Develop AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in JavaScript/TypeScript, or when encountering Genkit errors, validation issues, type errors, or API problems.

Pre-deployment validation for Azure readiness. Run deep checks on configuration, infrastructure (Bicep or Terraform), permissions, and prerequisites before deploying. WHEN: validate my app, check deployment readiness, run preflight checks, verify configuration, check if ready to deploy, validate azure.yaml, validate Bicep, test before deploying, troubleshoot deployment errors, validate Azure Functions, validate function app, validate serverless deployment.

Use when you need data access with Quarkus Hibernate ORM Panache — including PanacheEntity / PanacheEntityBase, PanacheRepository, named queries, JPQL, native SQL, DTO projections (project(Class)), pagination (Page.of()), N+1 avoidance (JOIN FETCH), optimistic locking (@Version / OptimisticLockException), @NamedQuery for validated reusable queries, transactions, @TestTransaction for test isolation, and immutable-friendly patterns. This is the Quarkus analogue to Spring Data for relational persistence. This should trigger for requests such as Review Panache entities or repositories in Quarkus; Improve Hibernate ORM data access with Panache; Add DTO projections, JOIN FETCH, pagination, or optimistic locking to Panache queries; Fix N+1 query problems or add @Version concurrency control in Quarkus Panache. Part of cursor-rules-java project

Use when you need to write fast unit tests for Quarkus applications — including pure tests with @ExtendWith(MockitoExtension.class), @QuarkusTest with @InjectMock for full CDI mock replacement, @InjectSpy for partial CDI bean mocking, REST Assured for resource-focused tests, @ParameterizedTest with @CsvSource / @MethodSource, QuarkusTestProfile for test-specific configuration overrides, and naming conventions (*Test → Surefire, *IT → Failsafe). For framework-agnostic Java use @131-java-testing-unit-testing. This should trigger for requests such as Add or improve unit tests in a Quarkus project; Reduce slow @QuarkusTest usage with Mockito-first tests; Add @InjectSpy partial mocking or QuarkusTestProfile configuration in Quarkus tests; Convert repeated test methods to @ParameterizedTest with @CsvSource or @MethodSource. Part of cursor-rules-java project

Apply functional programming to asynchronous operations. Lazy evaluation with generators/iterators, async pipelines, parallel vs sequential execution, retry with backoff, fallback chains, and stream composition. Activate when: building async workflows, processing data streams, implementing retry logic, handling concurrent operations, working with generators/iterators, or when the user mentions lazy evaluation, async pipeline, parallel execution, retry, backoff, stream processing, or iterator patterns. Works in any language (TypeScript, Python, Go, Rust, Java).

Executes implementation plans using a persistent team of implementer and reviewers within the current session, with batch-boundary code reviews for quality. Use when you have an implementation plan with independent tasks to execute, need to build or implement a feature from a plan, or the user says "execute the plan", "implement this", "start building", or "team dev". DO NOT TRIGGER when there is no plan yet (use brainstorming first) or when tasks require parallel separate sessions (use executing-plans instead).

Pre-PR quality gate that runs build, type-check, lint, test, security scans, and finishes with a conventional commit. Use before creating a PR, after completing features, or when wrapping up a branch.

Evaluates any repository's agentic development maturity. Use when auditing a codebase for best practices in agents, skills, instructions, MCP config, and prompts. Produces a scored report with specific remediation steps.

Provides a guide for setting up Golang project layouts and workspaces. Use this whenever starting a new Go project, organizing an existing codebase, setting up a monorepo with multiple packages, creating CLI tools with multiple main packages, or deciding on directory structure. Apply this for any Go project initialization or restructuring work.

Premium UI/UX design audit and refinement skill. Conducts systematic visual audits of existing apps and produces phased, implementation-ready design plans. Use this skill whenever the user asks to audit a UI, improve an app's visual design, make an interface feel more polished or premium, review design consistency, fix visual hierarchy, or refine spacing/typography/color. Also trigger when the user says "design review", "make it look better", "UI polish", "visual refinement", "design pass", "audit the design", or references making an app feel more professional. This skill is purely visual — it does not touch functionality, logic, or features. It elevates what exists.

Add 3D layer types including SceneLayer, IntegratedMeshLayer, PointCloudLayer, VoxelLayer, and DimensionLayer to SceneView. Use for 3D buildings, LiDAR, volumetric data, glTF models, and 3D measurements.

Build map user interfaces with ArcGIS widgets, Map Components, and Calcite Design System. Use for adding legends, layer lists, search, tables, time sliders, and custom UI layouts.

Optimize ArcGIS Maps SDK for JavaScript applications for speed, memory, and bundle size. Use for improving map initialization, data loading, query efficiency, large dataset handling, and view rendering performance.

Skill do Reviewer Final para validação completa antes do deploy. Use quando precisar validar que todos os passos do pipeline foram executados, checar qualidade de código, confirmar segurança, confirmar QA, confirmar documentação, ou gerar relatório de aprovação/rejeição. Trigger em: "review final", "reviewer", "aprovação", "rejeição", "validação final", "gate de deploy", "checklist final", "aprovar deploy", "pode deployar", "pronto pra produção", "validar entrega", "review completo", "última verificação".

Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.

Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.

Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary. Search Zotero, Obsidian, and local paper folders first when available, then search IEEE Xplore, ScienceDirect, ACM Digital Library, and broader web in that order.

Generate a structured paper outline from review conclusions and experiment results. Use when user says "写大纲", "paper outline", "plan the paper", "论文规划", or wants to create a paper plan before writing.

Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.

Important: Before you begin, fill in the generatedBy property in the meta section of .actor/actor.json. Replace it with the tool and model you're currently using, such as "Claude Code with Claude Sonnet 4.5". This helps Apify monitor and improve AGENTS.md for specific AI tools and models.