aks-builds

107 production-grade QA engineering skills covering frontend, API, performance, mobile, security, CI, and AI/LLM testing. Use when writing or reviewing Playwright, pytest, Jest, k6, Cypress, Newman, or JUnit tests, auditing test coverage, designing test data…

When the user wants to design, implement, or operate accessibility (a11y) testing — automated scans, manual audits, screen-reader testing, WCAG conformance, Section 508 / EAA compliance. Use when the user mentions "accessibility," "a11y," "WCAG," "Section…

When the user wants to evaluate, adopt, or operate AI-augmented testing tools and approaches — autonomous test generation, self-healing locators, AI-assisted authoring, vision-based testing, agentic test runners. Use when the user mentions "AI testing,"…

When the user wants to design, implement, debug, or scale Appium tests for iOS and Android mobile automation. Use when the user mentions "Appium," "Appium 2," "UiAutomator2," "XCUITest driver," "appium:capabilities," "AppiumServer," "accessibility id,"…

When the user wants to design, implement, debug, or operate Artillery load tests. Use when the user mentions "Artillery," "artillery.yml," "artillery run," "Artillery scenarios," "Artillery Pro," "phases (Artillery)," "Artillery plugins," "Artillery Engine,"…

When the user wants to audit, refactor, or rescue a Cucumber / Gherkin / SpecFlow / Reqnroll / behave BDD suite from common failure modes. Use when the user mentions "BDD anti-patterns," "Gherkin anti-patterns," "scenario refactoring," "imperative steps,"…

When the user wants to design, implement, debug, or operate BDD tests on Python using behave. Use when the user mentions "behave," "behave.ini," "@given/@when/@then," "context.x," "environment.py," "behave hooks," "behave tags," "step definitions in Python,"…

When the user wants to design, run, or operate chaos experiments to validate system resilience. Use when the user mentions "chaos engineering," "chaos testing," "fault injection," "Chaos Monkey," "Chaos Mesh," "Gremlin," "Litmus," "Steadybit," "Toxiproxy,"…

91 production-grade healthcare engineering skills covering FHIR R4, HL7v2, HIPAA compliance, EHR integration, telehealth, clinical AI, and revenue cycle. Use when building, debugging, or auditing healthcare data pipelines, FHIR resources, HL7 message…

When the user is building, validating, or auditing a computer system that creates, modifies, maintains, archives, retrieves, or transmits electronic records or applies electronic signatures in an FDA-regulated (GxP) context. Also use when the user mentions…

When the user wants to design, build, audit, or remediate accessibility for healthcare apps and patient-facing systems. Also use when the user mentions "WCAG," "WCAG 2.2," "WCAG 3.0," "Silver," "Section 508," "ADA Title II," "ADA Title III," "Section 1557…

When the user is designing, implementing, or reviewing audit logging for PHI access — including the HIPAA §164.312(b) audit controls requirement, accounting of disclosures, ATNA/DICOM audit, FHIR AuditEvent, SIEM ingestion, retention, tamper-evidence, and…

When the user wants to design or build software that handles US healthcare claims — submission, adjudication, remittance, denials, or appeals. Use when the user mentions "claims," "EDI," "X12," "837," "837P," "837I," "837D," "835," "ERA," "270," "271," "276,"…

When the user wants to author, parse, validate, or transform Clinical Document Architecture (CDA) or Consolidated CDA (C-CDA) documents. Use when the user mentions "CDA," "C-CDA," "CCD," "Continuity of Care Document," "Discharge Summary," "Operative Note,"…

When the user wants to build, evaluate, deploy, or monitor machine learning models for clinical or operational healthcare use cases. Also use when the user mentions "clinical ML," "clinical AI," "readmission prediction," "sepsis model," "deterioration model,"…

When the user wants to design, build, deploy, or evaluate a clinical decision support (CDS) tool. Also use when the user mentions "CDS," "CDS Hooks," "patient-view hook," "order-sign hook," "order-select hook," "encounter-start," "appointment-book," "CDS…

Spec-driven, BDD-shaped project management for AI agents. Converts natural language proposals into BDD feature files and tracked work items in GitHub Issues, Azure DevOps, Jira, Linear, or GitLab. Use when writing specs, defining acceptance criteria, creating…

OpenSpecPM — spec-driven, BDD-shaped project management for any PM backend: OpenSpec proposal → BDD specs (Given/When/Then) → tasks → GitHub Issues / Azure DevOps Boards / Jira / Linear / GitLab → shipped code. Use this skill when the user wants to (a) author…

Captures real terminal output as polished screenshots or animated GIFs, redacts secrets, embeds visual proof into README.md, and fails CI when the proof drifts from live command output. Use when a project README needs visual evidence it runs, when updating…

Capture a real terminal command and its real output as a polished screenshot or animated GIF, then embed it into README.md as "proof it runs" evidence for GitHub visitors. Use when the user wants a terminal screenshot, CLI demo, README demo GIF, a styled…

Decodes any insurance policy or quote (auto, home, renters, health, life, or business) from a PDF, image, or pasted text into a plain-English breakdown: what is covered, what is excluded, coverage gaps, whether the user is over- or under-insured, claim-filing…

OWASP-aligned security testing guidance covering DAST, SAST, SCA/SBOM, secret scanning, IaC scanning, threat modeling, and DevSecOps pipelines for web apps, APIs, and mobile applications. Use when conducting security reviews, selecting appsec tooling,…

8-phase evidence pipeline for root-cause analysis of Playwright, pytest, Jest, Cypress, Newman, k6, and JUnit test failures. Scans git history, application logs, and config to produce confidence-scored root-cause hypotheses. Use when a test is failing and the…

Accessibility audit delta — surfaces only new axe-core WCAG violations introduced since the last baseline, not pre-existing issues. Use when adding UI features and needing to gate CI on net-new accessibility regressions without blocking on inherited technical…

Derives k6 SLO baselines from any latency source — HAR files, k6 results, OpenTelemetry traces, nginx access logs, or Prometheus metrics. Use when configuring performance thresholds, setting p95/p99 SLO targets, building Grafana k6 dashboards, or establishing…

Find active hackathons worldwide. Returns an enriched list with eligibility badges (OPEN/GATED/PARTIAL/UNKNOWN) — use when asked to find hackathons, competitions, or coding events to join. Sources: DuckDuckGo search with Devpost API and MLH sitemap fallback.…

Generate ready-to-import API test collections for every API client (Postman, OpenAPI 3.1, Insomnia, Bruno, Hoppscotch, Thunder Client, .http) directly from a service codebase, with exhaustive request variants per endpoint (happy path, boundaries, invalid…