Controls Govee H6056 Flow Plus light bars (smart LED lights) via cloud REST API with correct segment-to-bar mapping (Yankee=0-5, Golf=6-11), phantom-segment awareness (12-14 return 200 OK but do nothing), correct "off" semantics (rgb=(1,1,1), not (0,0,0)), and rate-limit guidance (~7 req/min sustained → pair with iot-actuator-patterns-kotlin debounce). Use when the user wants to control Govee H6056 light bars, change LED light colors or brightness, set bar segment colors, or automate Govee smart lighting scenes.

Use for any question or task about .NET tests in C#, F# or VB.NET, including quick how-to questions and choosing between xUnit, NUnit and MSTest: Fact and Theory tables, fixtures and shared state between tests, parallel runs, mocking, async tests, output, and coverage with dotnet test. Has authoring conventions and anti-patterns for xUnit.net.

Use whenever someone asks for test factories or a FactoryBot setup, even a quick one: factories with traits and associations (Ruby, Rails), Mimesis bulk data (Python), Bogus Faker<T> builders (.NET), or which generator fits. Same fixture in each tool; plain fake values stay with faker-data.

Use for any question or task about a bug tracker workflow in Jira, Linear, GitHub Issues or Azure DevOps, including severity vs priority, filing bugs from failing CI tests without duplicates, and defect counts that are wrong (missing top-severity bugs, fixed items counted as new): dedupe before filing, lifecycle, transitions and CI filing.

Use when the user asks for Student Orientation from supplied source materials. Trigger language: student orientation; new student orientation; international student orientation. Produce a grounded interactive digital-human course learners can interrupt with voice questions. Do not invent unsupported facts or claim external certification, competence, or real-world completion. With explicit approval, this Skill may install or update the official PersonWise CLI and uses browser OAuth. Other course-creation requests are handled only when the user explicitly asks for them with this Skill.

Use when the user asks for Employee Onboarding Course from supplied source materials. Trigger language: employee onboarding; new hire onboarding; new hire training; role ramp. Produce a grounded interactive digital-human course learners can interrupt with voice questions. Do not invent unsupported facts or claim external certification, competence, or real-world completion. With explicit approval, this Skill may install or update the official PersonWise CLI and uses browser OAuth. Other course-creation requests are handled only when the user explicitly asks for them with this Skill.

Use when a repo already has Storybook and wants a visual test per story: the hosted Chromatic addon, or the self-hosted Storybook test-runner with a postVisit hook calling Playwright's toHaveScreenshot, plus CI setup.

Use for any question or task about sharing setup across Playwright tests, including reusing login, copy-pasted beforeEach blocks, and test users that collide between parallel workers. Builds test.extend fixtures with the right test or worker scope, setup and teardown, and per-worker isolation for login, database or feature-flag setup.

Use when testing FHIR servers, EHR integrations, claims processing or other health IT needs realistic patient records with no HIPAA exposure. Runs MITRE Synthea to simulate patient populations and outputs FHIR R4, STU3, DSTU2, C-CDA or CSV, with custom disease modules.

Use when a canary deploy needs an automatic promote or rollback decision instead of someone watching dashboards. Compares the canary's error rate, p50, p95 and p99 latency and business KPIs with the baseline over the observation window, with absolute and relative thresholds and a significance check.

Use when a design, story or architecture sketch touching login, user data, payments, file uploads or an external integration is about to be built with no threat model. Walks assets and trust boundaries through Microsoft's STRIDE categories, triages threats and writes the threat model into the repo.

Use for any question or task about a leaked secret, API key or token found in code or git history, including what to do next and whether scrubbing history is enough (it is not), or scheduled rotation: identify the provider, rotate the credential through its API (AWS IAM, GitHub, Stripe, GCP, Azure, Twilio, Slack and more), revoke the old one, log the audit trail and link the post-mortem.

Use before changing analyzers, synonyms, boosts or query templates on Elasticsearch, OpenSearch or Solr search, so a relevance baseline exists. Builds judgment lists and _rank_eval tests with precision, recall, MRR and DCG, plus OpenSearch and Solr specifics in its references.

Use when a business transaction spans two or more services and a mid-sequence failure must be undone, or compensation logic just changed. Tests orchestrated and choreographed sagas: each compensating step, partial failures, idempotent compensations and the outbox for atomic publish.

Use for any question or task about property-based or generated-input tests in Python, including quick how-to questions, round-trip checks like parse(format(x)), and inputs that break code in production: Hypothesis @given strategies, composite strategies, assume and filtering, settings, reproducibility and CI. Has round-trip and metamorphic property templates.

Use for any question or task about testing SMS sending, including one Twilio sender and runs that must not text real phones: Twilio magic numbers and test credentials, GSM-7 vs UCS-2 segment counts (emoji messages that cost more), rate limits, STOP and HELP opt-out keywords, and sender ID vs short code vs 10DLC differences.

Use when a Python pytest or unittest suite needs mutation testing to show whether the tests catch bugs. Sets up mutmut: mutmut run, results and browse, applying survivors, pragma: no mutate suppressions and pyproject.toml config.

Use when an iOS or Android app needs accessibility tests: XCUITest performAccessibilityAudit (iOS 17+), VoiceOver labels and traits, Espresso AccessibilityChecks, Accessibility Scanner and TalkBack order, plus WCAG checks for labels, 44pt and 48dp touch targets, contrast and focus order.

Use when an app supports right-to-left languages (Arabic, Hebrew, Persian, Urdu). Runs the suite under RTL locales, checks dir=rtl, mirrored layout, icons and alignment, logical CSS properties instead of left and right, and captures screenshots per locale for review.

Use when a GraphQL API must be hardened or audited against denial of service and schema disclosure. Sends over-limit depth and cost queries and asserts they are rejected, proving graphql-depth-limit, cost analysis or graphql-armor are enforced; covers introspection and persisted-query allowlists.