Skip to content
Get packs

Testing & QA agent skills

206 skills that teach Claude and other agents testing & qa work, from the most-starred GitHub repositories first. Each page explains what the skill does, who it suits, what it needs, and how to install it.

Building skills & agentsCreative & mediaData & analysisDesign & front-endDevOps & cloudDevelopmentDocuments & officeMarketing & contentProductivity & opsResearchSecurityWriting & communication
  1. 1REA CI and Tests Audit · rea-ci-tests-auditAudits REA's CI workflows and test suites for false passes, fixture drift, and safe speedups
  2. 2Test-Driven Development · test-driven-developmentMakes the agent write a failing test before any feature, bugfix, or behavior change code.
  3. 3Verification Before Completion · verification-before-completionMakes the agent run real checks and show evidence before saying work is done or passing
  4. 4Migrate to Shoehorn · migrate-to-shoehornSwap risky `as` type casts in TypeScript tests for type-safe shoehorn helpers.
  5. 5Playwright E2E Testing Patterns · e2e-testingWrite stable, maintainable Playwright browser tests and fix flaky ones in CI
  6. 6Module Regression Ledger · module-regressionChecks that changing one module doesn't silently break the modules that depend on it.
  7. 7Test Collaboration Governance · test-collaborationTrack a project's tests, required coverage, and bug-regression evidence in one registry
  8. 8Verification Loop · verification-loopRuns build, type, lint, test, security and diff checks before a Claude Code session claims work is done
  9. 9C++ Testing Workflow · cpp-testingGuides the agent through writing, fixing and debugging C++ tests with GoogleTest and CTest
  10. 10Kotlin Testing Patterns · kotlin-testingWrite Kotlin tests with Kotest, MockK, coroutine testing, property tests and Kover coverage
  11. 11End-to-End Testing with Playwright · e2e-testingWrite stable, maintainable browser E2E tests with Playwright, including flaky-test handling and CI setup
  12. 12Laravel Verification Loop · laravel-verificationRuns a full pre-PR and pre-deploy check sequence on a Laravel project: env, lint, tests, audit, migrations, queues.
  13. 13Python Testing Patterns · python-testingGuides an agent through pytest tests, TDD, fixtures, mocking and coverage targets in Python projects.
  14. 14Quarkus TDD Workflow · quarkus-tddGuides an agent to write failing tests first for Quarkus 3.x services, including Camel routes
  15. 15Verification Loop · verification-loopRuns build, type, lint, test, security and diff checks on a Claude Code session before a PR
  16. 16Agent Eval (コーディングエージェント比較) · agent-evalCompare coding agents like Claude Code, Aider and Codex head-to-head on your own tasks with pass rate, cost and time metrics
  17. 17AI Regression Testing · ai-regression-testingWrite sandbox-mode API tests and bug-check workflows that catch bugs AI reviewers miss
  18. 18Performance Benchmark · benchmarkMeasures page, API, and build speed, and flags regressions before and after changes.
  19. 19Browser QA Testing · browser-qaHas the agent test a live web page like a real user: clicks, forms, layout, and accessibility checks
  20. 20Click Path Audit · click-path-auditFinds UI buttons whose handler steps cancel each other out or leave the app in a wrong final state.
  21. 21Verify and Stop · verify-and-stopChecks that existing work meets its acceptance criteria, then stops without extra changes
  22. 22Browser Testing with DevTools · browser-testing-with-devtoolsLets an agent open, inspect and verify web pages in a real Chrome browser via Chrome DevTools MCP
  23. 23Test-Driven Development · test-driven-developmentMakes the agent write failing tests first, then code, and reproduce bugs with a test before fixing them.
  24. 24Add Product E2E Eval · add-product-e2e-evalAdds or extends full-stack end-to-end eval workflows for the Paperclip runner, with evidence and reporting.
  25. 25Add a Runner Eval · add-runner-evalAuthor and validate Paperclip Runner protocol evaluation cases, rosters, and assertions
  26. 26Paperclip Evals Navigator · paperclip-evalsGuides an agent through choosing, validating, and reporting Paperclip evaluation runs with evidence preserved.
  27. 27Review Storybook · review-storybookReview Paperclip UI stories and report render, interaction, and visual evidence separately
  28. 28Terminal-Bench Loop · terminal-bench-loopDrives one Terminal-Bench task through bounded smoke, diagnosis and board-gated fix cycles in Paperclip.
  29. 29Test Suite Audit · test-auditFind and remove redundant or vacuous tests while keeping meaningful regression coverage
  30. 30Verify Paperclip · verify-paperclipTest a Paperclip install or stack through real UI and CLI journeys and capture evidence
  31. 31QA Acceptance Plans · qa-acceptanceWrites acceptance criteria and a manual QA validation plan with pass/fail evidence for a feature change
  32. 32Agent Browser · agent-browserLets an agent drive a real browser to verify pages, capture screenshots, console and network logs
  33. 33Build and Test Runner · build-testRuns your project's typecheck, lint and test commands and reports whether the build passes.
  34. 34Blocking-IO Guard · blocking-io-guardAdds and verifies runtime tests that catch blocking I/O on DeerFlow's async backend code
  35. 35DeerFlow Smoke Test · smoke-testWalks an agent through pulling DeerFlow, deploying it locally or in Docker, and writing a health report
  36. 36Check Tests Evidence · check-testsRuns a local test-evidence check and keeps source paths in its results
  37. 37Custom 404 Page Checker · 404-pageReviews site markup to confirm missing pages show a helpful custom 404 with a real 404 status
  38. 38Accessibility Testing Guide · accessibility-testingGuides an agent to set up and review automated accessibility checks (axe-based) in tests and CI.
  39. 39Accessible Notifications Checker · accessible-notificationsReviews HTML and components so screen reader users get notifications like errors and success messages.
  40. 40Accesskey Uniqueness Checker · accesskeysReviews HTML pages to catch duplicate accesskey shortcuts that block keyboard users.
  41. 41Accessible Progress Bar Names · aria-progressbar-nameReviews progress bars so screen reader users know what task each one measures
  42. 42Carousel Accessibility Review · carousel-accessibilityChecks carousel markup for pause controls, keyboard access, ARIA and reduced-motion support.
  43. 43Contract Testing Guide · contract-testingGuides setup and review of consumer-driven contract tests (Pact) for frontend-backend APIs
  44. 44Cross-Browser Testing Checklist · cross-browser-testingReviews a site's CI and test coverage to confirm it works across Chrome, Firefox, Safari and Edge
  45. 45Definition List Structure Checker · definition-listReviews HTML so definition lists (dl/dt/dd) are valid and understandable to screen readers
  46. 46Draggable Accessibility Checker · draggable-accessibilityReviews drag-and-drop UI for keyboard and screen reader accessibility gaps
  47. 47Unique IDs for Active Elements · duplicate-id-activeReviews HTML for duplicate IDs on focusable elements that can break keyboard focus and screen readers.
  48. 48Duplicate ID ARIA Checker · duplicate-id-ariaReviews HTML for duplicate IDs that break ARIA label and description links.
  49. 49End-to-End Testing Reviewer · e2e-testingReviews a project's end-to-end test coverage and CI enforcement for critical user journeys.
  50. 50Error Monitoring Setup · error-monitoringGuides an agent to set up, check and review production error monitoring for a web app
  51. 51Heading Hierarchy Checker · heading-hierarchyReviews HTML pages for logical, accessible heading structure (one h1, no skipped levels).
  52. 52Integration Testing Guide · integration-testingGuides an agent to review and write integration tests for key workflows and CI coverage
  53. 53Application Security Testing · application-security-testingPlans and runs a whole-product security review, then ranks findings by proven exploitability.
  54. 54Strix Penetration Testing · penetration-testing-with-strixLets your agent run autonomous security pentests on apps, APIs, and repos and report proven vulnerabilities.
  55. 55Agent Browser Automation · agent-browserLets an agent open websites, fill forms, click, take screenshots and extract page data via a CLI
  56. 56CloudAnalyzer Command-Line Harness · cli-anything-cloudanalyzerLets an agent run CloudAnalyzer point cloud and trajectory QA checks from the command line
  57. 57WireMock Mock Server Control · cli-anything-wiremockLets an agent create, inspect and reset HTTP mock stubs on a WireMock server from the command line.
  58. 58Accessibility Audit and Fix · accesslint-auditAudits pages or code for WCAG 2.2 accessibility issues and can apply and verify fixes.
  59. 59Accessibility Diff Checker · accesslint-diffCompares a live page's accessibility violations before and after changes, reporting only what's new, fixed, or unchanged.
  60. 60AccessLint Page Scanner · accesslint-scanAudit a live web page for accessibility violations and get a selector-grounded fix list, without editing code.
  61. 61Advanced LLM Evaluation · advanced-evaluationDesign LLM-as-judge rubrics, scoring and pairwise comparisons with bias mitigation
  62. 62Agent Evaluation · agent-evaluationTest and compare agent behavior with versioned cases, explicit verifiers and honest uncertainty reporting.
  63. 63Agent QA Test Authoring · agent-qa-authoringLets an agent create, edit, validate and run Agent QA tests, suites and hooks with correct IDs and schemas.
  64. 64Agent QA Debug Fix · agent-qa-debug-fixDiagnose and minimally repair failed Agent QA test runs using run evidence and local code, then re-verify.
  65. 65Agent QA Result Triage · agent-qa-result-triageClassify failed Agent QA runs from recorded evidence and suggest next steps
  66. 66Quinn QA Tester · quinnWrites tests that verify requirements and reports honest coverage and failures.
  67. 67Audit a pytest suite · agentic-test-auditMeasure whether your pytest tests catch bugs, and find flaky, slow or bloated ones, report-only.
  68. 68Verify Python Change Tests · agentic-verifyChecks that Python changes are caught by tests by running mutants and adding tests until they fail.
  69. 69AI Prompt Regression Testing · ai-prompt-regression-testingCompare a prompt change against a fixed test set and report honest, case-level regression evidence
  70. 70Android UI Verification · android_ui_verificationLets an agent test and screenshot a React Native or Android app on an emulator using ADB.
  71. 71Android UI Journey Testing · android-ui-journey-testingRuns XML-specified user-flow tests on an Android device via ADB and writes a JSON pass/fail report.
  72. 72API Request Checker · api-analyzerReviews a pasted API request for obvious syntax and structure mistakes without sending it
  73. 73API Contract Testing · api-contract-testingChecks whether API changes will break the apps and services that depend on them, using local tests.
  74. 74API Fuzzing for Bug Bounty · api-fuzzing-bug-bountyGuides an agent through security testing of REST, SOAP and GraphQL APIs, with authorization gates.
  75. 75Dogfood web app QA · dogfoodLets an agent systematically test a website and file bug reports with screenshots and repro videos.
  76. 76WebMCP Tool Generator · webmcp-genBuilds and tests experimental WebMCP tools that let agents use a web page's real workflows safely.
  77. 77Competition Relay Coercion Chain · competition-relay-coercion-chainTraces forced-auth coercion and NTLM relay paths in a CTF sandbox, step by step.
  78. 78Browser & Desktop Automation · browser-automationLets the agent drive web pages and Windows desktop apps (Playwright, OpenReverse) via clicks, forms, screenshots and network capture.
  79. 79SRC Hunter Bug Bounty Workflow · src-hunterGuides an agent through authorized bug bounty and SRC vulnerability hunting, from recon to report.
  80. 80Screen Reader Testing · screen-reader-testingTest web apps with VoiceOver, NVDA, JAWS and TalkBack for accessibility issues
  81. 81Debugging Strategies · debugging-strategiesWalks the agent through systematic bug hunting, profiling, and root cause analysis
  82. 82E2E Testing Patterns · e2e-testing-patternsWrite reliable end-to-end browser tests with Playwright or Cypress and debug flaky ones
  83. 83LLM Evaluation Strategies · llm-evaluationPlan and build tests that measure how well an LLM application performs, using metrics, judges and human review
  84. 84ShellCheck Configuration Helper · shellcheck-configurationGuides an agent to set up and use ShellCheck to lint and fix shell scripts
  85. 85Test Planning & QA Breakdown · breakdown-testTurns feature docs into test strategies, QA plans, and GitHub test task checklists
  86. 86Bug Reproduction Brief · bug-reproduction-briefTurns a vague bug report into a minimal, verified reproduction before any fix is attempted.
  87. 87Caption QA · caption-qaChecks SRT/WebVTT captions against Netflix, BBC and DCMP timing and line rules, then fixes them.
  88. 88Chrome DevTools Browser Control · chrome-devtoolsLets an agent drive and inspect a live Chrome browser: navigate, click, debug, and profile performance.
  89. 89MSTest Unit Testing Guide · csharp-mstestWrite C# unit tests with modern MSTest 3.x/4.x assertions and data-driven patterns
  90. 90TUnit Testing Best Practices · csharp-tunitWrite C# unit tests with the TUnit framework, including data-driven tests, following its conventions.
  91. 91C# XUnit Testing Guide · csharp-xunitWrites C# unit tests with XUnit following standard best practices, including data-driven tests.
  92. 92Cypress Flake Fixer · cypress-flake-fixerFinds and repairs flaky Cypress test patterns and APIs removed in Cypress 12 to 16
  93. 93Eval-Driven Development for LLM Apps · eval-driven-devBuilds automated pixie-based evaluation pipelines to score a Python LLM app's behavior with real runs
  94. 94Test-First Development · tddGuides an agent through red-green test-first coding at pre-agreed test seams.
  95. 95Verify Changes Before Claiming Done · verifyMakes the agent prove a change works with tests or direct checks before saying it is complete
  96. 96Android APK Malware Static Analysis · analyzing-android-malware-with-apktoolStatically triage suspicious Android APKs for permissions, suspicious APIs and network indicators without running them
  97. 97APT Group Navigator Analysis · analyzing-apt-group-with-mitre-navigatorMap APT groups' ATT&CK techniques into Navigator heatmaps for detection-gap analysis
  98. 98C2 Communication Analysis · analyzing-command-and-control-communicationAnalyzes malware command-and-control traffic in packet captures to find beacons and decode protocols.
  99. 99DNS Exfiltration Log Analysis · analyzing-dns-logs-for-exfiltrationHunts DNS logs for tunneling, DGA domains and covert C2 traffic using entropy and volume checks
  100. 100Email Header Phishing Analyzer · analyzing-email-headers-for-phishing-investigationTraces a suspicious email's true origin by reading its headers and checking SPF, DKIM and DMARC.
  101. 101Kubernetes Audit Log Analysis · analyzing-kubernetes-audit-logsInvestigates Kubernetes API audit logs for exec, secret, RBAC and anonymous-access threats
  102. 102Linux ELF Malware Analysis · analyzing-linux-elf-malwareGuides an agent through triaging and analyzing suspicious Linux ELF malware samples
  103. 103Malpedia Malware Family Lookup · analyzing-malware-family-relationships-with-malpediaLook up malware family aliases, YARA rules, threat actor links and family relationships via the Malpedia API.
  104. 104Malware Persistence Analysis with Autoruns · analyzing-malware-persistence-with-autorunsHunt for malware autostart entries on Windows using Sysinternals Autoruns output and triage rules
  105. 105MFT Deleted File Recovery · analyzing-mft-for-deleted-file-recoveryRecovers traces of deleted files and detects timestomping from NTFS Master File Table artifacts.
  106. 106NetFlow Network Flow Analyzer · analyzing-network-flow-data-with-netflowSpot port scans, exfiltration, beaconing and traffic spikes in NetFlow/IPFIX records
  107. 107Network Traffic Incident Analysis · analyzing-network-traffic-for-incidentsGuides an agent through analysing packet captures and flow logs to spot command-and-control, lateral movement and exfiltration.
  108. 108Wireshark Network Traffic Analysis · analyzing-network-traffic-with-wiresharkGuides an agent through capturing and analyzing packet files with Wireshark/tshark for security investigations
  109. 109PowerShell Empire Artifact Analyzer · analyzing-powershell-empire-artifactsHunts Windows event logs for signs of PowerShell Empire attack-framework activity
  110. 110Splunk Security Log Analysis · analyzing-security-logs-with-splunkInvestigate security incidents by searching and correlating Splunk logs with SPL queries
  111. 111Analyzing Threat Intelligence Feeds · analyzing-threat-intelligence-feedsGuides an agent through evaluating, normalizing (STIX 2.1), deduplicating and enriching threat intelligence feeds and IOCs.
  112. 112Windows Shellbag Forensics · analyzing-windows-shellbag-artifactsReconstructs folder browsing history on Windows from registry Shellbag artifacts using SBECmd
  113. 113Device-Code Phishing Attack Simulation · attacking-oauth-with-device-code-phishingLets an agent run authorized red-team device-code and consent phishing tests against Microsoft Entra ID.
  114. 114Auditing AWS S3 Bucket Permissions · auditing-aws-s3-bucket-permissionsAudit AWS S3 buckets for public access, risky ACLs and policies, and missing encryption
  115. 115Kubernetes RBAC Auditor · auditing-kubernetes-cluster-rbacAudits Kubernetes cluster permissions for overly broad roles, risky bindings and privilege escalation paths.
  116. 116MCP Tool-Poisoning Auditor · auditing-mcp-servers-for-tool-poisoningAudits MCP servers for poisoned tool descriptions, rug pulls, SSRF and missing auth before you trust them.
  117. 117Splunk SPL Detection Rules · building-detection-rule-with-splunk-splLets an agent draft Splunk SPL correlation searches that flag security threats for SOC analysts.
  118. 118Timesketch Incident Timeline Builder · building-incident-timeline-with-timesketchBuild and search shared forensic incident timelines in Timesketch for attack chain reconstruction
  119. 119Cloud Penetration Testing · conducting-cloud-penetration-testingGuides an agent through authorized penetration tests of AWS, Azure and GCP accounts, from scoping to reporting.
  120. 120Full-Scope Red Team Engagement · conducting-full-scope-red-team-engagementPlan and run an ATT&CK-mapped red team exercise testing an organization's detection and response
  121. 121Network Penetration Test · conducting-network-penetration-testGuides an agent through a PTES-style network pentest: discovery, scanning, vuln checks, and controlled exploitation.
  122. 122Pass-the-Ticket Attack Playbook · conducting-pass-the-ticket-attackGuides red teamers through Kerberos ticket theft and reuse for authorized lateral-movement testing
  123. 123Vishing Pretext Call Assessment · conducting-social-engineering-pretext-callPlan, script and track authorized voice-phishing tests that measure staff susceptibility to phone social engineering
  124. 124JavaScript Malware Deobfuscator · deobfuscating-javascript-malwareUnpacks obfuscated malicious JavaScript from phishing pages and skimmers to reveal its logic
  125. 125Bug Report Writer · bug-reportTurns a bug description or source file into a structured, triaged bug report with repro steps.
  126. 126Playtest Report · playtest-reportCreates structured playtest report templates and turns raw playtest notes into routed findings.
  127. 127QA Test Plan Builder · qa-planBuilds a sprint, feature or story QA plan classifying tests by Logic, Integration, Visual and UI.
  128. 128Regression Suite · regression-suiteChecks that each bug fix has a test guarding it and flags gaps in game test coverage.
  129. 129Smoke Check Gate · smoke-checkRuns an automated critical-path check on a game build before handing it to QA
  130. 130Soak Test Protocol · soak-testGenerates a checklist for long play sessions to catch memory leaks, crashes and fatigue
  131. 131Team QA Testing Cycle · team-qaRuns a full QA cycle: test strategy, test cases, execution and sign-off via a QA agent team.
  132. 132Test Evidence Review · test-evidence-reviewReviews the quality of a story's test files and manual evidence, not just whether they exist.
  133. 133Test Flakiness Detective · test-flakinessFinds intermittently failing tests from CI logs and recommends quarantine or fixes
  134. 134Browser Automation with agent-browser · agent-browserLets the agent open web pages, read them, click, fill forms, and take screenshots via a browser CLI.
  135. 135Agent Browser · agent-browserLets the agent drive a real web browser to navigate sites, fill forms, click, and take screenshots.
  136. 136BrowserStack Cross-Browser Testing · browserstackRuns Playwright tests on BrowserStack's cloud browsers and summarises results per browser
  137. 137Test Coverage Gap Analyzer · coverageFinds which app pages, components and endpoints lack Playwright tests and ranks the gaps.
  138. 138Fix Flaky Playwright Tests · fixDiagnoses and fixes failing or intermittently passing Playwright tests using a four-category checklist.
  139. 139Generate Playwright Tests · generateWrites end-to-end Playwright browser tests for a feature, page, or component in your project.
  140. 140Migrate to Playwright · migrateConvert Cypress or Selenium test suites to Playwright, file by file, with verification runs.
  141. 141Playwright Project Setup · pw-initSets up Playwright end-to-end testing in a web project, including config, example test and CI workflow.
  142. 142Playwright Test Reviewer · pw-reviewReviews Playwright test files for anti-patterns, scores them, and proposes fixes
  143. 143Playwright Test Reporter · reportRuns Playwright tests and turns the results into a summary, report file, and optional Slack or TestRail post.
  144. 144TestRail Sync · testrailSync Playwright tests with TestRail cases, runs and results in both directions
  145. 145Deflake a Flaky Test · deflakeMakes a flaky test reliably pass with a minimal fix that keeps its checks intact
  146. 146End-to-End Testing for Qwen Code · e2e-testingRun and inspect real end-to-end tests of the Qwen Code CLI, including MCP and API traffic
  147. 147Terminal Capture · terminal-captureAutomates screenshots of CLI and terminal UI output for visual checks and PR reviews
  148. 148tmux Real User Testing · tmux-real-user-testingDrive Qwen Code's terminal UI in tmux like a real user and save a readable step-by-step test log
  149. 149Test Failure Explorer · test-failure-explorerLets an agent import a Vitest 3.2 JSON report and investigate its test failures with cited evidence.
  150. 150Dummy Dataset Generator · dummy-datasetCreates realistic fake test data as CSV, JSON, SQL, or a Python generator script
  151. 151Test Scenario Writer · test-scenariosTurns user stories into structured QA test scenarios with steps and expected outcomes
  152. 152Dogfood Branch QA · ce-dogfoodBrowser-tests your current branch's changes end to end, fixes small bugs, and writes a QA report
  153. 153Riffrec Feedback Analysis · ce-riffrec-feedback-analysisTurns screen-and-voice product feedback recordings into evidence-backed bug reports and requirements
  154. 154Browser Test Runner · ce-test-browserRuns browser tests on the pages a branch or PR changed and reports pass, fail, or skip per route.
  155. 155Ego Browser Automation · skill-bodyLets an agent drive a real browser through the ego-browser CLI to navigate and inspect pages
  156. 156Assay: AI Output Evaluator · AssayGrades AI prompts, models and agents with code checks and calibrated judges, and checks produced artifacts before you see them.
  157. 157Hardening (Property Tests) · HardeningFinds bugs in existing code tests by generating many inputs and shrinking failures to minimal cases.
  158. 158Interceptor Browser and Mac Control · InterceptorLets the agent drive a real Chrome test profile and macOS apps to verify pages and deploys
  159. 159Agent Evaluation Methods · evaluationBuild tests, rubrics, and quality gates to measure whether an AI agent works well.
  160. 160Browser Automation Patterns · browser-automationGuides an agent through navigating, filling forms and comparing prices in a web browser
  161. 161API Testing Expert · api-testerTest, debug, and validate REST and GraphQL APIs with curl and structured test plans.
  162. 162Security Audit and Code Review · security-auditGuides the agent through OWASP-style security reviews, CVE impact checks, and pen-test methodology
  163. 163Harness Eval · harness-evalRuns OpenHarness features end-to-end against a real codebase using live LLM API calls
  164. 164Update Integration Snapshots · update-int-snapshotsRegenerate Playwright visual test snapshots for Dozzle after intentional UI changes
  165. 165Playwright Login Flows · login-flowsAutomate website logins in Playwright tests, including OAuth, saved sessions and TOTP 2FA
  166. 166Drive MiMo Test Harness · drive-mimoLets an agent launch and check separate MiMo Code runs headlessly or in tmux for testing
  167. 167Playwright Browser Automation · playwrightLets an agent drive a real browser from the terminal: open pages, fill forms, take screenshots and traces.
  168. 168Dev Browser Automation · dev-browserLets the agent drive a Chromium browser to navigate, fill forms, screenshot and scrape pages.
  169. 169Chaos Engineer · chaos-engineerPlan and run controlled failure experiments on distributed systems, with safety limits and rollback steps
  170. 170Playwright Expert · playwright-expertWrites and debugs Playwright end-to-end browser tests, page objects, and CI setup.
  171. 171Test Master · test-masterWrites test suites, mocking strategies, test plans and defect reports across unit, E2E, performance and security testing.
  172. 172Integration Test Reporting · test-reportingRuns Hive's dummy-agent integration tests and writes a detailed HTML results report.
  173. 173Browser Automation via Hive Browser CLI · hive.browser-automationDrive the user's running Chrome from the terminal using hive-browser, with screenshot-based clicking.
  174. 174Validate Claude Ads Releases · ads-validateChecks Claude Ads contracts, scores, installs, uninstalls and release readiness with pass/fail evidence
  175. 175Generate Python Runnability Test · generate-python-runnability-testCreates a minimal smoke test that checks a Python recipe's agent module imports and defines root_agent
  176. 176Root-Cause Analysis for Agent Insights · rcaDiagnose why an AQuA-observed agent failed by reading its own source and conversations
  177. 177Play Policy Insights · play-policy-insightsAudits an Android app against Google Play policy areas and drafts a compliance report
  178. 178Offensive API Abuse Methodology · offensive-api-abuseGuides an agent through authorized penetration tests of API business logic, GraphQL, and JWT weaknesses.
  179. 179Offensive JWT Attack Checklist · offensive-jwtWalks an agent through testing JWT-based login systems for common token-forgery and auth-bypass flaws.
  180. 180Offensive Fuzzing Methodology · offensive-fuzzingGuides an agent through planning and running fuzz campaigns to find crashes and memory bugs in software
  181. 181Offensive IoT Testing Methodology · offensive-iotGuides an agent through hardware, firmware, and wireless security testing of IoT and embedded devices
  182. 182Offensive Phishing Campaigns · offensive-phishingPlans and runs authorized phishing simulations: infrastructure, pretexts, payloads and credential capture.
  183. 183Fast Testing Checklist · offensive-fast-checkingGives the agent a speed-focused offensive security checklist for time-boxed web app assessments.
  184. 184Offensive Deserialization Testing · offensive-deserializationGuides an agent through insecure deserialization exploitation tests across Java, PHP, .NET, Python, Node.js and Ruby
  185. 185Remote Code Execution Testing Checklist · offensive-rceGuides an agent through a structured checklist for finding remote code execution flaws in web apps.
  186. 186SQL Injection Testing Playbook · offensive-sqliGuides an agent through SQL injection testing methods, payloads, and exploitation for security assessments.
  187. 187WAF Bypass Techniques · offensive-waf-bypassGives the agent a checklist for evading web application firewalls during security tests
  188. 188Cross-Site Scripting Testing Checklist · offensive-xssWalks an agent through a structured XSS testing methodology for web apps and bug bounties
  189. 189XXE Injection Testing Checklist · offensive-xxeGuides an agent through XML External Entity (XXE) vulnerability testing methodology for web apps
  190. 190Claim Chart Builder · claim-chartBuilds patent or civil element charts with pin-cited cells and gap detection for litigation work.
  191. 191Demand Letter Drafter · demand-draftDrafts a sendable demand letter only after a privilege, waiver, and settlement-communication gate is checked.
  192. 192Demand Letter Intake · demand-intakeGathers the facts, leverage and risks you need before drafting a demand letter.
  193. 193Demand Letter Triage · demand-receivedTriages an inbound demand letter: extracts key fields, checks your matter log, rates merit, and recommends a response.
  194. 194Deposition Prep Outline · deposition-prepBuilds a deposition outline for a witness from case documents and theory, with impeachment material
  195. 195Privilege Log Review · privilege-log-reviewSorts a litigation privilege log into obvious-privileged, obvious-not, and attorney-review flags.
  196. 196DPA Review · dpa-reviewReviews a Data Processing Agreement term-by-term against your DPA playbook, with redlines and a memo.
  197. 197Privacy Policy Monitor · policy-monitorSpots where your privacy policy no longer matches what your team actually does
  198. 198Convex Test Writer · convex-testWrites vitest tests for Convex functions using an in-memory backend
  199. 199Convex Feature Verification · convex-verifyProve a Convex feature works by seeding data, testing as multiple users, and checking that unauthorized access is refused.
  200. 200Proof Video Recorder · proof-videoRecord, caption and attach real browser proof videos and screenshots to a GitHub pull request.
  201. 201Test-Driven Development · test-driven-developmentGuides an agent to write a failing test first, then minimal code, then refactor, when TDD is selected
  202. 202Test Reasoning Serialization · test-reasoningChecks that reasoning settings are sent correctly to each AI provider's API
  203. 203VM Lab for macOS GUI Testing · vm-labDrives a Parallels macOS VM to test GUI automation tools like Peekaboo with independent verification
  204. 204Test Playable Web Games · test-playable-web-gamesLets an agent QA browser games with deterministic fixtures, real playthroughs and browser evidence.
  205. 205Replica Diff: Clone Parity Checker · replica-diffScores how closely your app clone matches the original's features and screen layout
  206. 206Replica Clone Tester · replica-testPlans, automates and reports bugs for a cloned app's user flows, using Playwright tests and a click-through.