Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-calibrated judges, gated self-update loop, pressure testing, 10 authoring principles grounded in empirical research.
Like smixs/skill-conductor, 0 likes 0 Bookmark smixs/skill-conductor, 0 bookmarks 0 CLI / Framework for Agent Skills - create, test, measure and improve skill quality and effectiveness
Like microsoft/waza, 0 likes 0 Bookmark microsoft/waza, 0 bookmarks 0 Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.
Like NVIDIA/SkillEvaluator, 0 likes 0 Bookmark NVIDIA/SkillEvaluator, 0 bookmarks 0 Write professional-grade skills for agents, validate them using LLMs, and maintain a lean context window.
Like mgechev/skills-best-practices, 0 likes 0 Bookmark mgechev/skills-best-practices, 0 bookmarks 0 SkillsBench evaluates how well skills work and how effective agents are at using them.
Like benchflow-ai/skillsbench, 0 likes 0 Bookmark benchflow-ai/skillsbench, 0 bookmarks 0 An evaluation and evolution tool for Agent Skills.
Like alibaba/skill-up, 1 like 1 Bookmark alibaba/skill-up, 0 bookmarks 0 A test runner for agentskills.io-style AI agent skills
Like darkrishabh/agent-skills-eval, 0 likes 0 Bookmark darkrishabh/agent-skills-eval, 0 bookmarks 0 Specification and documentation for Agent Skills
Like agentskills/agentskills, 0 likes 0 Bookmark agentskills/agentskills, 0 bookmarks 0 Gaia is a living, open registry of every AI agent skill — structured as a leveling skill graph. Live site: https://gaiaskilltree.com/
Like gaia-research/gaia-skill-tree, 0 likes 0 Bookmark gaia-research/gaia-skill-tree, 0 bookmarks 0 
