by mgechev · Codex Skill · ★ 480
Skillgrade The easiest way to evaluate your Agent Skills. Tests that AI agents correctly discover and use your skills. See examples/ — superlint (simple) and angular-modern (TypeScript grader). Quick Start Prerequisites: Node.js 20+, Docker 1. Initialize — go to your skill directory (must have ) and scaffold: Generates with AI-powered tasks and graders. Without an API key, creates a well-commented template. 2. Edit — customize for your skill (see eval.yaml Reference). 3. Run: The agent is auto-detected from your API key: → Gemini, → Claude, → Codex. Override with . 4.
| Stars | 480 |
| Forks | 35 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 61.128/100 |
| Last Updated | 2026-05-19 |
| Created | 2026-02-26 |
| Platforms | claude-code, cli, codex, gemini, node |
| Est. Tokens | ~105k |
These tools work well together with skillgrade for enhanced workflows:
Explore other popular codex skill tools:
skillgrade is "Unit tests" for your agent skills. It is categorized as a Codex Skill with 480 GitHub stars.
skillgrade is primarily written in TypeScript. It covers topics such as agent, claude-code, codex.
You can find installation instructions and usage details in the skillgrade GitHub repository at github.com/mgechev/skillgrade. The project has 480 stars and 35 forks, indicating an active community.
skillgrade is released under the MIT license, making it free to use and modify according to the license terms.