Agent skill · data analytics · code-yeongyu
ultimate-browsing
Reaches web pages the user's browser cannot open: WAF-blocked and bot-scored hosts, platform-native readers (Chinese and social platforms), archive snapshots with provenance, and a browser you own for stealth or throwaway profiles. Not for plain search, an unblocked static fetch, or a page the user's browser can open.
Why this skill is useful
Adds multiple executable scripts for bypassing web access restrictions and extracting data from blocked or complex sites.
What it needs
Requires curl, jina, playwright, python3, yt-dlp installed locally. About 6k tokens when loaded. Last updated 2026-08-07. 67,387 stars on the source repository.
What this skill does
Ultimate Browsing Web access for the hosts the user's browser cannot open (WAF / 403 / Cloudflare / bot-scored pages) and for platforms with a native reader. Reading and interaction on a page the user's browser can open belong to the browser skill's attached engine, not here. Start at the cheapest tier that can reach the blocked host and climb only when it cannot: Tier 1 — insane-search (headless extraction + WAF bypass) -> Tier 1.5 — agent-reach (platform-native APIs, esp. Chinese platforms) -> Tier 2 — a real browser through omowright from js eval: 2a the owned engine (a browser your code launches, CloakBrowser for stealth), 2b the attached engine (the user's own signed-in browser). PHASE 0 — ROUTE FIRST (MANDATORY) Read the matching reference before acting: references/insane-search/README.md, references/agent-reach/README.md, or references/chrome-stealth.md. Tier 1 — insane-search (headless extraction) When: blocked-URL bypass, media metadata, archive surrogates — no browser UI needed. Why first: ~10x faster than a browser, no process spin-up; handles most "fetch this blocked page" requests via curlcffi TLS impersonation, yt-dlp (1858 sites), official public APIs, mobile URL transforms, Phase-2.5 surrogate archives (Wayback / archive.today snapshots, provenance-tagged — see references/insane-search/cache-archive.md), a key-gated Jina Reader (JINAAPIKEY), and a Playwright real-Chrome fallback. The engine lives inside this skill at engine/ and is invoked as a module. Surrogate results are dated COPIES: a result whose provenance is snapshot must be reported with its snapshottimestamp, never presented as the live page. The full engine harness (rules R1-R7, the Phase 0 official-API index, the no-site-name rule, and the references/insane-search/.md deep-dives for TLS, Playwright routing, Naver, media, etc.) is in references/insane-search/README.md. Read it before tuning the engine or adding a WAF profile. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills code-yeongyu/ultimate-browsing