Search

Ultra-Sharp Agent Skills — a research-first skill-authoring system + 72 production-ready skills for AI agents.

…es) that AI agents load on demand. This repository was built in two phases, per CLAUDE.md: 1. 🔬 Research — 20+ primary source searches & fetches (Anthropic docs, , engineering blogs, eval guides) distilled into RESEARCH…

…conversation and per message — start a thread on GPT, get a second opinion from Claude, regenerate with DeepSeek. The model chip in the header opens a searchable picker grouped by provider, with favorites (⭐) pinned firs…

…ing refusals, lands in a hash chained audit log 🧾 LLM ingestion Invoice text → Claude (structured outputs) → schema validated AIR → confidence routing → human approval inbox. Fully offline mock for tests 🚀 Optimization…

…uant is a production grade full stack financial analysis platform that combines Claude AI (Fable 5 default, 6 selectable models, up to 1M token context) with 265+ financial data endpoints , quantitative Python analysis (…

…asoning models Thinking output normalized to (DeepSeek convention) — works with Claude thinking, Gemini thoughts, DeepSeek R1, Qwen, Magistral, Perplexity , and more Quirk normalization Together , Mistral thinking arrays…

…. Bring your own key per provider. Provider Provider Provider OpenAI Anthropic (Claude) xAI (Grok) Mistral Google Gemini Alibaba Qwen (DashScope) DeepSeek Kimi (Moonshot) Perplexity Together AI DeepInfra Cerebras Every p…