skill-eval-harness is an open-source CLI tool for evaluating agent skills using benchmarks, paired variants, and holdout splits. Below are 9 llm eval & observability apps with similar functionality to skill-eval-harness, matched by what each product actually does — not ranked or scored. Explore each to find the closest fit for your use case.
skillfed is an open-source CLI tool that enables developers to discover and install vetted agent skills for Claude Code environments. It provides a no-clone installer that integrates with Claude Code and supports the Model Context Protocol (MCP), making it easy to add new skills via the command line. Designed for AI agent developers seeking streamlined skill management.
agent-skill-eval is an open-source CLI framework for evaluating the skills of code-generating agents across models like OpenCode, Claude Code, and Codex. It enables researchers and developers to benchmark agent performance using standardized tests.
skill-auditor is an open-source command-line tool that scans AI Agent skills for security issues before installation. It acts as an install gate, helping developers and maintainers ensure that only safe and validated skills are added to their AI agents. Ideal for those building or managing AI agent frameworks.
Evaluate agent skills via static analysis, trigger testing, and trace analysis. Run `sklab` after installing to scan your skills.
skillstat is an open-source command-line tool for diagnosing, auditing, and optimizing the skill usage of AI agents. It provides analytics and reports to help developers understand and improve agent performance across various tools.
Install AI coding CLI skills to Claude Code and Codex
skillscan-trace is an open-source behavioral execution engine designed for MCP-based AI agent skills. It provides tools for analyzing, executing, and securing agent behaviors, supporting developers working with autonomous agent frameworks.
touchstone-eval is an open-source CLI tool for benchmarking and comparing AI model outcomes across swappable agent harnesses on custom tasks. It is designed for AI researchers and developers seeking to evaluate and compare model performance.
skill-guard is an open-source CLI tool designed for AI developers to validate, secure, detect conflicts, and test agent skills. It provides a quality gate for agent skills, ensuring robust and secure deployment throughout their lifecycle. The tool is suitable for teams building or maintaining AI agents and skills.
