Automated exploratory bug hunting on web applications — explore, detect, and report bugs via browser automation
npx claudepluginhub williamfontaine/claude-plugins-marketplace --plugin qa-hunterUse this agent when the user wants to explore a running web application to find bugs. This agent navigates the app via browser automation, interacts with UI elements, monitors console and network for errors, and reports raw findings. <example> Context: User has a running web app and wants to find bugs. user: "Explore http://localhost:3000 and find bugs" assistant: "I'll launch the qa-explorer agent to navigate the app, interact with UI elements, monitor console and network errors, and report any bugs found." <commentary> User explicitly asks to explore a running app for bugs. The explorer agent will use browser tools to navigate, interact, and detect issues. </commentary> </example> <example> Context: User wants to test a specific feature in their web application. user: "Test the mandate creation flow on the portal" assistant: "I'll use the qa-explorer agent to systematically test the mandate creation flow — testing happy path, edge cases, and monitoring for errors." <commentary> Scope-guided exploration. The explorer focuses on a specific feature flow rather than the entire app. </commentary> </example> <example> Context: User wants to test the app with different user roles. user: "Hunt for bugs on the admin panel. I'll give you admin and regular user credentials." assistant: "I'll launch the qa-explorer agent to test the admin panel with both roles, checking for permission issues and role boundary violations." <commentary> Role-aware testing. The explorer tests with multiple credentials to find permission and authorization bugs. </commentary> </example>
Use this agent when raw QA findings need to be validated, filtered, and compiled into a structured bug report. This agent takes exploration results, removes false positives, verifies evidence, and produces a prioritized QA Bug Report. <example> Context: The qa-explorer agent has returned raw findings from a testing session. user: "Compile the bugs we found into a report" assistant: "I'll launch the qa-reporter agent to validate the findings, filter false positives, and compile a structured bug report with severity classification." <commentary> Raw findings exist from a previous exploration. The reporter validates, triages, and formats them into a clean report. </commentary> </example> <example> Context: User has a list of manually noted issues and wants a structured report. user: "I found several issues during manual testing, can you format them into a proper QA report?" assistant: "I'll use the qa-reporter agent to structure your findings into a standardized bug report with severity ratings and evidence." <commentary> User has informal findings that need professional formatting. The reporter applies severity classification and report structure. </commentary> </example> <example> Context: A QA exploration session has completed and the user wants the final output. user: "Generate the final bug report from this session" assistant: "I'll launch the qa-reporter agent to compile all findings into a prioritized bug report, filtering out false positives and duplicates." <commentary> End-of-session report generation. The reporter produces the definitive deliverable. </commentary> </example>
Use this skill whenever the user mentions QA, bug hunting, testing, quality assurance, exploratory testing, bug reports, severity classification, or wants to find bugs in a web application. Also use when the user says "test my app", "find bugs", "explore for issues", or asks about bug severity, test methodology, or report format. This is the foundational knowledge base for all qa-hunter testing work. When in doubt about whether QA testing principles apply, they do — load this skill.
Use this skill whenever the user wants to test a web application, needs a testing checklist, asks what to test, mentions form testing, navigation testing, console errors, network monitoring, i18n testing, accessibility testing in a QA context, or browser-based testing. Also use when the user says "test this page", "check for errors", "run through the checklist", or asks about edge cases to test. This skill provides the comprehensive testing checklists that qa-explorer agents use to systematically find bugs.
Battle-tested Claude Code plugin for engineering teams — 38 agents, 156 skills, 72 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement
AI-supervised issue tracker for coding workflows. Manage tasks, discover work, and maintain context with simple CLI commands.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.