Loading...
Loading...
Found 238 Skills
Implement API versioning with backward compatibility, deprecation notices, and migration paths. Use when managing API versions and backward compatibility. Trigger with phrases like "version the API", "manage API versions", or "handle API versioning".
Generate professional, Outlook-compatible email templates (EML + HTML) through natural conversation. Creates pixel-perfect newsletter layouts, announcement emails, weekly reports, event invitations, and any formatted email that needs to render correctly in Outlook. MUST use this skill when the user wants to: create or design an email template, generate an EML file, make a newsletter, format an email for Outlook, design a 邮件模板, do 邮件排版 or 邮件设计, create HTML email with Outlook compatibility, build a professional-looking email to send via Outlook, or produce any kind of formatted/styled email output. Also trigger when the user mentions: weekly report email (周报邮件), product update email, event invitation email (活动邀请邮件), announcement email (公告邮件), company newsletter, or wants to make an email "look professional/beautiful" for sending. This skill handles the visual design and EML generation — not email sending, SMTP setup, or email parsing. Without this skill, Outlook emails will have broken layouts because Outlook uses Word's rendering engine which ignores modern CSS.
Assess whether a project is ready for cloud-native deployment. Evaluates statelessness, config, scalability, and produces a readiness score (0-12). Use when user asks about containerization readiness, Docker/Kubernetes compatibility, deployment feasibility, whether their app can run in containers or the cloud, or wants a pre-deployment assessment. Also triggers on "/cloud-native-readiness".
Selects a base model and fine-tuning technique (SFT, DPO, or RLVR) for the user's use case by querying SageMaker Hub. Use when the user asks which model or technique to use, wants to start fine-tuning, or mentions a model name or family (e.g., "Llama", "Mistral") — always activate even for known model names because the exact Hub model ID must be resolved. Queries available models, validates technique compatibility, and confirms selections.
Use when checking code for functional correctness, backwards compatibility, logic errors, security vulnerabilities, performance issues, or missing test coverage — not style.
Build RAG pipelines with Exa.ai for real-time web retrieval. Use when building retrieval-augmented generation, integrating Exa with LangChain, LlamaIndex, Vercel AI SDK, or implementing AI agents with web search capabilities. Triggers on: RAG pipeline, retrieval augmented generation, Exa LangChain, Exa LlamaIndex, ExaSearchRetriever, ExaSearchResults, Exa MCP, Exa tool calling, Claude tool use, AI agent web search, grounded generation, citation generation, fact checking, hallucination detection, OpenAI compatibility, chat completions.
Apply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch make_graphed_callables, TE make_graphed_callables, MCore CudaGraphManager, FullCudaGraphWrapper, manual torch.cuda.graph), code compatibility, capture workflows, dynamic pattern handling, and troubleshooting. Triggers: CUDA graph, torch.cuda.graph, make_graphed_callables, reduce-overhead, graph capture, graph replay, kernel launch overhead, CudaGraphManager, FullCudaGraphWrapper, full-iteration graph, stream capture.
Create high-quality, secure, and performance-optimized Containerfiles (Dockerfiles) following best practices for multi-architecture builds, OpenShift/Kubernetes compatibility, and BuildKit cache optimization. Use when the user wants to: (1) create a new Containerfile or Dockerfile for any project (Python, Rust, Go, Node.js, .NET, or any language), (2) containerize an application with multi-stage builds, (3) optimize an existing Containerfile for security, performance, or image size, (4) review or improve container image build practices, (5) set up BuildKit cache mounts for package managers, (6) create OpenShift-compatible container images with non-root users and arbitrary UID support, (7) write a .dockerignore file, or (8) apply OCI LABEL standards.
Validates completeness and consistency of the project architecture against all GDDs. Builds a traceability matrix mapping every GDD technical requirement to ADRs, identifies coverage gaps, detects cross-ADR conflicts, verifies engine compatibility consistency across all decisions, and produces a PASS/CONCERNS/FAIL verdict. The architecture equivalent of /design-review.
Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.
CSS architecture and styling expert with deep knowledge of modern CSS features, responsive design, CSS-in-JS optimization, performance, accessibility, and design systems. Use PROACTIVELY for CSS layout issues, styling architecture, responsive design problems, CSS-in-JS performance, theme implementation, cross-browser compatibility, and design system development. If a specialized expert is better fit, I will recommend switching and stop.
Design Canvas-ready React components with slots and decomposition-first patterns. Use when (1) Designing a component's prop/slot structure, (2) A component is growing too large, (3) Deciding between props vs slots, (4) Refactoring monolithic components. Ensures Canvas compatibility.