skillgrade CLI
Unit tests for skills: checks that an agent finds and uses your skill. Node 20 and Docker are needed, plus a model key
- 722 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Runs agents in containers and spends tokens on your key
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add cli/skillgradeDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Runs agents in containers and spends tokens on your key
This is third-party code. Review the repository files before installing.
What it does
skillgrade tests skills like unit tests: it makes sure an agent finds your skill and uses it correctly. Installation: `npm i -g skillgrade`. Node 20 or newer, Docker and a model key (Gemini, Anthropic or OpenAI) are needed. The checks run agents in containers. MIT license. By Minko Gechev.
Who it is for. For skill authors who want to automatically check that their skills fire and give the needed result.
Good fit when
- You need to automatically check your skills
- You need to make sure an agent finds a skill by its description
- You need skill checks in containers
Not a fit when
- You have no Docker or model key
- You cannot spend tokens on checks
Example request
Check that the agent finds and applies my skill on five typical requests and show which did not fireLimitations
The checks run agents in containers and spend tokens on your key, so access is extended. Set a spending limit with the model provider and run a small set of checks.
How to disable. Remove the skill from the agent's folder or the plugin through the plugin manager.
FAQ
What does skillgrade do?
It tests skills like unit tests: whether the agent finds and uses them.
What is needed to work?
Node 20 or newer, Docker and a model key.
How do I install it?
npm i -g skillgrade.
Discussion
No questions or reviews yet.
Related
CLI toolsA CLI to evaluate and evolve agent skills: declarative YAML cases, runs across engines and structured reports
SkillEvaluator
skillevaluator
An NVIDIA framework for evaluating agent skills: quality checks, overlap detection, synthetic checks and live evaluation by an agent. Experimental
Swift Testing Agent Skill
swift-testing-agent-skill
A Swift Testing skill from Antoine van der Lee: the new APIs, migration from XCTest, parameterized tests and flat tests. For Claude Code and other agents
A skill that lets an agent write and run Playwright scripts: page tests, forms, screenshots and link checks
QA agents, skills and an MCP server: test generation, coverage gaps, flaky tests, security scans and chaos testing
Tester
Тестер
A scenario testing system for 1C:Enterprise with a set of agent skills that let an AI agent operate the application like a regular user
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Repository stars | Main difference |
|---|---|---|---|
| skillgrade (this entry) | no | 722 | |
| SkillEvaluator | yes | 561 | skill evaluation: checks, overlaps, live evaluation by an agent |
| upskill | yes | 759 | a strong model builds a skill from traces and a weak one uses it |
README in short
The README describes a tool for testing skills like unit tests in containers with installation through npm. MIT license.