skill-evaluation

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.

把工作流变成可研究、可评测、可发布的乔木 Agent Skill | Turn workflows into researched, tested, release-ready agent skills.

Evaluate agent skill quality. Find the weakest link. Fix it. Prove it worked.

Open-source self-hosted web tool for evaluating Agent Skills with rubric scores, Deep Review, and improvement suggestions.

The skill OS for Codex, Claude Code, and Gemini CLI. One pool, one router, one feedback loop — across all three hosts. Per-turn semantic top-K with dynamic context sizing, session-end self-evaluation, and evidence-blended re-ranking that gets better the more you use it.

OMK — Evidence-backed evaluation and observability for prompts, RAG, skills, agents, and workflows. Native Codex, Claude Code, and DeepSeek Harness support.

OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents

How do you KNOW if a 'skill' is any good - deterministically? This runs controlled skill-vs-no-skill experiments. It doesn't just ask, “Did the skill work?” It asks “Did we actually give the skill to the model, did the comparison remain fair, what changed, what did it cost, and do we have enough evidence to say that confidently?”

A complete, open-source guide to Agent Skill design: from cognition to production. 28 chapters + 6 appendices.

Your AI agent skill doctor - 5-dimension scoring + security gate + leaderboard

Convert methodology books from Anna's Archive into Claude Code skills using the Model Context Protocol.

Evidence-first evaluation and creation for Agent Skills.

MCP server for Claude Code: Anna's Archive search/download + Gemini methodology extraction → audited Claude Code SKILL.md. One tool call, end-to-end.

Binary-criteria evaluation harness for Claude skills with planned extension to plugins, agents, and MCP servers. Score every change yes/no across 7 layers — package integrity, trigger quality, functional quality, regression protection, baseline value, model variance, rollout safety. Never gradients.

Description Evidence-driven evaluation, benchmarking, and verified repair for Agent Skills across Codex, Claude Code, Gemini CLI, and Antigravity.

opencode 技能工厂 · Create, evaluate & optimize agent skills via DB physical-evidence eval engine. Cross-platform packaging (trae/claude/generic) + governance. 用 opencode.db 物理证据消除 LLM 自评偏差。

🩺 Behavioral testing for skill triggers — diagnose why a skill never fires (or fires too often), prescribe a fixed description, save a regression suite. One SKILL.md, 79 agents (Claude Code, Hermes, Codex, Gemini...)

SQS (Skill Quality Suite): linter, validator, security scanner and eval harness for AI Agent Skills (SKILL.md) on Claude Code, Codex, Cursor and Gemini CLI - and it tells you which skill to fix or write next from your own sessions

Claim-first repo 评测框架。in target repo + claim map → out bilingual verdict dossier + all-evals dashboard

Evidence-backed release audits for Agent Skills, covering discovery, behavioral uplift, safety, and package integrity. 为 Agent Skill 做有证据的上线审查，验证能否被正确触发、真实提升结果，并安全安装与复现。