Web, Search & Scraping Agent Skills

Drive a real stealth browser from your shell — act on websites (order food, file an expense, pull data behind a login), with per-person…

Download files from authenticated web sessions.

Upload local files through website file controls using Codex Browser Use.

This skill should be used when users need to capture screenshots of web pages.

Architecture for attaching Chrome page context and control to Agent Native conversations.

Captures polished screenshots or video of a web application in a browser, driving page-owned states through browser control and verifying…

Create polished 60 fps 4:3 4K browser screen-recording style videos from Codex in-app browser captures, with browser-only crop, natural…

Upload local files to a ChatGPT conversation through the Codex in-app browser without using the native file picker.

Automates ChatGPT web tasks like text processing, image generation, and document analysis via macOS osascript without extensions or API…

Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.

Record polished UI demo videos using Playwright.

Use when collecting data for a research project, downloading time series, building a dataset, accessing economic or social data APIs, or…

Complete knowledge domain for Firecrawl v2 API - web scraping and crawling that converts websites into LLM-ready markdown or structured…

Download videos, audio, playlists, and channels from YouTube and 1000+ websites using yt-dlp.

Procedure for answering a question with a thorough, cross-checked, cited web-research report using the Keenable search + fetch tools.

Run a disciplined, multi-source research investigation for a high-stakes question or decision — fan-out web search across many channels…

Run a deep, source-backed research query via DeepAPI (go to deepapi.co to get an API key) POST /v1/research/deep.

Use DeepAPI for all regular web searches (POST /v1/search/web) and for any deep research you perform (POST /v1/research/deep), instead of…

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens.

Download files from authenticated web sessions.

Exploratory QA of web apps: find bugs, evidence, reports.