Continuous test-driven development loop — after every code change, builds the project, starts the server, and runs Unit Tests, Integration Tests, and System Tests. Applies on top of microprofile-server skill. Use during development when you want full verification after each change. Triggers on "continuous testing", "continuous-testing", "test loop", "st-loop", or requests to run all tests after every change.
Use this skill whenever writing, editing, or generating Cucumber/Gherkin tests with the Pickleib framework! Triggers on any mention of Pickleib, PickleibSteps, BuiltInSteps, page-repository.json, @PageObject, @ScreenObject, @FindBy page objects, CommonSteps, ObjectRepository, PickleibWebDriver, PickleibAppiumDriver, or any request to write, fix, or add to a Cucumber test in a test automation project. Also use when asked to add entries to a page-repository JSON file, define page objects, write feature files, select dropdowns, verify elements, or perform any browser/mobile interaction through Pickleib. Always consult this skill before generating test code or locator definitions — do not guess step syntax or method signatures. --- # Pickleib — Agent Skill A Cucumber-based test automation framework that decouples **element acquisition** (via JSON repository or Java Page Objects) from **element interaction** (via built-in Cucumber steps). Tests are written in Gherkin; raw Selenium/Appium calls never appear in feature files. ## Companion Skills | Skill | Activates when | What it does | |---|---|---| | `test-composer` | User asks to expand coverage or "add more scenarios" | Iterative test suite expansion across the full app | | `bug-discovery` | After test coverage is achieved | Adversarial bug hunting after tests pass | --- ## ABSOLUTE RULES **STOP. Read before any action.** ### 1. Do NOT skip stages This skill operates in four stages. Complete each stage and get user approval before advancing.
Run ArduPilot SITL autotests (integration/behavior tests). Use when the user asks to run autotests, vehicle tests, or specific test methods.
- 📁 Tools/
- 📁 Workflows/
- 📄 AIVision.md
- 📄 CognitivePersonas.md
- 📄 CognitiveState.md
Cognitive Browser - AI-powered browser automation with constitutional safety, AI visual regression, cross-browser testing, responsive testing, A/B comparison, and user perspective testing. v16.10.0 (25 cognitive traits with research-based correlations, 9 personas, persona questionnaire, FCP/TTFB Web Vitals ratings, reduced stealth false positives). USE WHEN cognitive browser, smart browser, AI browser automation, vision-based automation, self-healing selectors, autonomous web agent, user testing, persona testing, authenticated automation, test suite, natural language tests, repair tests, fix broken tests, flaky test detection, detect flaky tests, unreliable tests, constitutional safety, safe automation, visual regression, screenshot comparison, cross-browser, responsive testing, viewport testing, mobile testing, A/B testing, staging vs production, compare URLs, performance regression, test coverage, coverage map, coverage gaps, MCP server, Claude Desktop, remote MCP, custom connector, Auth0 OAuth, accessibility, a11y, ARIA, verbose, debug, overlay, dismiss overlay, CI/CD, GitHub Action, Docker, GitLab CI, cognitive journey, cognitive simulation, user abandonment, friction detection, cognitive traits, patience, frustration, confusion, resilience, bounce-back, recovery, vision mode, hover, dropdown menu, daemon mode, persistent session, explore, custom dropdown, Alpine.js, React Select, agent-ready, competitive benchmark, empathy audit, focus hierarchy, attention patterns, session bridge, api-free, compare personas, deterministic, motor-tremor, low-vision, adhd, color-blind, disability personas, persona questionnaire, 25 traits, 6 tiers, trait correlations, web vitals.
Use when completing retro feature work, after implementation and tests pass, before creating PRs. Keywords: scenario tests, clean install, retro documentation updates.
- 📄 e2e-test-skill.md
- 📄 SKILL.md
E2E test skill for validation
Discover edge cases and test coverage gaps through systematic analysis. Use when analysing test coverage, finding bugs, hunting for edge cases, reviewing code for robustness, or when code-reviewer identifies test gaps. Also use when the user says things like "what could go wrong", "is this well tested", "find holes in my tests", "what am I missing", or asks about edge cases for any function or module.
Review and improve Kensa BDD tests written in Kotlin. Use this skill whenever the user shares a Kensa test file, asks you to review or improve a Kensa test, or mentions Given-When-Then tests in a Kensa project. Kensa tests use the KensaTest interface with given()/whenever()/then() DSL, @RenderedValue, @ExpandableSentence, Fixtures, and produce HTML reports with sequence diagrams.
Run tests, linters, type checkers, and builds with AI-powered analysis. Use this INSTEAD OF running test/lint/build commands directly via Bash. Wraps any command (pytest, jest, go test, make test, npm test, make lint, mypy, tsc, eslint, golangci-lint, cargo clippy, make typecheck, make build, etc.) to produce clean summarized output, keeping conversation context small. When a test or lint fails, ATR analyzes the full output and returns actionable failure insights.
Zephyr Scale CLI - manage test resources, run test cycles interactively, and automate test operations
- 📁 prompts/
- 📄 skill.json
- 📄 SKILL.md
A test skill
Execute unit-test alignment after large refactors or broad code changes. Trigger when the user explicitly uses the command "-- 对齐测试 --" or asks to align/fix tests after massive modifications. Run relevant unit tests, analyze failing test cases, update tests and/or implementation, and iterate until stable.
