Toolkit for testing and packaging portable AI agents across various LLMs, frameworks, and deployment targets
npx skills add jdutton/vibe-agent-toolkitToolkit for testing and packaging portable AI agents across various LLMs, frameworks, and deployment targets
Source: https://github.com/jdutton/vibe-agent-toolkit
Discovered from GitHub repositories pushed in the last 24 hours for agent skills, Claude/Codex/Gemini workflows, MCP tooling, and adjacent AI-agent automation.
Asta MCP skill — give Claude Code/Codex/Cursor/Windsurf/OpenClaw access to Semantic Scholar via Ai2 Asta MCP server
Stable customer-callable AI Agent Skills registry baseline
Analyze and evolve AI skills through comparative testing, pattern extraction, and iterative refinement to improve agent performance.
Multi-tenant X (Twitter) automation platform for AI agents — drive X via MCP or REST with browser-backed sessions, not the public API.
B/O/E evaluation framework for SKILL.md-based LLM operating systems and agent hubs
Specification framework for AI agents and humans.