Research capability for coding agents: multi-source corroboration, active discovery, logical-space thinking, structured output. Browser-first evidence.
Skill Claude CodeCodex
Skill "multi-search-engine" from lxinfei5/research-os, covering multi search engine — researchos tier-3 quota-free fallback, where this sits — the web search fallback chain, workflow, engine selection (topic-agnostic) and operators & filters.
Skill Claude CodeCodex
Distill and condense sources into topic knowledge.md along the half-life axis L3→L2→L1→L0. Stable knowledge stays in the KB; fast knowledge prefers live fetch. Core ResearchOS product skill — use after discovery.
Skill Claude CodeCodex
Run one ResearchOS growth cycle: prime from L0/L1 → discover on user-trusted channels → capture → distill/corroborate by half-life → think → emit a lowest-burden user surface (act / hold / flip), audit behind. Use when the user wants to grow/deepen/research a topic.
Skill Claude CodeCodex
Optional perception helpers: speech-to-text and OCR so media becomes text claims. Not a judgment engine.
Skill Claude CodeCodex
Source-agnostic evidence gathering for ResearchOS. Use whatever channels the user trusts (APIs, browser, files, briefings, library). Multi-angle coverage matters more than any single transport.
Skill Claude CodeCodex
Example domain skill: travel planning as research capability — multi-source corroboration, first-principle trip purpose, one-glance go/don’t plan. Not a scrape kit.
Skill Claude CodeCodex
Optional: gather Xiaohongshu (or similar) via whatever channel the user trusts (browser, MCP, export). Not a core dependency.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: