browser-agent-automation
Skill0 starsChanged 6 months agoMITView on GitHub
Automates web tasks with LLM-driven browsers using Playwright, Browser-Use, or Playwright MCP. Use for browser automation agents, scraping with agents, form filling, or E2E flows described in natural language.
In this repository14 other files it gives its agents.
- a2a-agent-delegationSkill
- agent-memory-patternsSkill
- agent-observabilitySkill
- agent-redteam-securitySkill
- build-mcp-serverSkill
- create-production-skillSkill
- cursor-sdk-automationSkill
- deploy-agent-productionSkill
- evaluate-agent-qualitySkill
- github-ci-agentsSkill
- langgraph-multi-agentSkill
- multi-agent-supervisorSkill
- rag-agent-pipelineSkill
- secure-mcp-serverSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
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
- Distinctive: line 19
Default: Playwright MCP in Cursor.
- Distinctive: line 23
Never automate login without explicit user consent in session
- Distinctive: line 26
Do not exfiltrate cookies/localStorage to logs
- Distinctive: line 46
Wait for network idle or specific selector, not fixed sleeps
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Browser Agent Automation
Choose approach
| Approach | Best for |
| Playwright MCP | Existing Playwright tests; IDE agents |
| Browser-Use (Python) | Greenfield "do this on the site" tasks |
| Cursor IDE browser MCP | Interactive debugging in Cursor |
Default: Playwright MCP in Cursor; Browser-Use for standalone Python agents.
Safety rules
- Never automate login without explicit user consent in session
- Respect
robots.txtand site ToS for bulk scraping - Cap steps (e.g. 30 actions) and timeout per navigation
- Do not exfiltrate cookies/localStorage to logs
Workflow
- [ ] Define goal and success condition (URL, element, downloaded file)
- [ ] Start from known URL; avoid open-ended googling
- [ ] Use accessibility snapshots before clicks (prefer refs/roles)
- [ ] Verify after each critical action (screenshot or DOM check)
- [ ] On failure: one alternate strategy, then stop and reportPlaywright MCP (Cursor)
- List tabs → navigate → lock → snapshot
- Interact via dedicated browser tools (not raw CDP input)
- Unlock when done
Reliability patterns
- Wait for network idle or specific selector, not fixed sleeps
- Idempotent clicks: confirm state changed
- For forms: fill → validate → submit → verify confirmation text
Anti-patterns
- Brittle CSS selectors when role+name available
- Infinite retry loops on captcha/login walls
- Storing credentials in skill files or repo
Report blockers (captcha, 2FA) and ask user to take over.
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
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.