ultimate-browsing
Escalation skill for blocked or hard-to-reach web access — load it when a normal browse/fetch is blocked (WAF, 403, Cloudflare, JS-only…
Examining code for the line that is wrong
What it does
Escalation web access for tasks a normal browse or fetch cannot complete. Reach for this skill the moment a page is blocked (WAF / 403 / Cloudflare), needs JS rendering, hides behind a login, or lives on a platform a generic fetcher cannot read. Escalate only when the cheaper tier cannot do the job:
What it can touch
Includes 24 scripts
Your AI can run these when the skill is used — on your computer in a coding tool (which asks first unless you have told it not to), or in the AI’s own sandbox in Claude and ChatGPT.
How we know
Found in the skill’s folder: engine/__init__.py, engine/__main__.py, engine/bias_check.py, engine/curl_probe.py….
Asks for an API key or token
You will need an account with the service it talks to, and your own key. Keep keys in your settings or environment, never in a chat.
How we know
The SKILL.md names JINA_API_KEY.
Mentions 3 outside web addresses
The instructions point your AI at these sites or APIs. Anything it sends there leaves your computer.
How we know
Web addresses in the SKILL.md, excluding GitHub and documentation sites: r.jina.ai, weibo.com, www.v2ex.com.
Uses terminal commands
It shows your AI commands to run. In a coding agent that means your terminal; in a chat app it usually can’t.
How we know
The SKILL.md contains shell code blocks.
Tells your AI to open private keys or password stores
These words are aimed at your AI rather than at you. Skills that teach defence quote such phrases too — open the line and judge the context.
How we know
scripts/cookie_crypto.py line 54: “raise RuntimeError(f"cannot read {safe_storage} from Keychain: {result.stderr.strip()}")”. Read 2026-10-05, commit 9d2b45e.
scripts/cookie_crypto.py, line 54 ↗Its code sends data over the internet
A script in it uploads or posts data. That is normal for a skill that talks to a service — check that the address is the service you expect.
How we know
engine/tests/fixtures/search_interstitial.html line 15 (and 2 more in that file): “q);q=m+n;a:{try{var t=window.navigator.sendBeacon(q,"");var u=t===void 0?!0:t;break a}catch(A){}u=!1}u||google.log("","",q)}};var N=functio…”. Read 2026-10-05, commit 9d2b45e.
engine/tests/fixtures/search_interstitial.html, line 15 ↗1 smaller thing worth knowing
Contains commands that delete or overwrite. Usually legitimate — listed so nothing is hidden.
How we know
Contains commands that delete or overwrite — SKILL.md line 107. Read 2026-10-05, commit 9d2b45e.
SKILL.md, line 107 ↗Recently maintained
Its repository has had changes recently.
How we know
Last push to code-yeongyu/lazycodex: 2026-10-04 (1 days before the scan).
Read automatically from the skill’s own files on GitHub on 5 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Partly. Upload it in Claude’s settings — the instructions work; the scripts need the full folder.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
This skill ships 24 scripts beside its instructions. The download here is the SKILL.md alone — enough for the instructions, not for the parts that run code. Use the command route, or take the full folder from the repository.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end
More from code-yeongyu
All from this publisher →- ast-grep
Use ast-grep (sg) for AST-aware code search and rewrite across 25 languages.
- coding-agent-sessions
MUST USE when asked to find, read, list, search, inspect, fetch, export, or reconstruct coding-agent sessions across Codex, Claude Code/Desktop, OpenCode,…
- data-scientist
Expert data processing specialist with intelligent DuckDB/Polars selection for maximum performance.
- frontend
MUST USE for frontend/web UI/UX/visual work: building, styling, redesigning pages/components, React setup, performance audits, visual QA, taste, and…
- full-output-enforcement
Overrides default LLM truncation behavior.
