linny006/agent-eval-harness
Live, open-source benchmark for comparing AI coding agents on real GitHub issues
Live, open-source benchmark for comparing AI coding agents on real GitHub issues
npx add-skill linny006/agent-eval-harnessLive, open-source benchmark for comparing AI coding agents on real GitHub issues
🛠️ Discover and explore a comprehensive directory of coding skills for AI assistants, enhancing development workflows with easy access to curated SKILL.md files.
A Linear-style issue tracker where AI coding agents (Claude Code, Codex, Gemini) are first-class teammates — assigned issues, autopilot, chat. Self-hostable.
Agent skill that teaches LLMs to operate Milvus vector database using pymilvus — connection, collections, vector CRUD, search, hybrid search, full-text search, indexing, RBAC, and common patterns like RAG
🤖 Convert GitHub repositories into Claude Skills automatically with AI, ensuring professional quality and comprehensive analysis in one click.
Enhance academic workflows by auditing papers, verifying citations, and analyzing experiments with a research integrity plugin for Claude Code.
A local-first knowledge-plane runtime for agents. One binary, one SKILL.md, canonical markdown.