AI Agent Skills

🏆 Top-1 on 5+ benchmarks | Web UI | Supports MiroThinker, Claude, Kimi, OpenAI

Search and read research papers. The main agent calls alphaXiv, OpenAlex, and bioRxiv discovery primitives, ranks the combined candidates, and chooses sources for focuse…

Evaluation harness for Apodex-1.0 on public deep-research benchmarks.

Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only for binary search) a…

Audience research module — builds six-dimension buyer personas (demographic, psychographic, behavioral, need-state, information, decision), Jobs-to-Be-Done maps, RFM/beh…