a generalized evaluation framework for quantized LLMs in agentic workflows
npx skills add minyang-chen/AQBEa generalized evaluation framework for quantized LLMs in agentic workflows
Source: https://github.com/minyang-chen/AQBE
Discovered from GitHub repositories pushed in the last 24 hours for agent skills, Claude/Codex/Gemini workflows, MCP tooling, and adjacent AI-agent automation.
Autonomous AI agent with hot-loadable skills — Anthropic & OpenAI support
Homebrew taps for AI agent skills. Agent-agnostic. Install from any git host or npm registry, search across taps and searchable registries like skill.sh, find, static and semantic security scanning before anything touches disk.
Store persistent AI agent memory in Markdown files with search, context injection, checkpoints, and compaction—no database needed
draw.io compatible xml (bpmn2) claude skill
Installable Hive Intelligence agent skills for crypto MCP setup, discovery, and research workflows.
Rally: governed portfolio research and trade planning — scores public-market candidates with risk-bounded allocation.