Verify behavior

Testing and QA skills for AI agents

Find skills that help agents generate tests, run browser checks, inspect failures, validate APIs, and keep product flows reliable.

Try this task

I need my agent to test a web app, reproduce bugs, and verify fixes.

16
Matched
16
Strong trust
1
Install ready
0
Auto allowed
16
500+ stars

Agent should be able to

  • +Run test suites
  • +Capture failures
  • +Report what changed after a fix

Resolve

Let the agent pick

Returns the best skill, alternatives, install handoff, risk summary, and safety gate.

Text plan

LLM-readable output

Plain text version for Codex, Claude Code, Cursor, and custom agent runtimes.

Browse

Human shortlist

Open the filtered registry view for this workflow and compare candidates manually.

Workflow map

What to build with these skills

01

Generate regression tests

02

Verify user flows

03

Debug failing checks

04

Validate API responses

Best first installs

Start with high-signal skills

16 matched skills

Use Playwright to interact with and test local web applications, capture screenshots, debug UI behavior, and inspect browser logs.

180K stars87 trust92 auditREVIEWED

Install

Agent install candidate

Risk

Safe to try

Agent fit

Claude Code + OpenAI Agents

Updated

Oct 9, 2026

$ npx skills add anthropics/skills --skill webapp-testing

Playwright

VERIFIED

Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.

91K stars87 trust89 auditREVIEWED

Install

Human review before install

Risk

Safe to try

Agent fit

Browser agents + Codex

Updated

Jun 19, 2026

$ npx skills add microsoft/playwright

Crawlee

VERIFIED

Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.

26K stars88 trust91 auditREVIEWED

Install

Human review before install

Risk

Safe to try

Agent fit

OpenAI Agents + Browser agents

Updated

Sep 10, 2026

$ npx skills add apify/crawlee

Skill shortlist

More options for this use case

Browse full marketplace

Crawlee Python

browser-automationCoding

Crawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Parsel, BeautifulSoup, Playwright, and raw HTTP. Both headful and headless mode. With proxy rotation.

Low metadata risk · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

9.5K stars86 trust91 audit71 safety

Browser Use

agent-frameworksCoding

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Review before production · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

99K stars85 trust88 audit72 safety

Puppeteer

coding-agentsCoding

JavaScript API for Chrome and Firefox

Review before production · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

95K stars85 trust88 audit72 safety

Implement

coding-agentsCoding

Implement work from an approved spec or ticket set, run focused and full tests, invoke code review, and commit the result to the current branch.

Review before production · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

176K stars87 trust90 audit78 safety

Grill With Docs

coding-agentsCoding

A relentless interview that pressure-tests a plan against the codebase, sharpens domain language, and updates CONTEXT.md and ADRs when decisions become durable.

Review before production · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

165K stars85 trust88 audit76 safety

Echarts

data-analysisData

Apache ECharts is a powerful, interactive charting and data visualization library for browser

Low metadata risk · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

67K stars89 trust91 audit75 safety

Hoppscotch

coding-agentsCoding

Open-Source API Development Ecosystem • https://hoppscotch.io • Offline, On-Prem & Cloud • Web, Desktop & CLI • Open-Source Alternative to Postman, Insomnia

Low metadata risk · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

80K stars84 trust88 audit64 safety

Scrapling

web-automationCoding

Adaptive web scraping for agent data collection

Review before production · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

70K stars83 trust88 audit72 safety

Act

github-automationCoding

Run your GitHub Actions locally 🚀

Review before production · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

71K stars87 trust89 audit77 safety

Page Agent

web-automationCoding

Control web interfaces with natural language agents

Review before production · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

29K stars83 trust88 audit72 safety

Bagisto

commerce-automationMarketing

Free and open source laravel eCommerce platform

Review before production · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

28K stars88 trust92 audit76 safety

Reverse Skill

developmentCoding

Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code, Kiro, Cursor, Cline, and other AI coding clients 逆向/渗透/安全技能路由包 - AI 自动路由 + 按需自举工具链 + 自动进化经验库 | 支持 Claude Code / Kiro / Cursor / Cline 等代码 AI 客户端

Low metadata risk · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

26K stars87 trust91 audit67 safety

Maxun

web-automationResearch

🔥 The open-source no-code platform for web scraping, crawling, search and AI data extraction • Turn websites into structured APIs in minutes 🔥

Low metadata risk · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

16K stars87 trust90 audit74 safety

FAQ

How to choose skills for this workflow

These answers are written for both human builders and agents consuming the Registry API.

What are the best AI agent skills for testing and qa?

Start by comparing Webapp Testing, Playwright, Crawlee. OpenAgentSkill ranks them by workflow fit, GitHub adoption, trust score, safety gate, and install readiness.

Can an AI agent use this page directly?

Yes. Use the linked Registry API prompt to query /api/skills/search with the task: "I need my agent to test a web app, reproduce bugs, and verify fixes." and retrieve install handoff links for the top results.

Should I install every recommended skill?

No. Start with the highest-fit skill, test it in a sandbox workflow, and add companion skills only when the task needs extra coverage.