SkillEvaluator

About SkillEvaluator

SkillEvaluator SkillEvaluator is an open-source, multi-tier framework for evaluating AI agent artifacts, starting with agent skills: deterministic quality gates, semantic overlap detection, synthetic eval dataset generation, and live agent evaluation. Agent skills are folders of instructions and supporting files that extend AI agents, as defined by the Agent Skills specification. SkillEvaluator is part of the NVIDIA Verified Skills pipeline. Three-tier overview Tiers are independent entry points; nothing requires running earlier ones first.

Quick Facts

Compatible Skills

These tools work well together with SkillEvaluator for enhanced workflows:

• eval-view — semantic(0.28)+complementary+rare_topics+same_lang+similar_pop+shared_platform (64%)
• intelligent-audit-system — semantic(0.37)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)
• qiaomu-meta-skill — semantic(0.33)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
• coder_eval — semantic(0.32)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
• RagScore — semantic(0.31)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)

More Codex Skill Tools

Explore other popular codex skill tools:

• openclaw ⭐ 393.0k
• hermes-agent ⭐ 256.8k
• ui-ux-pro-max-skill ⭐ 139.3k
• agent-skills ⭐ 106.3k
• orca ⭐ 105.0k
• open-design ⭐ 103.8k
• taste-skill ⭐ 102.0k
• career-ops ⭐ 77.0k
• graphify ⭐ 76.9k
• system_prompts_leaks ⭐ 70.1k

Popular Python Agent Tools

• hermes-agent ⭐ 256.8k · Codex Skill
• skills ⭐ 179.5k · Agent Tool
• dify ⭐ 159.4k · MCP Server
• open-webui ⭐ 156.7k · MCP Server
• langflow ⭐ 156.0k · Agent Tool

Frequently Asked Questions