By musingfox
Skills for browser automation with agent-browser CLI, Playwright test generation, and web debugging workflows
This skill should be used when the user asks to "browse a web page", "open a URL in the browser", "click an element", "fill a form field", "take a screenshot of a page", "inspect page elements", "get a page snapshot", "interact with a website", "automate a browser", "scrape a web page", "use agent-browser", or mentions the agent-browser CLI. Provides the ref-based browser automation workflow for AI agents.
This skill should be used when the user asks to "write a Playwright test", "create E2E tests", "add test assertions", "set up Playwright", "write a test spec", "use Playwright locators", "check element visibility", "test a web page", "fix a flaky test", "debug a failing Playwright test", or mentions Playwright, @playwright/test, E2E testing, browser testing, or test automation frameworks. Provides high-precision locator strategies and test structure guidance.
This skill should be used when the user asks to "debug a web page", "find what's wrong with this page", "investigate a UI bug", "figure out why this page is broken", "generate tests from debugging", "create regression tests for a page", "write E2E tests after exploring", "debug and write tests", "turn browser exploration into test cases", or when combining agent-browser exploration with Playwright test generation. Orchestrates the debug-to-test workflow.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub musingfox/cc-plugins --plugin agent-browserJujutsu (jj) VCS helper: workflow commands, natural language operations, and Git-to-jj translation
Fetch Apple Podcasts episode audio download URLs via iTunes API and RSS feeds
Contract-driven development pipeline with human-in-the-loop decision gating — agents defined by what they see, not who they are
One-stop hook setup assistant — detect project environment, generate Claude Code hooks and git pre-commit scripts with security checks, code quality gates, and CLAUDECODE skip logic
Interact with Fizzy via the Fizzy CLI — manage boards, cards, columns, comments, steps, reactions, tags, users, notifications, pins, webhooks, and account settings
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows.
Turn your coding agent into a SOTA browser agent. Drives a local Playwright workspace via one bash command at a time, saving screenshots and an action log into final_runs/run_<id>/, and visually self-verifies the result.
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script. Originally from OpenAI's curated skills catalog.
AI-powered browser automation -- lets Claude control real web browsers to navigate, click, type, extract content, and automate workflows
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.