Agent skills
Testing Claude skills and agent skills
What testing skills do
Drive a browser, write tests first, debug step by step and find bugs before review. A skill is a folder with a SKILL.md: the agent reads its one-line description up front and loads the instructions only when a task matches, so a testing skill costs almost nothing until you need it. The 14 here come from Anthropic, Vercel, OpenAI, Microsoft (Playwright), Trail of Bits, Microsoft (.NET), Browserbase, Sentry, Grafana Labs, Jesse Vincent (obra).
- Web App Testing · Anthropic
Toolkit for interacting with and testing local web applications using Playwright.
- Agent Browser · Vercel
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots,...
- Playwright Browser Automation · OpenAI
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`...
All testing & qa skills
14 of 14 skills
- Web App TestingOfficial · Anthropic
Uses Playwright to drive a local web app, check behavior, read console logs and take screenshots.
★ 184k (repo)
Install (any agent)Claude Code, Codex, Copilot, Cursor, Gemini CLI steps →npx skills add anthropics/skills --skill webapp-testing - Agent BrowserOfficial · Vercel
Drives a real browser from the command line to navigate, click, fill forms and screenshot pages.
★ 45k (repo)
Install (any agent)Claude Code, Codex, Copilot, Cursor, Gemini CLI steps →npx skills add vercel-labs/agent-browser --skill agent-browser - Playwright Browser AutomationOfficial · OpenAI
Automates a real browser from the terminal for form filling, snapshots, scraping and UI debugging.
★ 28k (repo)
Install (any agent)Claude Code, Codex, Copilot, Cursor, Gemini CLI steps →npx skills add openai/skills --skill playwright - Playwright CLIOfficial · Microsoft (Playwright)
Microsoft's skill for driving browsers and working with Playwright tests from the CLI.
★ 15k (repo)
Install (any agent)Claude Code, Codex, Copilot, Cursor, Gemini CLI steps →npx skills add microsoft/playwright-cli --skill playwright-cli - Property-Based TestingOfficial · Trail of Bits
Writes and debugs property-based tests with Hypothesis, fast-check, proptest and similar tools.
★ 7.8k (repo)
Install (any agent)Claude Code, Codex, Copilot, Cursor, Gemini CLI steps →npx skills add trailofbits/skills --skill property-based-testing - Analyze .NET PerformanceOfficial · Microsoft (.NET)
Scans .NET code for common performance anti-patterns in async, memory, LINQ and I/O.
★ 5.7k (repo)
Install (any agent)Claude Code, Codex, Copilot, Cursor, Gemini CLI steps →npx skills add dotnet/skills --skill analyzing-dotnet-performance - Browserbase BrowserOfficial · Browserbase
Controls a browser through CLI commands to browse sites, fill forms and extract data.
★ 3.7k (repo)
Install (any agent)Claude Code, Codex, Copilot, Cursor, Gemini CLI steps →npx skills add browserbase/skills --skill browser - Adversarial UI TestOfficial · Browserbase
Tests what changed in a git diff through a browser: functionality, accessibility, layout, UX.
★ 3.7k (repo)
Install (any agent)Claude Code, Codex, Copilot, Cursor, Gemini CLI steps →npx skills add browserbase/skills --skill ui-test - Find BugsOfficial · Sentry
Reviews the current branch's changes for bugs, security holes and quality problems.
★ 1.1k (repo)
Install (any agent)Claude Code, Codex, Copilot, Cursor, Gemini CLI steps →npx skills add getsentry/skills --skill find-bugs - k6 Load TestingOfficial · Grafana Labs
Writes and reviews k6 scripts for load, stress, soak and browser tests.
★ 290 (repo)
Install (any agent)Claude Code, Codex, Copilot, Cursor, Gemini CLI steps →npx skills add grafana/skills --skill k6 - Sentry Debug IssueOfficial · Sentry
Pulls a Sentry issue's stack trace, breadcrumbs and logs, fixes the code and resolves it.
★ 271 (repo)
Install (any agent)Claude Code, Codex, Copilot, Cursor, Gemini CLI steps →npx skills add getsentry/sentry-for-ai --skill sentry-debug-issue - Systematic DebuggingCommunity · Jesse Vincent (obra)
A root-cause-first process for bugs and failing tests before any fix is attempted.
★ 305k (repo)
Install (any agent)Claude Code, Codex, Copilot, Cursor, Gemini CLI steps →npx skills add obra/superpowers --skill systematic-debugging - Test-Driven DevelopmentCommunity · Jesse Vincent (obra)
Enforces a red-green-refactor loop: write a failing test first, then the code.
★ 305k (repo)
Install (any agent)Claude Code, Codex, Copilot, Cursor, Gemini CLI steps →npx skills add obra/superpowers --skill test-driven-development - Verification Before CompletionCommunity · Jesse Vincent (obra)
Requires running checks and showing their output before claiming work is done.
★ 305k (repo)
Install (any agent)Claude Code, Codex, Copilot, Cursor, Gemini CLI steps →npx skills add obra/superpowers --skill verification-before-completion
FAQ
What are testing agent skills?+
Drive a browser, write tests first, debug step by step and find bugs before review. Each is a SKILL.md folder that Claude Code, Codex, Cursor, Copilot and other agents load when a task matches its description. This page lists 14, from Anthropic, Vercel, OpenAI, Microsoft (Playwright), Trail of Bits, Microsoft (.NET), Browserbase, Sentry and others.
What are the best testing agent skills?+
Start with the ones from the publisher of the tool you use: Web App Testing (Anthropic), Agent Browser (Vercel), Playwright Browser Automation (OpenAI), Playwright CLI (Microsoft (Playwright)), Property-Based Testing (Trail of Bits), Analyze .NET Performance (Microsoft (.NET)).
How do I install a testing skill?+
Run npx skills add owner/repo --skill name and pick your agent, or copy the skill folder into ~/.claude/skills (Claude Code), .agents/skills (Codex) or .github/skills (Copilot). Each skill page has the exact command for Web App Testing and the rest.
More skills: Documents · Frontend & design · Backend & databases · Cloud & DevOps · Security & auth · AI & ML · Workflow & planning · Writing & notes · Media · Data & analytics · Mobile · Payments · Integrations · MCP servers