nc9nc9/skills/browserbase/SKILL.md

browserbase

Skill4 starsChanged 54 days agoMITView on GitHub

Fetch web pages via Browserbase headless browsers with proxy and automatic captcha solving. Use when a page is behind Cloudflare, bot protection or geo-restriction, or needs JavaScript rendered before its content is readable.

Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

CarriedWorldUniverse/nexustheir own version, first seen Oct 12, 2026

Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
CarriedWorldUniverse/nexus★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository18 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-browserSkill
- ai-writing-detectorSkill
- animate-svgSkill
- clickhouseSkill
- commitSkill
- geist-designSkill
- generate-faviconSkill
- generate-imageSkill
- google-indexingSkill
- google-search-consoleSkill
- google-searchSkill
- humanizerSkill
- keyword-researchSkill
- parallelSkill
- remove-backgroundSkill
- reviewSkill
- web-uiSkill

The file

Create a free account to mount

Files

SKILL.md

Browserbase Fetch

Remote headless Chromium via Browserbase, with proxy, captcha solving and ad blocking.

Requirements

BROWSERBASE_API_KEY — browserbase.com
BROWSERBASE_PROJECT_ID — from the Browserbase dashboard

Commands

./scripts/browserbase_fetch fetch "https://example.com" [options]
./scripts/browserbase_fetch fetch-many "https://a.com" "https://b.com" [options]

Options

Option	Description
`-f, --format`	`text` \| `html` \| `json` (default `text` for `fetch`, `json` for `fetch-many`)
`--proxy / --no-proxy`	Proxy, default on
`--captcha / --no-captcha`	Captcha solving, default on
`--block-ads / --no-block-ads`	Ad blocking, default on
`-t, --timeout`	Page load timeout, seconds (default 30)
`-w, --wait`	Extra wait after load, ms (default 0)

Output

text is document.body.innerText, html the rendered DOM, json is {url, title, content}. fetch-many emits an array of those objects, substituting {url, error} for any page that failed.

Gotchas

fetch-many ignores -f and always prints JSON. Use fetch per URL for text or html.
Each fetch opens and releases its own billed session; fetch-many reuses one, so batch when you can. --no-proxy is cheaper and faster where geo and IP reputation do not matter.
Load waits for networkidle, so pages that poll never settle — cap with -t and lean on -w.

Examples

./scripts/browserbase_fetch fetch "https://example.com" -f json
./scripts/browserbase_fetch fetch "https://spa.example.com" -w 3000 -t 15
./scripts/browserbase_fetch fetch-many "https://a.com" "https://b.com" --no-proxy

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free