agentleFS
Sign inStart free
ScinoScino/fstack/skills/browse/SKILL.md

browse

Skill18 starsChanged 53 days agoMITView on GitHub

Web browsing and page extraction. Attaches to Chrome over CDP when it is running, otherwise one-shot headless Chrome. Use for /browse, "open URL", public competitor pages, interactive search UIs, or a session where you are already logged in.

53 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-gbrain, open-gstack-browser and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ShreyRaviSkill

    setup-gbrain

    Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. One command from zero to "gbrain is running, and this agent can call it." Use when: "setup gbrain", "connect gbrain", "start gbrain", "install gbrain", "configure gbrain for this machine". (gstack)

    Also in 9 projects that use this

  • seek888Skill

    open-gstack-browser

    Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".

    Also in 11 projects that use this

  • Saqlain-811Skill

    ios-sync

    Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)

    Also in 6 projects that use this

  • ayudaySkill

    setup-deploy

    Configure deployment settings for /land-and-deploy. Detects your deploy platform (Fly.io, Render, Vercel, Netlify, Heroku, GitHub Actions, custom), production URL, health check endpoints, and deploy status commands. Writes the configuration to CLAUDE.md so all future deploys are automatic. Use when: "setup deploy", "configure deployment", "set up land-and-deploy", "how do I deploy with gstack", "add deploy config".

    Also in 19 projects that use this

  • ShreyRaviSkill

    landing-report

    Read-only queue dashboard for workspace-aware ship. Shows which VERSION slots are currently claimed by open PRs, which sibling Conductor workspaces have WIP work likely to ship soon, and what slot /ship would pick next. No mutations — just a snapshot. Use when asked to "landing report", "what's in the queue", "show me open PRs", or "which version do I claim next". (gstack)

    Also in 9 projects that use this

  • Saqlain-811Skill

    ios-clean

    Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)

    Also in 5 projects that use this

  • +3 more from ShreyRavi
  • +1 more from Saqlain-811

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 45 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use CDP when you need to type, click, or wait on a page, or when headless is blocked.

    line 61
  2. Distinctive:

    If the host agent already has a working browser tool (Cursor, Antigravity), use it for ordinary pages.

    line 87

“Common” is measured: kept by at least 6 in 10 of the 45 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Browse

Drive a real browser. Prefer this over naive Playwright scripts. Extracted text is sanitized before it hits the model.

How to invoke

From any harness:

npx @scino/fstack browse <command>

From this skill folder (works when the skill is a junction into the fstack package):

node run.mjs <command>

From a clone:

node bin/fstack.js browse <command>

Commands

fstack browse goto https://example.com
fstack browse text
fstack browse text https://example.com
fstack browse screenshot
fstack browse screenshot https://example.com out.png
fstack browse eval "document.title"
fstack browse eval https://example.com "document.title"
fstack browse check-cdp
fstack browse sanitize ./raw.txt

goto / text / screenshot / eval without a URL need Chrome CDP (your session). With a URL they can run headless in one shot.

text waits for visible body text, then fails if the body is still empty. That is usually a search shell, a challenge page, or JS that never painted. Do not retry the same URL. Search or click, then text again.

Strategy 1: One-shot headless

Public pages where the URL already has the content. Pass the URL on the command.

fstack browse text https://example.com

Uses installed Chrome when possible. Text is injection-sanitized.

Strategy 2: Real Chrome (interaction and login-walled sites)

Use CDP when you need to type, click, or wait on a page, or when headless is blocked.

Empty extract is not a login problem by itself. Many public UIs start as a search shell. Attach CDP, complete the query or click in that window (or goto a URL that already encodes the query), wait until results exist, then fstack browse text with no URL.

Login-walled sites (LinkedIn, X, and similar) still need you to log in by hand in that Chrome. Only use sessions you own.

Start Chrome once:

Windows (throwaway profile; does not fight an already-open Chrome):

& "C:\Program Files\Google\Chrome\Application\chrome.exe" --remote-debugging-port=9222 --user-data-dir="$env:TEMP\chrome-fstack-cdp"

To reuse your real cookies, quit Chrome first, then point --user-data-dir at $env:LOCALAPPDATA\Google\Chrome\User Data.

macOS:

/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222

Confirm with fstack browse check-cdp.

Strategy 3: Harness native browser

If the host agent already has a working browser tool (Cursor, Antigravity), use it for ordinary pages. Use this skill when you need CDP attach, sanitization, or a harness that has no browser.

Needs

playwright-core (ships with @scino/fstack). Headless one-shot wants Chrome installed, or npx playwright install chromium.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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