6 boosters for "evals" — open source, verified from GitHub, ready to install
skill-creator enables users to build, refine, and evaluate AI skills through an iterative workflow with testing and performance benchmarking. Developers and AI engineers benefit from streamlined skill development and optimization.
"name": "@mastra/mcp-docs-server", "version": "1.1.25-alpha.4", "description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
This skill is for running evaluations against models on the Hugging Face Hub on local hardware. It does not cover: If the user wants to run the same eval remotely on Hugging Face Jobs, hand off to the skill and pass it one of the local scripts in this skill.
Build reusable skill packages, not long prompts. Mode rules: Operating Modes, QA Ladder, Resource Boundary Spec, Method. 1. Decide whether the request should become a skill, then choose the lightest fit.
is an eval workbench for agent skills. It runs a model in an isolated Docker directory, provides skills/references as normal workspace files, captures an agent trace, and grades deterministic local outcomes. Use this skill as the source of truth for authoring eval suites in this repo. Detailed sche
"description": "Prefect workflow orchestration - read-only MCP server for diagnostics, CLI skill for mutations", "name": "Prefect Technologies", "email": "help@prefect.io",
