agentsclimarketplace
Sign in

Shelves Test

End to end & browser

1,372 rows from 441 repositories

Driving the real thing the way a user would.

What End to end & browser skills agree on

521 skill files read, by 499 of the 513 authors on this shelf whose files we hold, 2026-09-06

The middle one of the 60 measured here is ~1.4k tokens long, counted with cl100k_base

Counted by distinct author, so one author publishing three of these counts once. Where a claim sits in fewer files than authors, that is said: a claim held by forty authors across three files is one file people copied, not forty people who agreed. Near-identical wordings are grouped and the other wordings are shown, so the grouping is yours to check.

What they tell the agent to do

  1. Capture screenshots, videos, and traces on failure32 of 499 in 23 filesalso worded as capture screenshots and videos only on failure; Capture screenshots and traces on failure
  2. Close the browser when done22 of 499also worded as Close the browser when finished; Close browser sessions when done
  3. Interact with elements using snapshot refs21 of 499 in 20 filesalso worded as Take a snapshot before interacting with elements; Interact using refs from the latest snapshot
  4. Wait for specific network responses instead of fixed timeouts20 of 499 in 10 filesalso worded as wait for specific conditions instead of fixed timeouts; Wait for specific responses instead of fixed timeouts
  5. Keep tests independent with no shared state19 of 499 in 17 filesalso worded as Keep tests independent; Keep each test independent
  6. Use Page Object Model classes to encapsulate page interactions19 of 499 in 9 filesalso worded as use the Page Object Model to encapsulate interactions; Encapsulate page interactions in page object classes
  7. Locate elements with data-testid attributes19 of 499 in 10 filesalso worded as locate elements by data-testid attributes; Use data-testid attributes for selectors
  8. Quarantine flaky tests with fixme or skip17 of 499 in 7 filesalso worded as Quarantine known-flaky tests with skip markers; quarantine flaky tests with test.fixme
  9. Upload test artifacts after every CI run17 of 499 in 8 filesalso worded as Upload test artifacts from CI runs; Always upload the test report as a CI artifact
  10. Wait on conditions instead of using fixed sleeps17 of 499 in 13 filesalso worded as Wait for specific conditions, not fixed timeouts; Wait on explicit conditions instead of fixed sleeps
  11. Clean up test data after each test17 of 499 in 16 filesalso worded as create and clean up test data per test; Use unique test data or clean up after tests
  12. Test user-visible behavior, not implementation details16 of 499 in 10 filesalso worded as Test user behavior, not implementation details; test user behavior, not implementation
  13. Keep each test independent and deterministic16 of 499 in 15 filesalso worded as Keep each test isolated and independent; keep every test independent and parallel-safe
  14. Use auto-waiting locators instead of raw page clicks15 of 499 in 6 filesalso worded as use auto-waiting locators over direct page clicks; Use auto-waiting locators instead of raw clicks
  15. Detect running dev servers before writing test code14 of 499 in 11 filesalso worded as Detect dev servers before writing test code; Start the dev server before running tests

What they tell it not to do

  1. Don't share mutable state across tests30 of 499 in 21 filesalso worded as Sharing state between tests; Do not share state between tests
  2. Never use page.waitForTimeout()28 of 499 in 24 filesalso worded as Using waitForTimeout(); Never use waitForTimeout()
  3. Never use arbitrary fixed timeouts22 of 499 in 12 filesalso worded as Don't use arbitrary waitForTimeout delays; using arbitrary waitForTimeout delays
  4. Never use fixed sleeps for waiting14 of 499also worded as Do not use fixed sleep or waitForTimeout calls; Never use fixed sleep or waitForTimeout
  5. Never run financial flows against production12 of 499 in 4 filesalso worded as running financial flows against production; Never run tests against production
  6. Never use CSS class or XPath selectors12 of 499 in 9 filesalso worded as Never use CSS class or XPath selectors; Do not rely on CSS class selectors
  7. Never leave test.only enabled in CI11 of 499 in 3 filesalso worded as leaving test.only enabled in CI; Don't leave test.only in CI
  8. Never hardcode URLs11 of 499 in 9 filesalso worded as Hardcoded URLs; Never hardcode external URLs in tests
  9. Never write test files to the skill directory10 of 499 in 7 filesalso worded as never write test files into the skill directory
  10. Never click elements mid-animation10 of 499 in 4 filesalso worded as Don't click elements during animations; Never click mid-animation

What they expect to be installed

  1. Playwright168 of 499 in 161 files
  2. npx playwright test74 of 499 in 64 files
  3. curl48 of 499
  4. npm44 of 499 in 40 files
  5. Cypress39 of 499 in 33 files
  6. git36 of 499
  7. GitHub Actions34 of 499 in 24 files
  8. Vitest33 of 499 in 28 files
  9. playwright-cli33 of 499 in 32 files
  10. Chromium31 of 499 in 28 files

What they ask it to produce

  1. Page object classes49 of 499 in 38 filesalso worded as Page object files; Page object classes per screen
  2. playwright.config.ts46 of 499 in 40 filesalso worded as Playwright config; playwright.service.config.ts
  3. E2E spec files32 of 499 in 27 filesalso worded as E2E test files; E2E test spec files
  4. Screenshots29 of 499 in 28 filesalso worded as screenshot files; Screenshot images
  5. Failure screenshots28 of 499 in 18 filesalso worded as screenshots on failure; Failure screenshot on test failure
  6. Markdown test report26 of 499 in 17 filesalso worded as Markdown E2E test report; Test report markdown file
  7. HTML test report25 of 499 in 16 filesalso worded as HTML report
  8. Page PDFs18 of 499 in 16 filesalso worded as page PDF file; PDFs

When End to end & browser authors say to reach for one

The situations these authors wrote into their own files, counted out of the same 499 authors, with the skills that name each one

How End to end & browser skills are built

1,241 skill directories by 406 authors, read from their repositories’ own file trees 2026-08-05

The middle bundle among those shipping files is 3 files, 19.5 KB beside SKILL.md

Counted by distinct author, same as above, so one author publishing forty template copies counts once. SKILL.md itself is not counted as a file, so a single-file skill is one where that file is the whole skill.

The shape

  1. SKILL.md is the whole skill147 of 406 authors, 534 of 1,241 skills
  2. files ship beside it259 of 406 authors, 707 of 1,241 skills
  3. executable scripts ship inside113 of 406 authors, 195 of 1,241 skills

The folders they converge on

  1. references/163 of 406 authors, 264 of 1,241 skills
  2. scripts/82 of 406 authors, 139 of 1,241 skills
  3. agents/42 of 406 authors, 124 of 1,241 skills
  4. assets/41 of 406 authors, 67 of 1,241 skills
  5. evals/21 of 406 authors, 32 of 1,241 skills
  6. examples/21 of 406 authors, 29 of 1,241 skills

  • Playwright mcp

    microsoft/playwright-mcp/io.github.microsoft/playwright-mcp MCP server

    in 1 stack36,126★ repo

    Playwright Tools for MCP

  • Playwright skill

    lackeyjb/playwright-skill/skills/playwright-skill Skill

    3,026★ repo

    Claude Code Skill for browser automation with Playwright. Model-invoked - Claude autonomously writes and executes custom automation for testing and validation.

  • Configure

    SponsioLabs/Sponsio/plugins/sponsio-claude-code/skills/configure Skill

    445★ repo

    Deterministic safety solutions for probabilistic AI agents

  • Playwright skill

    testdino-hq/playwright-skill Skill

    349★

    TestDino Playwright Skill: AI-powered guides for Playwright best practices, made by testdino.com.

  • Activitypub testing

    Microck/ordinary-claude-skills/skills_all/activitypub-testing Skill

    no license324★ repo

    An unappealing collection of Claude Skills and resources.

  • Travel guidebook

    geekjourneyx/travel-guidebook Skill

    75★

    AI agent skill that generates beautifully typeset travel guidebook PDFs — from research to print, powered by parallel agents and Amap MCP.

  • Accessibility testing

    petrkindlmann/qa-skills/skills/accessibility-testing Skill

    70★ repo

    50 QA and test-automation skills for Claude Code, Codex, Cursor, and any Agent Skills Standard runtime.

  • Cypress author

    cypress-io/ai-toolkit/skills/cypress-author Skill

    38★ repo

    Fast, flexible, and open tooling for building intelligent workflows with Cypress.

  • Browsing with playwright

    mjunaidca/mjs-agent-skills/.claude/skills/browsing-with-playwright Skill

    no license27★ repo

    A curated collection of Agent Skills — reusable units of intelligence that teach AI General Agents how to perform specific tasks autonomously.

  • Skills

    alex-feel/claude-code-toolbox/tests/e2e/fixtures/mock_repo/skills Skill

    16★ repo

    Claude Code Toolbox — automated installers and environment configuration framework for Claude Code with one-line setup across Windows, macOS, and Linux.

  • Does it work

    TsakunovR/does-it-work Skill

    10★

    Claude Code / Codex skill: проверяет, что ваш продукт реально работает — находит баги и строит защиту от регрессий автотестами

  • Cypress debugger

    voidmatcha/e2e-skills/skills/cypress-debugger Skill

    9★ repo

    AI agent testing toolkit for Playwright and Cypress: generate E2E tests from scratch, review existing specs against 24 anti-patterns (P0/P1/P2 silent-always-pass smells), and debug flaky failures from playwright-report/ or cypress/reports/. Agent Skills for Claude Code and Codex.

  • Periscope mcp

    segentic-lab/periscope-mcp/io.github.segentic-lab/periscope-mcp MCP server

    8★ repo

    Web-app QA for AI agents: 73 Playwright tools — auth, E2E, a11y/SEO/GEO, Web Vitals + Lighthouse

  • Playwright auth state

    hzijad/playwright-agent-skills/skills/playwright-auth-state Skill

    6★ repo

    Playwright skills for writing, reviewing, and debugging reliable end-to-end tests.

  • Browsing with playwright

    sheikh-mohammad/agent-factory-claude-skills/.claude/skills/browsing-with-playwright Skill

    no license6★ repo

  • Android emulator harness

    simiancraft/simiancraft-skills/skills/android-emulator-harness Skill

    6★ repo

    Public Claude Code skills and agents from simiancraft. Marketplace-installable.

  • Selenium mcp

    pshivapr/selenium-mcp/io.github.pshivapr/selenium-mcp MCP server

    6★ repo

    Selenium Tools for MCP

  • Agent browser

    vanducng/skills/skills/agent-browser Skill

    5★ repo

    A daily-driver collection of skills for agentic coding — a portable, agent-agnostic catalog managed with the vd CLI.

  • Playwright skill

    appautomaton/playwright-skill Skill

    no license5★

    Android-friendly Playwright SKILL for AI agents — Termux launcher patch, headless Chromium, install via git subtree into .codex/skills.

  • Clerk claude skill

    wrsmith108/clerk-claude-skill Skill

    4★

    Claude Code skill for Clerk authentication patterns

  • Cypress agent skill

    KahlilR23/cypress-agent-skill Skill

    3★

    Cypress E2E testing skill for AI agents — Claude Code, Codex, OpenClaw, Cursor, and more. Covers selectors, network stubbing, auth, CI, flake prevention, POM, and TypeScript. Cypress 15.x compatible.

  • E2e runner

    fastslack/mtw-e2e-runner/io.github.fastslack/e2e-runner MCP server

    3★ repo

    JSON-driven E2E test runner with parallel Chrome pool execution and 16 MCP tools.

  • Skills

    2389-research/scenario-testing/skills Skill

    2★ repo

    End-to-end testing with real dependencies - no mocks allowed; scenarios with real data are the only source of truth

  • Skill

    netopsengineer/agent-skill-description-optimizer/tests/e2e/skill Skill

    2★ repo

    Optimizes the description frontmatter of a Claude Code / Agent Skill - the text that decides whether Claude invokes the skill. Both halves of the loop (evaluation and improvement) run entirely through the `claude -p` CLI, so no `ANTHROPIC_API_KEY` is required.

  • Tester

    erikfiala/e2e-tester/.cursor/skills/tester Skill

    2★ repo

    Reusable /tester skill for Playwright + Lighthouse e2e audits with light/dark and desktop/mobile coverage plus 100/100 gap analysis.

  • Bdd

    danielsogl/skills/skills/bdd Skill

    2★ repo

    Personal collection of Anthropic Agent Skills with capability + trigger evals — currently: ngrx-signals (Angular Signal Store, +16pp pass rate vs baseline)

  • Test e2e

    knowhowlab/agent-testkit/skills/test-e2e Skill

    2★ repo

    Universal E2E & manual acceptance testing skills for Claude Code — every run writes a protocol

  • Playwright enterprise tester

    lopadova/playwright-enterprise-tester/skills/playwright-enterprise-tester Skill

    1★ repo

    Writing and run Enterprise-grade E2E tests automatically with claude and Playwright

  • E2e test plan

    cacaoapps/e2e-test-plan Skill

    1★

  • Local e2e

    aitit-inc/leadace/.claude/skills/local-e2e Skill

    no license1★ repo

    Outbound sales, autopiloted.

  • Playwright scout

    Zenolitee/playwright-scout Skill

    1★

    Deterministic Playwright QA scout and AI-agent skill that crawls web apps and generates Playwright tests.

  • Playwright skill

    jovd83/playwright-skill Skill

    1★

    End-to-end Playwright skill pack for planning, authoring, debugging, documenting, and operationalizing test automation.

  • Browsing with playwright

    Eng-Muhammad-Affan/digital-fte/.qwen/skills/browsing-with-playwright Skill

    no license1★ repo

    Personal AI agent that handles social media as well as any social media

  • E2e testing

    magallon/testing-toolkit/e2e-testing Skill

    1★ repo

    Stack-agnostic testing skills for AI agents — testing strategy, prioritization, and E2E browser automation

  • Mission control 3d visual regression

    MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-3d-visual-regression Skill

    1★ repo

    An Open Source Platform For Building Projects With OpenAI's Codex, Claude CLI, And Other Coding LLMs Using Multi-Agent Swarms And Customizable Workflows. Runs On Windows, MacOS, And Linux.

  • Qa testing kit

    SoftwareOneHN/qa-testing-kit Skill

    1★

    🧪 QA Testing Kit — lifecycle-driven Agent Skill for manual & automation testing. Playwright, Selenium, Appium. Generate test cases, automation scripts, locators, test data & flaky analysis. Compatible with Claude Code, Cursor, Kiro, and 40+ agentic clients.

  • Pw playwright fieldkit

    jpbaking/playwright-fieldkit/skills/shared/pw-playwright-fieldkit Skill

    1★ repo

    Playwright FieldKit: gives coding agents hands and eyes on the web — crawl, debug, record, and test live sites via deterministic scripts; portable Agent Skill for Codex, Claude Code, Antigravity, and Cline

  • Playwright network chaos mcp

    vola-trebla/playwright-network-chaos-mcp/io.github.vola-trebla/playwright-network-chaos-mcp MCP server

    1★ repo

    MCP server that gives AI agents dynamic network chaos control over Playwright browser sessions

  • Playwright trace decoder mcp

    vola-trebla/playwright-trace-decoder-mcp/io.github.vola-trebla/playwright-trace-decoder-mcp MCP server

    1★ repo

    MCP server for unpacking and analyzing Playwright trace.zip archives

  • Mtg argentina playwright

    rodrijuarez/mtg-argentina-skills/mtg-argentina-playwright Skill

    0★ repo

    Claude Code skills for shopping MTG sealed product in Argentina — store lookup, full-catalog scraping, ARS/USD price verification

  • Annotate ask playwright

    BarclayII/browser-annotator-skills/skills/annotate-ask-playwright Skill

    0★ repo

    Browser annotation and question-answering skills for Claude Code

  • Selenium java skill

    MrRahulR/selenium-java-skill Skill

    no license0★

    A Claude Code skill providing expert-level guidance for Selenium WebDriver with Java. Includes templates and best practices for enterprise-grade browser automation.

  • Claude

    vasyafomiuk/skills/java-playwright-cucumber-e2e/1.0/claude Skill

    0★ repo

    Claude Code skill plugin marketplace — java-playwright-e2e: Java + Playwright + Cucumber (BDD) end-to-end test automation

  • Contract test writer

    SkillMedev/qa-test-automation/skills/contract-test-writer Skill

    0★ repo

    Build a test suite that actually catches bugs — and stops flaking.

  • Anti test theater

    nanami7777777/anti-test-theater Skill

    0★

    Stop AI agents from writing useless tests. Decision trees for mocking, test layering, and requirement-driven testing that catches real bugs.

  • Playwright skill

    up1/demo-api-testing-with-playwright-skill/.agents/skills/playwright-skill Skill

    no license0★ repo

    API testing with Playwright Skill

  • Cypress skill

    jovd83/Cypress-skill Skill

    0★

    End-to-end Cypress skill pack for planning, authoring, debugging, documenting, and operationalizing test automation.

  • Goose gui e2e

    Miyamura80/MCP-Template/.agents/skills/goose-gui-e2e Skill

    0★ repo

    🏵️ MCP Server with CLI interface ready for distribution

  • E2e testing methodology

    tianchong1980/e2e-testing-methodology Skill

    no license0★

  • Api test skill

    fxckcode/skills-kit/skills/api-test-skill Skill

    0★ repo

    A collection of agent skills for repository setup, multi-CLI agent workflows, and intelligent context loading.

  • Pre refined skill

    barryroodt/refine-skill/e2e/fixtures/pre-refined-skill Skill

    0★ repo

    Refine an Agent Skill via the skill-forge judge → hitl loop, in a sandboxed Docker container. npx-installable.

  • Agent browser guide

    heart-wcl/agent-browser-guide Skill

    0★

    Claude Code skill for browser automation via Vercel Agent Browser CLI. Replaces Playwright MCP with CLI-first approach.

  • Test gen

    ZaneL1u/test-generate-skills/skills/test-gen Skill

    0★ repo

    Agent skills to decide, generate, and set up frontend tests (unit vs e2e). Framework-agnostic, installable via npx skills add.

  • Prod playwright audit

    nahuelsoria/prod-playwright-audit Skill

    no license0★

    Cross-agent skill (Claude Code, Codex, Cursor, opencode): safely audit critical flows of a deployed web app with Playwright — never mutates production data

  • Agent ready ui

    dvnc-labs/agent-ready-ui Skill

    0★

    Make web UIs controllable by browser agents without brittle selectors.

  • Skill

    raphaelbleier/userstory-playwright-skill/skill Skill

    0★ repo

    Point your coding agent at a website codebase: it writes user stories into Excel, tests them with Playwright, and writes the bugs back. Works with Claude Code, Codex, Kilo Code, OpenCode and GitHub Copilot CLI.

  • E2e secondary

    game-dev-rta-club/gh-skill-linker/.test-fixtures/skills/e2e-secondary Skill

    0★ repo

    GitHub CLI extension to link project-local Agent Skills to explicit, versioned GitHub sources on macOS and Linux.

  • App verify

    nikhilkyn-png/app-verify Skill

    0★

    Claude Code skill: exploratory smoke-sweep + deploy verification for running/deployed web apps. Catches bugs that pass typecheck and return 200 but are wrong (dead DB columns, silent query failures, fake stats).

  • Playwright e2e

    alsovdev/playwright-e2e Skill

    no license0★

    testing skill

  • Playwright mcp

    dinesh-nalla-se/playwright-mcp/io.github.dinesh-nalla-se/playwright-mcp MCP server

    0★ repo

    Playwright Tools for MCP

All 1,372 in the catalog