Agent skills for Cursor

Automate Chrome browser via DevTools Protocol.

Automates web browsers and Windows desktop applications for testing, scraping, and security research.

Extract structured data via stored browser-templates or one-shot DOM queries, with mandatory AIDefence PII + prompt-injection gates before…

Site-specific browser playbooks (domain-skills, interaction-skills) for Naver, GitHub, etc.

Use when opening or verifying any web page in Hermes.

Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features.

Cross-browser and cross-device testing using BrowserStack or Sauce Labs

Automate Browser Tool tasks via Rube MCP (Composio).

Reference for the Browser Use MCP tools — parameters, returns, session lifecycle.

Use this skill when the user wants to retrieve a URL without a full browser session: fetch HTML or JSON from static pages, inspect status…

Guide Claude through deploying serverless browser automation using the official bb CLI

Run tests on BrowserStack. Use when user mentions "browserstack", "cross-browser", "cloud testing", "browser matrix", "test on safari"…

Use when creating or configuring Claude Code agents and their frontmatter.

Autonomous research review loop using any OpenAI-compatible LLM API.

Audit and rewrite content to remove AI writing patterns ("AI-isms").

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command…

Document a recently solved research problem to compound methodological knowledge

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens.

Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop).

Compile LaTeX paper to PDF, fix errors, and verify output.