen · 67 lines · 32 tokens per session scan A 0dabd9b89816
calculator is a skill published in the GitHub repository NVIDIA/SkillEvaluator (406 stars, last pushed 3d ago), licensed Apache-2.0. It adds 32 tokens to every session and 419 once invoked, about $0.0002 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.
Other skills, from other repositories
indec
Datos macro y sociales de Argentina via la API oficial Series de Tiempo del Estado (apis.datos.gob.ar/series). 4250 series del INDEC + BCRA + Min Economia + Sec Trabajo. Sin auth, sin API key. IPC nacional, EMAE, IPI, ISAC, EPH (desempleo), pobreza, comercio exterior, salarios (RIPTE, SMVM), tipo de cambio, reservas…
backtesting
Academic backtesting framework for quantitative research. 30 risk and performance ratios, 10 classes of indicators, event-driven engine with 6+ strategies, MPT optimizer, forward-looking simulation with Johnson SU + t-Copula, walk-forward CV, stress testing, fundamental analysis (Altman Z, Piotroski, DuPont). All flat…
bcra-macro
API de Estadísticas Monetarias v4.0 del BCRA con 638 series macroeconómicas (reservas, tipo de cambio, tasas, M1/M2/M3, inflación, CER, UVA).
fred-macro
API gratuita de la Reserva Federal (FRED): 840K+ series macroeconómicas (GDP, CPI, tasas, empleo, M2, VIX, treasuries).
deltasci
Two-perspective co-reasoning for AI4Science hypothesis generation. Runs a structured 4-round dialogue between a domain scientist (parameterized by a domain pack) and an ML engineer, producing a grounded, falsifiable research hypothesis that is honest about the AI's training-distribution edges. Domain-agnostic via…
aql-authoring
This skill should be used when the user asks to "write an AQL query", "optimize an AQL query", "review AQL", or "query openEHR data" — the multi-step authoring/optimization workflow for AQL (Archetype Query Language) over openEHR clinical data. For a one-off explanation of an existing query or a single AQL…