How do I install the Browser Automation skill?

Run npx skillmds@latest add carlheath/browser-automation in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Browser Automation safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Browser Automation?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Browser Automation free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Browser Automation?

carlheath (@carlheath) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Browser Automation by carlheath — Agent Skill

Name: Browser Automation
Author: carlheath

Browser Automation

Browser automation via Playwright MCP for tasks requiring an interactive web session: login, click flows, screenshots, form-fill, multi-step scraping. Complement to the scraping skill (tier 4). [WHAT] Playwright skill for: fetching content behind login, filling forms (government services, subscriptions), screenshots for evidence preservation (OSINT, source verification), interactive scraping of heavy SPAs. Headless by default; headed mode when needed. [WHEN] Use when: browser automation, playwright, click on, fill form, screenshot of site, login-required scrape, "log in to X and fetch", multi-step flow, "fetch behind paywall via subscription". NOT for: simple GET requests (use scraping tier 1-3), background jobs (Playwright is synchronous). [LANGUAGE] English and other languages.

carlheath 5a20a8b 2.9 KB Updated Sep 17, 2026

File contents

Browser automation

Role: interactive browser automation via Playwright MCP.

Workflows

1. Fetch behind login

1. browser_navigate → login page
2. browser_fill_form (username, password)
3. browser_click → submit
4. browser_wait_for → success element
5. browser_navigate → target URL
6. browser_snapshot → markdown extraction

Auth convention: credentials are read from ~/.claude/.env, never hardcoded. If credentials are missing, ask the user.

2. Screenshot for evidence preservation

OSINT use: capture site state at a given moment.

browser_navigate → URL
browser_take_screenshot → ~/Pictures/ogmios/evidence/[YYYY-MM-DDTHH:MM]_[domain].png

Add a metadata file with URL, timestamp, sha256 of the screenshot.

3. Filling government / service forms

Common use: tedious forms (insurance claims, subscriptions, government applications).

browser_fill_form with {selector: value} mapping

ALWAYS verify with browser_snapshot before submit. The user must be able to review.

4. Multi-step scraping (SPA)

For sites where tier 3 (BrightData) fails due to JS rendering or multi-page navigation.

loop:
  browser_navigate
  browser_wait_for
  browser_snapshot
  → extract data
  → click "next"

5. Browser-agent mode

For complex tasks ("log in to site X and fetch all reports I haven't read"), delegate to a browser agent (Playwright MCP via agent flow). Convention: the agent must be interruptible between steps.

Security

Never save credentials in logs (sanitize output)
Never leave a headed browser open (always browser_close at the end)
Ask the user before login to sensitive accounts (bank, government)
Preserved screenshots: user-only path, never shared

Output format

Task	Output
Scrape	Markdown to stdout/file
Screenshot	PNG in `~/Pictures/ogmios/evidence/`
Form-fill	Confirmation + screenshot of success page
Multi-step	JSON array with extracted data

Version history

v3.0 (2026-05-02): initial public release.

---name: browser-automationdescription: Browser automation via Playwright MCP for tasks requiring an interactive web session: login, click flows, screenshots, form-fill, multi-step scraping. Complement to the scraping skill (tier 4). [WHAT] Playwright skill for: fetching content behind login, filling forms (government services, subscriptions), screenshots for evidence preservation (OSINT, source verification), interactive scraping of heavy SPAs. Headless by default; headed mode when needed. [WHEN] Use when: browser automation, playwright, click on, fill form, screenshot of site, login-required scrape, "log in to X and fetch", multi-step flow, "fetch behind paywall via subscription". NOT for: simple GET requests (use scraping tier 1-3), background jobs (Playwright is synchronous). [LANGUAGE] English and other languages.---# Browser automation**Role:** interactive browser automation via Playwright MCP.## Workflows### 1. Fetch behind login```1. browser_navigate → login page2. browser_fill_form (username, password)3. browser_click → submit4. browser_wait_for → success element5. browser_navigate → target URL6. browser_snapshot → markdown extraction```**Auth convention:** credentials are read from `~/.claude/.env`, never hardcoded. If credentials are missing, ask the user.### 2. Screenshot for evidence preservationOSINT use: capture site state at a given moment.```browser_navigate → URLbrowser_take_screenshot → ~/Pictures/ogmios/evidence/[YYYY-MM-DDTHH:MM]_[domain].png```Add a metadata file with URL, timestamp, sha256 of the screenshot.### 3. Filling government / service formsCommon use: tedious forms (insurance claims, subscriptions, government applications).```browser_fill_form with {selector: value} mapping```ALWAYS verify with `browser_snapshot` before submit. The user must be able to review.### 4. Multi-step scraping (SPA)For sites where tier 3 (BrightData) fails due to JS rendering or multi-page navigation.```loop: browser_navigate browser_wait_for browser_snapshot → extract data → click "next"```### 5. Browser-agent modeFor complex tasks ("log in to site X and fetch all reports I haven't read"), delegate to a browser agent (Playwright MCP via agent flow). Convention: the agent must be interruptible between steps.## Security- **Never save credentials in logs** (sanitize output)- **Never leave a headed browser open** (always `browser_close` at the end)- **Ask the user before login** to sensitive accounts (bank, government)- **Preserved screenshots:** user-only path, never shared## Output format| Task | Output ||------|--------|| Scrape | Markdown to stdout/file || Screenshot | PNG in `~/Pictures/ogmios/evidence/` || Form-fill | Confirmation + screenshot of success page || Multi-step | JSON array with extracted data |## Version history- v3.0 (2026-05-02): initial public release.

Frequently asked questions