Explorar skills

Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.

Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.

Group-first channel selection algorithm for v2 tool-supplier architecture. Given a research query + clarify rubrics + channel_priority hints, picks 1-3 relevant groups from the router index, then 3-8 leaf channels from within those groups. Replaces flat-rank selection across 41 channels with a two-stage pick so runtime AI never has to read all 41 SKILL.md bodies.

Add field definitions to existing research outline.

LinkedIn public pages — company profiles, job posts, professional articles via Jina Reader (no auth needed for public content).

Summarize deep research results into a markdown report, covering all fields, skipping uncertain values.

Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.

Transcribe video/audio URL or local file to text + SRT using yt-dlp + Groq Whisper API (free tier). Preferred default for v2 transcription. Returns raw text and segments; summary is caller's responsibility.

Use for Chinese community forum discussions on Baidu Tieba when query involves Chinese tech topics, product feedback, or hobby communities not covered by xiaohongshu/zhihu.

Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.

Explicit loop state for multi-round research — maintains gaps, visited URLs, bad URLs, failed-evaluator feedback, and decides whether to fire another round of queries or stop. Inspired by WebThinker's in-band search protocol, node-deepresearch's agent.ts state, and Scira's extreme-search.

Use for public Discourse-based community discussions, especially Linux DO, when queries need Chinese AI/dev forum posts and native operator troubleshooting.