Claude Code harness that builds a live AI dungeon RPG from scratch, then governs it as game master — real-time agent competition with evolving rules
npx skills add sparsh-555/forge-arenaClaude Code harness that builds a live AI dungeon RPG from scratch, then governs it as game master — real-time agent competition with evolving rules
Source: https://github.com/sparsh-555/forge-arena
Discovered from GitHub repositories pushed in the last 24 hours for agent skills, Claude/Codex/Gemini workflows, MCP tooling, and adjacent AI-agent automation.
SpectraScout is a multi-agent, AI-powered assistant designed to analyze companies, validate job offers, debug and execute code, and help users grow their technical skills. It combines GitHub MCP intelligence, web search, and code-analysis tools to deliver reliable insights, trust scores, and personalized roadmaps.
AI-powered autonomous code debugger built with MERN Stack + Groq AI + MCP — upload your project ZIP, let the AI agent inspect, analyze, and fix bugs step by step.
A Claude Code skill for ElevenLabs TTS — wraps single-voice / multi-voice / v3-with-timestamps endpoints, plus a hard-won Chinese podcast cookbook (tag patterns, pacing, literacy rules, multi-chunk merge bug fixes, sync UI tips).
onlava — one CLI tool for building, running, inspecting, and debugging Go backends. Local-first runtime, APIs, logs, traces, DB tools, generated clients, and AI agent skills included.
article-proof-check 是一个用于 SCI 论文 proof 阶段终校的 Codex skill。它面向作者收到期刊 proof、galley proof、校样、清样或 article proof 后的提交前最终检查，重点发现明确错误、出版排版问题、图表/引用/编号问题，以及需要作者确认的高风险信息。
Enable efficient smart contract bug bounty hunting with AI-powered skills built from thousands of real Immunefi and DeFiHack reports.