zhjai/agent-arena
Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to independently review, red-team & judge high-stakes code and architecture decisions.
Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to independently review, red-team & judge high-stakes code and architecture decisions.
npx add-skill zhjai/agent-arenaEvidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to independently review, red-team & judge high-stakes code and architecture decisions.
Claude skills for development
CLACOROO — Claude Code Control Room: pannello visuale per plugin, marketplace, skill e agent
GitHub Action + CLI to detect malicious patterns in MCP servers, AI agent skills, and plugins. 68+ attack signatures.
Automate Docnify tasks via Rube MCP (Composio). Always search tools first for current schemas.
Plan and run long-lived autonomous development loops with explicit safety rails, mechanical verification, resumable state, and bounded task scopes.
微信读书 CLI / WeRead CLI: 基于官方支持 API，面向人类与 AI Agent 的书架、笔记、划线、书评、阅读统计和推荐工具。Official API-based WeRead command-line tool with Agent Skill support.