6 min read
Browser Testing Skills
Browser testing skills separate deterministic regression tests from visual QA, live browser inspection, screenshots, and local verification. Source: Skill Registry, 2026-09-25
When To Use This
Use this family for Playwright, screenshots, local verification, visual QA, browser automation, desktop app checks, and rendered proof.
Core Model
Executable behavior lives in skills/**/SKILL.md. This page owns family-level routing, tradeoffs, and failure modes. Exhaustive inventory lives in Skill Registry. Full retired article bodies live in Retired Skill Article Ledger.
Concept Position
| Axis | Value |
|---|---|
| Family | Generated skill-family synthesis |
| Concept owned | Browser testing skills separate deterministic regression tests from visual QA, live browser inspection, screenshots, and local verification. |
| Operationalizes into | Skill Registry, Skill Resolver, executable SKILL.md source |
| Use this page when | choosing the right skill family before loading executable source |
Decision Matrix
| Need | Route |
|---|---|
| Use Playwright for repeatable assertions. | Load the named SKILL.md from Skill Registry and use this page for context. |
| Use browser-harness or agent-browser for exploratory rendered inspection. | Load the named SKILL.md from Skill Registry and use this page for context. |
| Keep browser automation separate from agent search or docs lookup. | Load the named SKILL.md from Skill Registry and use this page for context. |
Do Not Confuse
- Browser automation is not the same as localhost testing.
- Agent search/retrieval is a different capability family.
Tool And Skill Routing
| Skill | Category | Origin | Executable source | Trigger signal |
|---|---|---|---|---|
| agent-browser | engineering | personal | skills/engineering/agent-browser/SKILL.md | Default browser automation surface for Kevin's agents. Use when automating browsers, opening sites, scraping pages, filling forms, taking screenshots, testing UIs, extracting data, checki... |
| babylonjs-engine | engineering | personal | skills/engineering/babylonjs-engine/SKILL.md | Comprehensive skill for Babylon.js 3D web rendering engine. Use this skill when building real-time 3D experiences, browser-based games, interactive visualizations, or immersive web applic... |
| beta-dx-walk | engineering | personal | skills/engineering/beta-dx-walk/SKILL.md | Agent-led beta DX/UX readiness walk. Walk a product's critical user journeys as a skeptical first-time user and treat friction as a bug: anything that makes the user pause, guess, reread,... |
| browser-use | engineering | personal | skills/engineering/browser-use/SKILL.md | Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take scr... |
| core-web-vitals | engineering | personal | skills/engineering/core-web-vitals/SKILL.md | Optimize Core Web Vitals (LCP, INP, CLS) for better page experience and search ranking. Use when asked to "improve Core Web Vitals", "fix LCP", "reduce CLS", "optimize INP", "page experie... |
| dcs-test | engineering | dedalus | skills/engineering/dcs-test/SKILL.md | Run DCS test profiles against controlplane (Go), host-agent (Rust), storage-daemon, or live clusters. Use when testing DCS changes locally or triggering CI test suites. |
| dogfood | engineering | personal | skills/engineering/dogfood/SKILL.md | Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this... |
| electron | engineering | personal | skills/engineering/electron/SKILL.md | Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electr... |
| gstack-qa | engineering | personal | skills/engineering/gstack-qa/SKILL.md | QA lead with real browser testing. Tests your app, finds bugs, fixes them with atomic commits, generates regression tests. Use when the user says "QA", "test this", "find bugs", "explorat... |
| human-review | productivity | unknown | skills/productivity/human-review/SKILL.md | Open a local HTML file, rendered Markdown document, or localhost page for the user to edit and annotate directly, then apply one durable feedback batch to source. Use when the user asks t... |
| implicit-cad | engineering | external | skills/engineering/implicit-cad/SKILL.md | Create, edit, render, and snapshot browser-native implicit CAD .implicit.js and .implicit.mjs files using GLSL signed-distance fields, shader primitives, smooth booleans, TPMS fields,... |
| pdf-operations | productivity | personal | skills/productivity/pdf-operations/SKILL.md | Route and execute private PDF work. Use when Kevin asks to read, search, merge, split, reorder, compress, convert, OCR, sign, redact, secure, edit, batch, or automate PDF files. Uses pdf-... |
| playcanvas-engine | engineering | personal | skills/engineering/playcanvas-engine/SKILL.md | Lightweight WebGL/WebGPU game engine with entity-component architecture and visual editor integration. Use this skill when building browser-based games, interactive 3D applications, or pe... |
| playwright | engineering | personal | skills/engineering/playwright/SKILL.md | Use for committed Playwright regression tests, existing Playwright suites, CI browser gates, traces for reproducible failures, and explicit user requests to write or run Playwright test f... |
| screenshot | engineering | personal | skills/engineering/screenshot/SKILL.md | Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable a... |
| spline-interactive | engineering | personal | skills/engineering/spline-interactive/SKILL.md | Browser-based 3D design tool with visual editor, animation, and web export. Use this skill when creating 3D scenes without code, designing interactive web experiences, prototyping 3D UI,... |
| ui-vocabulary | engineering | personal | skills/engineering/ui-vocabulary/SKILL.md | Identify an unfamiliar UI element or visual style from a plain-language description, screenshot, rendered page, accessibility tree, DOM, or code clue; rank the real names, distinguish con... |
| vitest | engineering | skills-sh | skills/engineering/vitest/SKILL.md | Vitest fast unit testing framework powered by Vite with Jest-compatible API. Use when writing tests, mocking, configuring coverage, or working with test filtering and fixtures. |
| vue | engineering | skills-sh | skills/engineering/vue/SKILL.md | Use for Vue ecosystem work: Vue, Vue Router, Vue testing, VueUse, Pinia, Nuxt, Nitro, and Slidev. Confirm installed versions and project conventions before applying examples. |
| webapp-testing | engineering | personal | skills/engineering/webapp-testing/SKILL.md | Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and view... |
| webwright | engineering | external | skills/engineering/webwright/SKILL.md | Solve a user-specified web task code-as-action style by driving a local Playwright browser through one bash command at a time, saving screenshots and an action log into `final_runs/run_<i... |
Failure Modes
- Confusing browser automation with deterministic test coverage.
- Skipping console/network inspection.
- Treating screenshots as proof when an assertion is needed.
Timeline
- 2026-09-25 | Regenerated this concise family synthesis page from Skill Registry after archiving verbose retired skill-article bodies to Retired Skill Article Ledger. Source: User request, 2026-06-27
- 2026-09-25 | Concepts category refresh linked this generated family page to Concept System Map and kept it generated because executable skill source owns the procedure details. Source: User request, 2026-07-01
Related Pages
98 pages link here
Actionable Tools IndexToolsActive Stack (What to Actually Use)MetaAgent Browser -- Browser Automation for AgentsToolsAgent Cookie - Session State Sync for the Agent's Second MacToolsAgent Environment Setup ArchitectureArchitectureAgent Iteration LoopConceptsAgent LoopingConceptsAgent MachinesProjectsAgent Operating SystemArchitectureAgent Operations HubMetaAgent Reach - Internet Access for AgentsToolsagent-browserSkillsAgent-Docs MeshConceptsAgent-Native CLIsConceptsAgentic Quality SystemConceptsAutobrowse (Browserbase Skills)Toolsbabylonjs-engineSkillsBeta DX Walk (Friction Is a Bug)Conceptsbeta-dx-walkSkillsBorrowed Intelligence (Drain It into Plans)ConceptsBrowse.sh (Browserbase Skills)ToolsBrowser Automation and QAConceptsBrowser Automation RoutingSkill ResolverBrowser Harness - Self-Healing Browser AutomationToolsBrowser to APIToolsBrowser Use (Framework)ToolsBrowser Use Box (Bux)Toolsbrowser-useSkillsBrowserbase Browse.sh (Open Web Catalog)ToolsBrowserbase EcosystemToolsBud - AI Human EmulatorToolsCamofox BrowserToolsCapability Routing MapMetaChris TatePeopleComplementary Browser TestingConceptsComputer Use and Browser Automation PatternsConceptsConcept System MapConceptscore-web-vitalsSkillsCSS UI EnforcementStyledcs-testSkillsDedalus E2E Tiered TestingWorkflowsDedalus LabsProjectsDefuddle - Web Content ExtractionToolsdogfoodSkillsego-liteToolselectronSkillsFFF (Fast File Find)ToolsFirecrawlToolsFrontend Frontier Radar WorkflowWorkflowsGitHub Starred Repos Harvest - 2026-06-28Researchgstack-qaSkillsHermes Mac Mini Agent OSArchitecturehuman-reviewSkillsimplicit-cadSkillsLighthouse Agentic Browsing AuditToolsLightpandaToolsLive Process AuditingConceptsLocal Search CLIProjectsLocal Web VerificationConceptsMCP as the Integration StandardConceptsNative SDK (formerly Zero Native)Toolspdf-operationsSkillsPixelRAGToolsplaycanvas-engineSkillsplaywrightSkillsPortlessToolsQA Testing RoutingSkill ResolverRecordlyToolsRetired Skill Article LedgerMetascreenshotSkillsShopifyToolsSkill RegistryMetaSkill ResolverSkill ResolverSkill Sync WorkflowWorkflowsSlash Command IndexMetaspline-interactiveSkillsStaying in the Loop with AgentsConceptsTailnet Agent Mesh - Reaching Your Agents from AnywhereConceptsThe Eval Loop (Slop Is an Output Problem)ConceptsTikTok ScraperToolsTransitions.devToolsui-vocabularySkillsVideo UseToolsvitestSkillsvueSkillsWeb Scraping Stealth (TLS Fingerprinting & Anti-Bot Evasion)Conceptswebapp-testingSkillsWebsite Cloner SkillToolswebwrightSkillsWebwrightToolsWiki Capsules And Agent Doc PacksMetaWiki Redirect IndexMetaX Bookmark Ingest 2026-06-28ResearchX Bookmark Ingest 2026-07-06ResearchX Bookmarks: AI Agents & Tools (Jan 2025 – Jun 2026)ToolsX Bookmarks: Dev Tools (Mar–Jun 2026)ToolsYC AI StackToolsZero (Programming Language)Tools