Ayanami

deep_research_bench. DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

arag. A-RAG: Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces. State-of-the-art RAG framework with keyword, semantic, and chunk read tools for multi-hop QA.

paper-read-skill. AI Agent prompts for deep paper reading — auto-routes to benchmark, methodology, or survey/opinion analysis frameworks. Works with Cursor, Claude Code, Codex, and OpenCode.