Explorar skills

Use for Docker image and container registry searches when query involves Docker images, containers, or deployment artifacts.

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

Advisory skill — three-tier (Fast / Standard / Best) model routing catalog for autosearch skills. Tells the runtime AI which tier each leaf skill needs, and how to escalate or de-escalate. Autosearch does not switch models itself; the runtime AI is the decision-maker.

Read research outline and launch independent agents for in-depth research on each item. Task output disabled.

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

Assesses team fitness and composes agent teams. Use when "set up a team", "team for this", "should I use agents", "design a team", "how many agents", "agent team".

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

Deep URL fetch using crawl4ai (Playwright-powered) for JS-rendered pages, anti-bot sites, and dynamic content. Slower than fetch-jina but handles sites that block simple fetchers. Requires user-installed crawl4ai package.

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

Structured entity data (people, places, concepts) from Wikidata knowledge graph.

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

Search scholarly works through OpenAlex's public works search API with open-access URL fallback.