全部能力

Divergent ideation and corpus expansion using Verbalized Sampling + extended thinking. Single-shot mode generates 5 internally diverse candidates (p<0.10 each)…

Build type-safe native platform integrations using MethodChannels, EventChannels, and Pigeon. Use when communicating with Android/iOS native code, implementing…

Use when adding interaction testing to Storybook stories. Enables automated testing of component behavior, user interactions, and state changes directly in…

Create HTML technical documentation with code blocks, API workflows, system architecture diagrams, and syntax highlighting. Use when users request technical…

Refactors route handlers into service layer with clean boundaries, dependency injection, testability, and separation of concerns. Provides service interfaces,…

Investigate sudden drops in organic traffic or rankings and run a structured forensic SEO incident response with triage, root-cause analysis and recovery plan.

Test trading strategies on historical data to evaluate performance, risks, and profitability.

Receive and verify SendGrid webhooks. Use when setting up SendGrid webhook handlers, debugging signature verification, or handling email delivery events.

Guides development with SAP AI Core and SAP AI Launchpad for enterprise AI/ML workloads on SAP BTP. Use when: deploying generative AI models (GPT, Llama, Gemini, Mistral), building orchestration workflows with templating/filtering/grounding, implementing RAG with vector databases, managing ML training pipelines with Argo Workflows, configuring content filtering and data masking for PII protection, using the Generative AI Hub for prompt experimentation, or integrating AI capabilities into SAP applications. Covers service plans (Free/Standard/Extended), model providers (Azure OpenAI, AWS Bedrock, GCP Vertex AI, Mistral, IBM), orchestration modules, embeddings, tool calling, and structured outputs.

Sequential release gate validating build success, test suite, security checks, type checking, manifest counts consistency, and changelog presence. Each step…

Use when designing Xiaohongshu post thumbnails or first images, creating eye-catching cover images, improving click-through rates, or A/B testing cover designs

Creates ephemeral preview deployments for each pull request with automatic deployment, unique URLs, and cleanup on PR close. Use for "preview deployments", "PR…

Expert in browser extension content scripts, DOM integration, and safe page augmentation across modern web apps.

Benchmark compensation against market data. Trigger with "what should we pay", "comp benchmark", "market rate for", "salary range for", "is this offer…

Production-grade end-to-end testing with Playwright. Covers test generation from user stories, page object patterns, locator strategy, flaky test diagnosis, Cypress/Selenium migration, CI integration, visual regression testing, and accessibility auditing. Use when writing E2E tests, fixing flaky tests, or migrating from Cypress/Selenium.

Builds and queries code knowledge graph for dependency analysis, references, implementations, and architecture overview. Use when starting work on unfamiliar…

Run workloads on Hugging Face Jobs with managed CPUs, GPUs, TPUs, secrets, and Hub persistence.

Creates reusable Terraform modules with proper structure, variables, outputs, and state management for infrastructure as code. Use when users request…

Investigate and fix CI failures on a pull request. Use when CI checks fail on a PR branch — covers finding the PR, identifying failed checks, downloading logs…

Run the full Stitch SDK generation pipeline. Use when a new tool is added, or the SDK needs to be regenerated end-to-end.