by fastxyz · MCP Server · ★ 58
skill-optimizer Docker workbench and Agent Skill for running deterministic evals against agent skills. Use this repo in two ways: Install the skill/plugin into your agent so it can author and debug eval suites. Run the local CLI to execute cases and suites in Docker against OpenRouter models. Installation Installation differs by agent. The canonical skill is ; every plugin manifest points at that same file.
| Stars | 58 |
| Forks | 9 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 71.7118989859558/100 |
| Open Issues | 13 |
| Last Updated | 2026-05-28 |
| Created | 2026-03-06 |
| Platforms | cli, mcp, node |
| Est. Tokens | ~150k |
These tools work well together with skill-optimizer for enhanced workflows:
Explore other popular mcp server tools:
skill-optimizer is Benchmark, evaluate, and optimize skills to ensure reliable performance across all LLMs. It is categorized as a MCP Server with 58 GitHub stars.
skill-optimizer is primarily written in TypeScript. It covers topics such as ai, ai-agent, ai-skill.
You can find installation instructions and usage details in the skill-optimizer GitHub repository at github.com/fastxyz/skill-optimizer. The project has 58 stars and 9 forks, indicating an active community.
skill-optimizer is released under the MIT license, making it free to use and modify according to the license terms.