Generates code test-first — writes a failing test from a requirement, then generates the minimal code to pass it, then refactors, in strict red-green-refactor cycles. Use when building new features where the spec is clear, when the design is uncertain and you want tests to drive it, or when you need high confidence in coverage from the start.

Generates metamorphic tests — tests that check relationships between multiple runs instead of checking exact outputs, useful when the correct output is unknown or expensive to compute. Use when there's no oracle, when testing ML/numerical/search code, or when the spec describes properties rather than values.

Proves two program fragments semantically equivalent using symbolic reasoning — stronger than testing, applicable when differential testing is insufficient or impossible. Use when behavior preservation must be proven rather than sampled, when the input space is too large to enumerate, or when a transformation needs a correctness argument.

Translates a single function or small code unit between programming languages, mapping idioms and preserving observable behavior. Use when porting one function, when the user pastes code and asks for it in another language, or as the per-unit primitive for larger migrations.

Infrastructure as Code with Terraform and Terragrunt. Use this skill whenever the user mentions Terraform, Terragrunt, HCL, or infrastructure as code. Triggers include writing or reviewing .tf files, creating reusable modules, debugging terraform plan/apply errors, managing remote state and locks, fixing state drift, setting up CI/CD for Terraform, scaffolding new modules, validating module structure, and implementing Terragrunt DRY patterns across environments.

Reverse-engineering specialist that extracts specifications from existing codebases. Use when working with legacy or undocumented systems, inherited projects, or old codebases with no documentation. Invoke to map code dependencies, generate API documentation from source, identify undocumented business logic, figure out what code does, or create architecture documentation from implementation. Trigger phrases: reverse engineer, old codebase, no docs, no documentation, figure out how this works, inherited project, legacy analysis, code archaeology, undocumented features.

Use when building React 18+ applications in .jsx or .tsx files, Next.js App Router projects, or create-react-app setups. Creates components, implements custom hooks, debugs rendering issues, migrates class components to functional, and implements state management. Invoke for Server Components, Suspense boundaries, useActionState forms, performance optimization, or React 19 features.

Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning, instruction tuning, RLHF, DPO, or quantizing and deploying fine-tuned models. Trigger terms include: LoRA, QLoRA, PEFT, finetuning, fine-tuning, adapter tuning, LLM training, model training, custom model.

Use when building .NET 8 applications with minimal APIs, clean architecture, or cloud-native microservices. Invoke for Entity Framework Core, CQRS with MediatR, JWT authentication, AOT compilation.

[Deprecated: use baoyu-imagine] AI image generation with OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.

GDPR and German DSGVO compliance automation. Scans codebases for privacy risks, generates DPIA documentation, tracks data subject rights requests. Use for GDPR compliance assessments, privacy audits, data protection planning, DPIA generation, and data subject rights management.

App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on Apple App Store and Google Play Store. Use when the user asks about ASO, app store rankings, app metadata, app titles and descriptions, app store listings, app visibility, or mobile app marketing on iOS or Android. Supports keyword research and scoring, competitor keyword analysis, metadata optimization, A/B test planning, launch checklists, and tracking ranking changes.

Use when you need to implement acceptance tests from a Gherkin .feature file for Micronaut applications — @acceptance scenarios, @MicronautTest, HttpClient, BaseAcceptanceTest with TestPropertyProvider for Testcontainers and WireMock, *AT suffix, Failsafe. Requires the .feature file in context. This should trigger for requests such as Implement Micronaut acceptance tests from a Gherkin feature file; Set up BaseAcceptanceTest with Testcontainers and WireMock for Micronaut. Part of cursor-rules-java project

Use when you need to write unit tests for Micronaut applications — Mockito-first with @ExtendWith(MockitoExtension.class), @MicronautTest with @MockBean, HttpClient @Client(/) assertions, @Property overrides, @ParameterizedTest, and *Test vs *IT naming. For framework-agnostic Java use @131-java-testing-unit-testing. This should trigger for requests such as Add or improve unit tests in a Micronaut project; Reduce unnecessary @MicronautTest usage with Mockito-first tests. Part of cursor-rules-java project