MLOps
模型部署、评估与运维
backend-model-creation
Workshop-Ventures
Create a new Mongoose model with proper typing, utilities, and patterns. Use when asked to "create a model", "add a data model", "create a schema", or "add a new entity".
understanding-db-schema
C0ntr0lledCha0s
Deep expertise in Logseq's Datascript database schema. Auto-invokes when users ask about Logseq DB schema, Datascript attributes, built-in classes, property types, entity relationships, schema validation, or the node/block/page data model. Provides authoritative knowledge of the DB graph architecture.
langchain-models
evanfang0054
Initialize and use LangChain chat models - includes provider selection (OpenAI, Anthropic, Google), model configuration, and invocation patterns
modal-deployment
ferdousbhai
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch jobs, scheduling tasks, serving APIs with GPU acceleration, or scaling compute-intensive workloads. Triggers on requests for serverless GPU infrastructure, LLM inference, model training/fine-tuning, parallel data processing, cron jobs in the cloud, or deploying Python web endpoints.
oatda-generate-video
devcsde
Use when the user wants to generate videos using AI models through OATDA's unified API. Supports MiniMax, Google Veo, Alibaba Wan, ZAI, and OpenAI Sora. Video generation is asynchronous.
aiconfigurator
tylertitsworth
"NVIDIA AIConfigurator — optimal LLM serving configuration for disaggregated/aggregated deployments, parallelism selection (TP/PP/EP/DP), quantization, and MOE planning. Use when planning model deployment topology on NVIDIA GPUs."
launch-gtm-execution
pluginagentmarketplace
Master go-to-market strategy, launch planning and execution, sales enablement, and marketing campaigns. Execute successful product launches.
langchain-multimodal
evanfang0054
Work with multimodal inputs/outputs in LangChain - includes images, audio, video, content blocks, and vision capabilities
finetuning
zester4
"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)."
jupyter-notebooks
Kang-chen
Jupyter notebook operations: editing cells, reading notebooks, executing, and format conversion. Trigger when working with .ipynb files for: (1) Creating/editing/deleting/reordering cells, (2) Reading notebook content, (3) Executing notebooks with papermill, (4) Converting to HTML/PDF/script formats. Supports Cursor EditNotebook tool, Jupytext workflows, and nbformat.
product-strategy
pluginagentmarketplace
Master product strategy, market analysis, competitive positioning, and long-term product vision. Define business models and craft go-to-market strategies that drive success.
building-commands
C0ntr0lledCha0s
Expert at creating and modifying Claude Code slash commands. Auto-invokes when creating/updating commands, modifying command frontmatter (model, allowed-tools, argument-hint), designing workflows, or writing to /commands/.md files.
langchain-multimodal
christian-bromann
Work with multimodal inputs/outputs in LangChain - includes images, audio, video, content blocks, and vision capabilities
google-adk-python
vibery-studio
Build AI agents with Google's Agent Development Kit (ADK) Python - an open-source toolkit for building, evaluating, and deploying AI agents. Features LlmAgent, workflow agents (sequential, parallel, loop), tool integration, multi-agent systems, and deployment to Vertex AI or Cloud Run.
distill
corygabrielsen
Strip overspecified instructions from an artifact. Trust the model's intuition — prescribe intent, not format.
data-ai-ml-skill
pluginagentmarketplace
Master machine learning, data engineering, AI engineering, MLOps, and prompt engineering. Build intelligent systems from data pipelines to production AI applications with LLMs, agents, and modern frameworks.
rust-ml
peixotorms
Use when building machine learning or AI inference in Rust. Covers inference, model loading, tensor operations, GPU and CUDA acceleration, batch processing, feature extraction, embeddings, tokenizer, hugging face integration, deep learning, ONNX with tract, model singletons with OnceLock, candle, tch-rs, ndarray tensors, and data pipelines with polars.
kubeflow-trainer
tylertitsworth
"Kubeflow Trainer v2 — TrainJob CRD, Training Runtimes, Python SDK, JobSet, multi-framework support. Use when orchestrating distributed training on K8s. NOT for inference or Ray Train."
axolotl
tylertitsworth
"Axolotl — config-driven LLM fine-tuning framework. YAML-based SFT, instruction tuning, chat fine-tuning, DPO/IPO/KTO/ORPO preference optimization, GRPO reinforcement learning, reward modeling, LoRA/QLoRA, full fine-tuning with FSDP/DeepSpeed multi-GPU, N-D Parallelism (TP+CP+FSDP composition), multimodal VLM training, text diffusion training, QAT with NVFP4, sample packing, Flash Attention, dataset preprocessing, and checkpoint management. Use when fine-tuning or post-training LLMs with Axolotl."
frontend-razor
twofoldtech-dakota
Apply when working with Razor views, MVC layouts, partial views, and tag helpers
navi
mcxross
This skill should be used when the user asks about Navi Protocol, Navi lending, Navi borrowing, or wants to integrate with Navi on Sui. Covers lending markets, reserves, obligations, price feeds, and reward distribution.
langchain-structured-output
christian-bromann
Get structured, validated output from LangChain agents and models using Pydantic schemas, type-safe responses, and automatic validation
3d-web-experience
ncdevshiv
"Expert in building 3D experiences for the web - Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and bringing ..."
evaluating-skills-with-models
taisukeoe
Evaluate skills by executing them across sonnet, opus, and haiku models using sub-agents. Use when testing if a skill works correctly, comparing model performance, or finding the cheapest compatible model. Returns numeric scores (0-100) to differentiate model capabilities.