By kellymears
Browser automation for web testing, form filling, screenshots, and data extraction.
Claude Code plugin marketplace — git workflows, research, writing, browser automation, and more.
Add the marketplace, then install plugins by name:
/plugin marketplace add kellymears/agents
/plugin install git@kellymears
| Plugin | Description |
|---|---|
git | Commit curation, PR creation, issue filing, and context switching |
research | Deep-dive multi-source research with cited evidence |
comms | Draft emails, Slack messages, blog posts in your voice |
playwright-cli | Browser automation for testing and data extraction |
sim | Progressive assessments and live pair programming challenges |
sprint-worker | Batch-process GitHub issues with parallel agents |
tdd | Red-green-refactor TDD cycle |
obsidian | Write notes to Obsidian vaults (configurable path) |
hud | Real-time statusline HUD for monitoring |
cli | CLI design best practices — argument design, help text, output formatting |
ink | Best practices for building terminal UIs with Ink (React for CLIs) |
guardrails | Code quality hooks for safe, consistent workflows |
The site/ directory contains a Next.js + MDX documentation site with page-based routing for plugin and skill detail views.
cd site && npm install && npm run dev
| Route | Description |
|---|---|
/plugins | Plugin listing |
/plugins/[name] | Plugin detail — skills, commands, install |
/plugins/[name]/skills/[skill] | Skill detail — SKILL.md, reference files, file tree |
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 kellymears/agents --plugin playwright-cliCode quality hooks — auto-formatting, linting, file protection, context recovery, and subagent orientation.
Red-green-refactor TDD cycle — write a failing test, make it pass, clean up.
Batch-process GitHub issues using parallel agents.
Real-time statusline for Claude Code — context health, tool activity, agent tracking, and todo progress.
Best practices for building terminal UIs with Ink (React for CLIs).
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.
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.
Claude Code Skill for general-purpose browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp, and autonomously handles any browser automation task.
Browser automation skill for Claude Code using Stagehand. Automate web interactions, extract data, and navigate websites using natural language.
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.
Browser automation via Playwright CLI for testing, screenshots, and interaction workflows