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 skills add linny006/agent-eval-harnessLive, open-source benchmark for comparing AI coding agents on real GitHub issues
⚙️ Manage and sync AI coding assistant skills across multiple platforms to streamline development with Claude Code, Codex, and Opencode.
Claude Code skill that derives infrastructure architectures from workload analysis using first-principles math (Little's Law, Erlang-C, USL, availability calculus). 7-dimension constraint framework with swappable cloud/regulatory catalog.
Personal Agent OS for Claude Code — 46 hooks, 3501 skills, 97 agents. Blocks rm -rf, prompt injection, pipe-to-shell at runtime. Apache 2.0.
Cost-Xray: a Claude Code / Codex skill for product cost breakdown and pricing analysis.
基于 ZAKER 权威资讯库的 AI 技能集，包含24小时头条、行业新闻与精准检索。免鉴权开箱即用，为 AI 提供实时真实的新闻数据，有效降低幻觉。 | ZAKER News Skills for AI Agents: 24h headlines, category news & precise search. No API key needed. Reduces AI hallucinations with real-time authoritative news.
An open-source framework for engineering your professional discoverability across platform algorithms, search engines, and AI agents. Covers CV/ATS, LinkedIn, GitHub, personal websites, X, and Agent Context Optimization (ACO).