Loading...
Loading...
Found 106 Skills
Autonomous design critique mode using the Agentation annotation toolbar. Use when the user asks to "critique this page," "add design annotations," "review the UI," "self-driving mode," "auto-annotate," or wants an AI agent to autonomously add design feedback annotations to a web page via the browser. Requires the Agentation toolbar to be installed on the target page and agent-browser skill to be available.
Use this skill to triage bugs found by Antithesis using the `agent-browser` skill to control a headless Chromium browser. If you are about to check run status, read property results, inspect findings, view environment images, or extract any information from the triage report — you MUST use this skill first. Covers runs page, run metadata (title, date, run/session IDs), property statuses (passed/failed/unfound), environment source images, findings, utilization metrics, and run logs.
Search Zhihu (知乎) using agent-browser with proper authentication handling. Use when user asks to "search zhihu", "知乎搜索", "在知乎上找", or any Zhihu-related search requests. Handles login requirements, session persistence, and common error cases like 40362 restrictions.
Private browser testing rules for jb workflows. Prefer playwrighter_exec with careful tab selection, fall back to agent-browser, and avoid playwright-mcp.
Diff-aware AI browser testing — analyzes git changes, generates targeted test plans, and executes them via agent-browser. Reads git diff to determine what changed, maps changes to affected pages via route map, generates a test plan scoped to the diff, and runs it with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, running regression checks on changed components, or validating that recent code changes don't break the user-facing experience.
agent-browser CLI로 Chrome Beta CDP에 연결하여 페이지 탐색, 데이터 확인, 요소 조작을 수행하는 스킬. "브라우저 확인", "페이지 봐줘", "DOM 확인", "데이터 점검", "클릭해줘", "화면 확인" 키워드로 트리거. E2E 시나리오 작성 중 셀렉터 확인이나 실행 실패 디버깅에도 사용한다.
Generate interactive presentation slides using React + Tailwind, and export to standalone single-file HTML. Triggers on keywords like "slides", "presentation", "PPT", "demo", "benchmark", or when user requests export. Uses agent-browser skill for browser verification before export (install with `npx skills add vercel-labs/agent-browser` if not available).
Scope coverage, build a testing strategy, test the feature with agent-browser, capture screenshots/video (always mandatory), upload to S3, and create a structured test report (never skip)
Use Tabbit with agent-browser by reading Tabbit's live DevToolsActivePort file, deriving the browser wsEndpoint, and routing browser actions through agent-browser --cdp.
Unified decision tree for web research and competitive monitoring. Auto-selects WebFetch, Tavily, or agent-browser based on target site characteristics and available API keys. Includes competitor page tracking, snapshot diffing, and change alerting. Use when researching web content, scraping, extracting raw markdown, capturing documentation, or monitoring competitor changes.
Use this skill whenever a user needs terminal-first browser automation with `steel browser`, asks to navigate/click/fill/snapshot/extract from websites, needs explicit browser session lifecycle control (`start`, `stop`, `sessions`, `live`), or wants to migrate `agent-browser` scripts. Trigger even when the user does not mention this skill by name and instead asks for multi-step web workflows, CDP attach behavior, local runtime setup, or browser automation troubleshooting.
Save a live webpage as a high-fidelity PDF that preserves the original layout AND every image (including lazy-loaded ones) using the agent-browser CLI. Use this whenever the user asks to "download this page as PDF", "save this article", "archive this URL", "fetch this page for reference", or otherwise wants a local PDF of a web page that looks like the browser version. Especially important on modern JS-heavy sites (engineering blogs, Next.js sites, anything with IntersectionObserver lazy loading) where naive `chrome --headless --print-to-pdf` or a bare `agent-browser pdf` produces blank rectangles or broken-image placeholders. Trigger this skill even when the user does not name the tool - any request to capture a webpage's full visual content as a PDF on disk should pull this in. For reader-mode/article-only output (no nav, no footer, no manual trimming) prefer percollate instead - see "When NOT to use this".