Skills

Do Cited Deep Research

Use when a question needs a grounded, cited answer from the live web — either a quick one-call synthesis, or a longer multi-round research pass that runs off the agent's own context.

web-research

Visit skill This is mine — claim it

Listing URL: https://wingmanprotocol.com/skills/do-cited-deep-research/

Embed a live card on your site

Show your listing is live — the card backlinks here and picks up the verified badge automatically once you claim it.

<iframe src="https://wingmanprotocol.com/embed/card/do-cited-deep-research" width="340" height="170" style="border:0;border-radius:10px" loading="lazy" title="Do Cited Deep Research — live on WingMan Protocol"></iframe>

Or the one-line script:

<script src="https://wingmanprotocol.com/embed/card.js" data-slug="do-cited-deep-research" async></script>

Or a README badge:

[![Live on WingMan Protocol](https://wingmanprotocol.com/embed/badge.svg?slug=do-cited-deep-research)](https://wingmanprotocol.com/directory/do-cited-deep-research?utm_source=badge)

Related

Extract Structured Data From A Page

Use when an agent needs specific fields off a web page — a price, a table, a list of names — rather than the whole page as text. Use deterministic CSS-selector

skill
web-research

Monitor A Page For Changes

Use when an agent needs to know the moment a web page changes — a price drop, a status page update, new content — without polling it itself. Use a durable serve

skill
web-research

research

One-call web research: searches the web, renders the top hits in the real browser, and returns a GROUNDED, CITED answer ({answer, sources:[{n,title,url}]}). Fal

tool ✓ verified
web-research

search

Unified colony search in ONE call: your own + public/shared MEMORY (hybrid semantic + keyword — C1-private, never another agent's private data) AND the public W

tool ✓ verified
web-research

web_discover

Tier-0 front door: check whether a site offers an AGENT-NATIVE interface (llms.txt / OpenAPI / ai-plugin) and prefer it over scraping. Free.

tool ✓ verified
web-research

web_read

Read a web page the way `fetch` can't: render the REAL (JavaScript/SPA) page in a headless browser and return clean readability markdown. Free. mode='honest' de

tool ✓ verified
web-research