32 skills
Configure LoRA and QLoRA supervised fine-tuning with current best-practice hyperparameters. Use when writing or reviewing a LoRA/QLoRA training configuration, choosing rank/alpha/target modules, or deciding between LoRA, QLoRA, and full fine-tuning.
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useCh
Generate embeddings via npx ruvector@0.2.25 embed text (ONNX all-MiniLM-L6-v2, 384-dim), normalize, and store in HNSW index
Builds local vector search, RAG, embeddings, and semantic search on the Azure SQL Database container using the native VECTOR type and VECTOR_DISTANCE. Use when you need to store embeddings, do similarity search, top-k nearest neighbor, cosine distance, retrieval-augmented generation, "find similar documents", chatbot memory, or semantic lookup against a local SQL database. Use this instead of pgvector, FAISS, Chroma, Pinecone, or a separate vector store when the data already lives in (or can live in) Azure SQL. Covers the VECTOR(n) column type, inserting embeddings with CAST(CAST(? AS NVARCHAR
Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.
Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation", or needs vision-capable AI generation.
Generate HeyGen presenter videos via the v3 Video Agent pipeline — handles Frame Check (aspect ratio correction), prompt engineering, avatar resolution, and voice selection. Required for any HeyGen video generation. Replaces deprecated endpoints with v3. Use when: (1) generating any HeyGen video (via API or otherwise), (2) sending a personalized video message (outreach, update, announcement, pitch, knowledge), (3) creating a HeyGen presenter-led explainer, tutorial, or product demo with a human face, (4) "make a video of me saying...", "send a video to my leads", "record an update for my team"
When the user wants to create, generate, or produce video content using AI tools or programmatic frameworks. Also use when the user mentions 'video production,' 'AI video,' 'Remotion,' 'Hyperframes,' 'HeyGen,' 'Synthesia,' 'Veo,' 'Sora,' 'Runway,' 'Kling,' 'Seedance,' 'Hailuo,' 'MiniMax,' 'Pika,' 'Hunyuan,' 'Wan,' 'video generation,' 'AI avatar,' 'talking head video,' 'programmatic video,' 'video template,' 'explainer video,' 'product demo video,' 'video pipeline,' 'copy this edit,' 'match this video style,' 'reverse-engineer this video,' 'edit like this reference,' or 'make me a video.' Use t
Use the `quickdesign` CLI to generate AI media — UGC promo videos, image edits, product creatives, video upscales — through Seedance, Kling, Sora2, Nano Banana, and GPT Image. Invoke this skill whenever the user asks for a talking-avatar video, multi-segment ad / promo / explainer, image edit (object swap, angle change, state change), product photoshoot, or video upscale via QuickDesign.
Decide whether to fine-tune at all, and route to the right method (SFT, DPO/ORPO/KTO, GRPO/RLVR, continued pretraining) and base model. Use when starting any fine-tuning effort, when unsure whether RAG or prompting would suffice, or when choosing between preference-optimization and reinforcement methods.
Drop-in inspector panel for any json-render app. Use when the user wants to debug a generative UI, inspect the spec tree, edit state at runtime, see dispatched actions, follow stream patches live, browse a catalog, or pick DOM elements to find their spec keys. Triggers include "add devtools", "debug json-render", "inspect the spec", "why is this element not rendering", "see the state at runtime", or requests to tap streams / capture action logs for `@json-render/devtools`.
SOTA semantic search — hybrid (sparse+dense), Graph RAG multi-hop, MMR diversity reranking, recency weighting
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).
Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and batch-capable image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
Translate and dub a video into another language with voice cloning and lip-sync, powered by HeyGen Video Translation. The presenter keeps their face, their voice is cloned into the target language, and lips re-sync to the new audio — viewers see the same person speaking natively. Use when: (1) localizing an existing video into one or more languages ("translate this video to Spanish", "make this in French and German", "dub this into Japanese", "I need this in 10 languages for a launch"), (2) the user has a finished video and wants the SAME presenter speaking another language (not a new presente
When the user wants to create, generate, edit, or optimize images for marketing — blog heroes, social graphics, product mockups, profile banners, listing visuals, or brand assets. Also use when the user mentions 'AI image generation,' 'generate an image,' 'create a graphic,' 'product mockup,' 'hero image,' 'social media graphic,' 'banner image,' 'cover photo,' 'profile banner,' 'listing screenshot,' 'Flux,' 'Flux Kontext,' 'Midjourney,' 'DALL-E,' 'GPT Image,' 'ChatGPT Images,' 'Ideogram,' 'Gemini image,' 'Nano Banana,' 'Recraft,' 'Stable Diffusion,' 'Canva,' 'Figma,' 'image optimization,' 'com
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Prepare, format, and validate datasets for supervised fine-tuning and preference training. Use when converting raw data into training format, applying chat templates, configuring sequence packing, generating synthetic training data, or writing a dataset card before a run.
Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.
One-shot chat completion against DeepSeek's `deepseek-chat` model via the OpenAI-compatible /v1/chat/completions endpoint. Reads DEEPSEEK_API_KEY from the environment; degrades gracefully (exit 0 with a JSON status:degraded envelope) when the key is missing or the API is unreachable. Use for non-reasoning tasks — summarization, extraction, quick classification — where deepseek-reasoner would be overkill.
Create a persistent HeyGen avatar — a reusable face + voice identity for the agent, the user, or any named character — powered by HeyGen Avatar V technology. Prompt-based creation by default (description → HeyGen builds it); photo upload is optional for real-person digital twins. Use when: (1) giving the agent a face + voice so it can present videos ("bring yourself to life", "create your avatar", "give yourself an avatar", "design a presenter", "set up an avatar", "let's make an avatar"), (2) the user wants to appear in videos as themselves ("create my avatar", "I want my face in a video", "d
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
Migrate applications from AI SDK 6.x to AI SDK 7.0. Use when upgrading Vercel AI SDK packages, fixing v7 migration errors, or when the user mentions AI SDK v6, v7, upgrade, migration, breaking changes, system to instructions, fullStream, telemetry, tool context, or finalStep.
