mgiovani/ai-arsenal / skills/agent-browser
agent-browser
VerifiedHeadless browser automation CLI optimized for AI agents: drives a real browser via accessibility-tree snapshots and @e1-style refs for ~93% less context than raw DOM tools. Use whenever a task needs to interact with a live web page: click, fill forms, log in, extract text or data, take screenshots, test a running web app, or scrape a site. Triggers on 'automate the browser', 'fill this form', 'click the button', 'take a screenshot of the page', 'log into', 'scrape this site', 'test my web app', 'headless browser'. Not for Playwright test-suite authoring or CDP/service-worker work needing the full JS API: use Playwright directly. Not for driving the user's own already-open, logged-in Chrome tab: use claude-in-chrome for that.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.5 KB |
| evals/evals.json | config | 5.1 KB |
| evals/trigger-eval.json | config | 2.2 KB |
| references/advanced.md | markdown | 29.0 KB |
| references/commands.md | markdown | 21.5 KB |
| references/workflows.md | markdown | 17.1 KB |
evals/trigger-eval.json
View on GitHub[
{"query": "can you fill out this login form on staging.myapp.com and log in for me", "should_trigger": true},
{"query": "take a screenshot of the pricing page on our site", "should_trigger": true},
{"query": "click through the signup flow and tell me if it works", "should_trigger": true},
{"query": "scrape the product titles and prices off this ecommerce site", "should_trigger": true},
{"query": "I need to test my running web app - add to cart then checkout", "should_trigger": true},
{"query": "automate logging into this dashboard with 2FA", "should_trigger": true},
{"query": "extract all the links from this page for me", "should_trigger": true},
{"query": "check if the submit button is disabled after I fill the form wrong", "should_trigger": true},
{"query": "navigate to example.com and grab the page title and url", "should_trigger": true},
{"query": "record a video of the checkout flow so I can show the team", "should_trigger": true},
{"query": "run a headless browser against this URL and tell me what's on the page", "should_trigger": true},
{"query": "write a Playwright test suite for our checkout flow with CI integration", "should_trigger": false},
{"query": "use claude-in-chrome to click the button in my open Chrome tab", "should_trigger": false},
{"query": "click the submit button in the Chrome tab I already have open and logged into", "should_trigger": false},
{"query": "debug why our service worker isn't caching requests with CDP", "should_trigger": false},
{"query": "fix the bug where the login form throws a 500 on empty password", "should_trigger": false},
{"query": "review this PR that touches the checkout module", "should_trigger": false},
{"query": "write unit tests for the discount code validation logic", "should_trigger": false},
{"query": "our existing Playwright tests are flaky, help me stabilize them", "should_trigger": false},
{"query": "explain how OAuth device emulation works in general", "should_trigger": false},
{"query": "set up a GitHub Actions workflow to run our test suite on push", "should_trigger": false},
{"query": "refactor this API client to remove duplicated fetch calls", "should_trigger": false}
]
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |