Evaluate agent skill quality. Find the weakest link. Fix it. Prove it worked.
ai-agents skill-evaluation anthropic agent-skills claude-code skill-rating claude-code-skill openclaw openclaw-skill
-
Updated
Apr 23, 2026 - JavaScript
#
skill-evaluation
Here are 19 public repositories matching this topic...
Language: All
Filter by language
Sort: Most stars
Sort options
Open-source self-hosted web tool for evaluating Agent Skills with rubric scores, Deep Review, and improvement suggestions.
typescript skills skill nextjs self-hosted developer-tools cursor ai-agents claude rubric skill-evaluation llm agent-skills claude-code openclaw
-
Updated
May 17, 2026 - TypeScript
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.
-
Updated
Jun 8, 2026 - Python
OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents
-
Updated
Jun 1, 2026 - Python
Evaluation framework for LLM knowledge inputs — prompts, RAG corpora, skills, agent workflows. Fix the model, vary the artifact. Built-in statistical rigor: bootstrap CI, Krippendorff α, length-debias, saturation curves.
benchmark ai evaluation-framework claude knowledge-engineering skill-evaluation llm prompt-engineering prompt-testing llm-evaluation rag-evaluation llm-judge claude-code agent-evaluation bootstrap-ci krippendorff-alpha evaluation-as-code multi-judge-ensemble
-
Updated
Jun 14, 2026 - TypeScript
Your AI agent skill doctor - 5-dimension scoring + security gate + leaderboard
security evaluation cursor ai-agents skill-evaluation ai-agent llm claude-code codex-cli claude-skills meta-skill openclaw skill-review hemerss
-
Updated
Jun 10, 2026 - Shell
MCP server for Claude Code: Anna's Archive search/download + Gemini methodology extraction → audited Claude Code SKILL.md. One tool call, end-to-end.
nodejs pdf typescript mcp gemini epub methodology rag knowledge-extraction skill-evaluation ai-agent annas-archive anthropic google-ai-studio model-context-protocol agent-skills claude-code stdio-server claude-skill book-extraction
-
Updated
May 26, 2026 - TypeScript
Triage-trainer:从零为您的个人助手构建定制化的导诊 Skill,赋予精准的就诊科室推荐能力
-
Updated
Mar 28, 2026 - HTML
Convert methodology books from Anna's Archive into Claude Code skills using the Model Context Protocol.
nodejs pdf typescript mcp gemini epub methodology rag knowledge-extraction skill-evaluation ai-agent annas-archive anthropic google-ai-studio model-context-protocol agent-skills claude-code stdio-server claude-skill book-extraction
-
Updated
Jun 14, 2026 - TypeScript
🧬 Agent 自我进化系统 - 基于数据驱动的 AI Agent 能力提升平台 | ✨ 任务监控/技能评估/智能调度/自动进化 | 📊 95%+ 测试覆盖,<20ms 延迟
python open-source machine-learning automation data-driven performance-monitoring self-improvement skill-evaluation ai-optimization ai-agent intelligent-scheduling agent-evolution
-
Updated
Jun 12, 2026 - JavaScript
Automated model evaluation pipeline v10 (post-incident architecture rewrite)
benchmark mcp chinese skill-evaluation huggingface ai-agent vllm llm-evaluation claude-code agent-evaluation
-
Updated
Jun 2, 2026 - Python
Evaluate agent SKILL.md files for structure, security, quality, and domain correctness.
-
Updated
Apr 18, 2026 - Python
A skill that reviews whether skills found online are safe to install for non-tech-background developers
-
Updated
Mar 22, 2026
AI-powered mock interview platform with automated scoring, role-based questions, modern React UI, FastAPI backend, and a fully implemented freemium SaaS architecture.
machine-learning-application technical-interviews fastapi skill-evaluation ai-tools assessment-platform interview-simulator ai-scoring
-
Updated
Dec 13, 2025 - Python
Claim-first 仓库评测框架。in: owner/repo + repo_type → out: eval scaffold + 可靠性桶 (unusable/usable/reusable/recommendable)
-
Updated
May 26, 2026 - HTML
Source-backed companion guide for agent skills, AI agent workflows, framework resources, evaluation templates, and rollout playbooks.
mcp verification cursor codex ai-agents skill-evaluation github-copilot langchain langgraph coding-agents gemini-cli model-context-protocol agent-skills claude-code openai-agents agent-workflows agent-safety openclaw hermes-agent rollout-playbooks
-
Updated
Jun 11, 2026 - Python
Detect malicious code and security risks in AI skill files before installation to protect AI agents from hidden threats and obfuscation techniques.
performance-tracking learning-platform skills-assessment skill-management workforce-development skill-evaluation hr-software training-management employee-training online-assessments talent-development career-growth skill-gap-analysis competency-mapping training-dashboard
-
Updated
Jun 14, 2026 - Python
A focused Go evaluator for agent-skills CI
-
Updated
Jun 1, 2026 - Go
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.
mcp regression-testing skill-evaluation ai-evaluation llm-eval claude-code plugin-testing eval-harness agent-eval binary-criteria
-
Updated
Jun 14, 2026 - TypeScript
Improve this page
Add a description, image, and links to the skill-evaluation topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the skill-evaluation topic, visit your repo's landing page and select "manage topics."