ML Ops
Machine learning operations
nano-banana-build
by cnemri
Generate and edit high-quality images using Gemini 2.5 Flash Image and Gemini 3 Pro Image (Nano Banana). Supports Text-to-Image, Style Transfer, Virtual Try-On, and Character Consistency.
faion-ai-agents
by faionfaion
"AI agents: autonomous agents, multi-agent systems, LangChain, LlamaIndex, MCP."
dspy
by L-yifan
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming
faion-ml-ops
by faionfaion
"ML operations: fine-tuning (LoRA, QLoRA), model evaluation, cost optimization, observability."
brandmint
by Sheshiyer
End-to-end brand identity orchestration system. Generates text strategy, visual assets, campaign copy, video deliverables, and publishing outputs using 44 specialized skills across 9 categories. Chains FAL.AI/Nano Banana/Flux visual generation with brand positioning, buyer personas, and campaign workflows via wave-based execution. Includes Remotion-based programmatic video generation.
sentence-transformers
by L-yifan
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.
aio-mental-models
by aiocean
This skill should be used when the user faces complex decisions, problem-solving, debugging, system design, strategic thinking, or needs structured reasoning. Comprehensive mental models framework with 50+ models covering first principles, second-order thinking, inversion, feedback loops, and more.
model-researcher
by IgorWarzocha
Add new/custom AI models to opencode.json. Use proactively for bleeding-edge releases, non-standard providers, self-hosted models, or custom endpoints. Examples: - user: "Add the new Claude 4.5" → websearch for API specs, add provider entry with baseUrl, verify model ID format - user: "Use my local Ollama instance" → configure custom provider with http://localhost:11434, set model ID format - user: "Configure this OpenAI-compatible proxy" → add provider with custom baseUrl, set apikey env var, verify compatibility - user: "Model X just released, add it" → research provider documentation, find model ID and capabilities, add to config
opencode-config
by IgorWarzocha
Edit opencode.json, AGENTS.md, and config files. Use proactively for provider setup, permission changes, model config, formatter rules, or environment variables. Examples: - user: "Add Anthropic as a provider" → edit opencode.json providers, add API key baseEnv var, verify with opencode run test - user: "Restrict this agent's permissions" → add permission block to agent config, set deny/allow for tools/fileAccess - user: "Set GPT-5 as default model" → edit global or agent-level model preference, verify model name format - user: "Disable gofmt formatter" → edit formatters section, set languages.gofmt.enabled = false
grey-haven-evaluation
by greyhaven-ai
"Evaluate LLM outputs with multi-dimensional rubrics, handle non-determinism, and implement LLM-as-judge patterns. Essential for production LLM systems. Use when testing prompts, validating outputs, comparing models, or when user mentions 'evaluation', 'testing LLM', 'rubric', 'LLM-as-judge', 'output quality', 'prompt testing', or 'model comparison'."
plan-down
by VCnoC
Method clarity-driven planning workflow using zen-mcp tools (chat, planner, consensus). Phase 0 uses chat to judge if user provides clear implementation method. Four execution paths based on automation_mode × method clarity - Interactive/Automatic × Clear/Unclear. All paths converge at planner for task decomposition. Produces complete plan.md file. Use when user requests "create a plan", "generate plan.md", "use planner for planning", "help me with task decomposition", or similar planning tasks.
skool-money-model-strategist
by DaronVee
Applies Alex Hormozi's $100M Money Models frameworks to design, evaluate, and improve Skool community monetization strategies. Uses CAC-based stage diagnosis (5 stages), 30-day cash maximization formulas, and sequential implementation to create actionable roadmaps grounded in Hormozi's 15 money model mechanisms and Skool's 5 business models (Free, Subscription, Freemium, Tiers, One-Time). Helps Skool community owners identify which mechanisms to implement, validate money models against Hormozi principles, and create step-by-step Skool setup instructions for maximum revenue per customer in 30 days.
competitor-analysis
by assimovt
Analyze competitive landscape with feature matrices, positioning maps, and strategic gap analysis. Use when asked to analyze competitors, map the competitive landscape, find differentiation, or evaluate alternatives to a product.
ml-ablation-design
by dongzhuoyao
Use when designing ablation studies to compare model components, loss functions, or architectural choices. Covers synthetic data experiments, variant loops, production metrics, and W&B grouping. Triggers: "ablation", "ablation study", "variant comparison", "controlled experiment", "synthetic data experiment"
hydra-experiment-config
by dongzhuoyao
Use when structuring ML experiment configs with Hydra, adding new config groups, or debugging config resolution. Applies to any project using Hydra for hyperparameter management. Triggers: "Hydra", "config", "yaml config", "OmegaConf", "config groups", "defaults list", "config override"
slurm-gpu-training
by dongzhuoyao
Use when running ML training on HPC clusters with Slurm, including job submission, environment setup, monitoring, and failure triage. Applies to any GPU training workload on Slurm-managed clusters. Triggers: "sbatch", "srun", "Slurm", "SBATCH", "job submission", "HPC", "cluster", "walltime", "squeue"
gpu-training-acceleration
by dongzhuoyao
Use when optimizing PyTorch training speed or memory on CUDA GPUs — global flags, torch.compile, fused optimizers, mixed precision, gradient checkpointing, kernel fusion, memory layout, or latent-space training. Applies to any PyTorch training workload. Triggers: "torch.compile", "TF32", "fused optimizer", "mixed precision", "bf16", "fp16", "gradient checkpointing", "Triton kernel", "CUDA flags", "GPU slow", "GPU memory"
fail-fast-ml-engineering
by dongzhuoyao
Use when designing ML training pipelines, data loaders, or inference systems. Enforces engineering discipline — no silent fallbacks, explicit errors on critical paths, config as single source of truth. Triggers: "silent failure", "fallback", "preflight", "assertion", "error handling", "fail fast", "config truth"
pydantic-ai-agents
by Fuenfgeld
"Build and debug Pydantic AI agents using best practices for dependencies, dynamic system prompts, tools, and structured output validation. Use when the user wants to: (1) Create a new Pydantic AI agent, (2) Debug or fix an existing agent, (3) Add features like tools, validators, or dynamic prompts, (4) Integrate OpenRouter for multi-model access, (5) Add Logfire for debugging/observability, (6) Structure agent architecture with dependency injection."
wandb-experiment-tracking
by dongzhuoyao
Use when integrating W&B experiment tracking into ML training pipelines, including logging strategy, run configuration, and online/offline mode management. Triggers: "W&B", "wandb", "weights and biases", "experiment logging", "wandb.log", "wandb.init", "training dashboard"
vercel-ai-sdk
by wsimmonds
Guide for Vercel AI SDK v5 implementation patterns including generateText, streamText, useChat hook, tool calling, embeddings, and MCP integration. Use when implementing AI chat interfaces, streaming responses, tool/function calling, text embeddings, or working with convertToModelMessages and toUIMessageStreamResponse. Activates for AI SDK integration, useChat hook usage, message streaming, or tool calling tasks.
matlab-medical-imaging-toolbox
by rrmaram2000
"MATLAB Medical Imaging Toolbox. Functions - medicalVolume, dicomread, dicominfo, dicomCollection, niftiread, niftiinfo, nrrdread, medicalref3d, intrinsicToWorld, worldToIntrinsic, volshow, sliceViewer, imregmoment, imregdeform, imregtform, radiomics, intensityFeatures, shapeFeatures, textureFeatures, medicalSegmentAnythingModel, segmentCells2D, dicomConnection, dicomquery, dicomget. Tasks - load medical scans, read DICOM series, open NIfTI or NRRD files, convert patient and voxel coordinates, visualize 3D volumes, overlay segmentation, align MRI or CT scans, register pre and post treatment images, extract radiomics features, segment with MedSAM or Cellpose, connect to PACS server, label ground truth, resample to isotropic spacing. Domains - DICOM, NIfTI, NRRD, MRI, CT, PET, PET/CT fusion, ultrasound, X-ray, brain imaging, liver segmentation, cardiac imaging, lung nodules, tumor analysis, clinical workflows, PACS integration."
matlab-deep-learning
by rrmaram2000
"MATLAB Deep Learning Toolbox. Functions - trainNetwork, trainnet, trainingOptions, unetLayers, unet, deeplabv3plusLayers, deeplabv3plus, semanticseg, yolov4ObjectDetector, fasterRCNNObjectDetector, maskrcnn, resnet50, vgg16, efficientnetb0, dlarray, dlfeval, dlgradient, adamupdate, dlnetwork, imageDatastore, augmentedImageDatastore, minibatchqueue. Tasks - train a deep learning model, classify medical images, build a CNN classifier, segment tumors or organs, detect objects or nodules in images, fine-tune a pretrained network, set up transfer learning, create a U-Net for segmentation, train with custom loss function, augment training data, deploy model to ONNX, run training on GPU, build a 3D volumetric network, compare model architectures, improve training accuracy, reduce overfitting, handle class imbalance. Domains - MRI, CT, X-ray, PET, histopathology, dermatology, retinal imaging, cell detection, medical image classification, lesion segmentation, nodule detection, pathology grading."
matlab-stats-ml
by rrmaram2000
"MATLAB Statistics and Machine Learning Toolbox. Functions - fitcsvm, fitctree, fitcensemble, fitcknn, fitcnb, fitcnet, fitlm, fitglm, fitrgp, fitrensemble, lasso, kmeans, linkage, fitgmdist, dbscan, pca, tsne, factoran, ttest, ttest2, anova1, anovan, ranksum, chi2gof, fitdist, makedist, mle, ecdf, coxphfit, cvpartition, crossval, kfoldLoss, perfcurve, confusionchart, bayesopt, shapley, normalize. Tasks - run t-test or ANOVA, fit distributions, classify patients, train SVM or random forest, predict with regression, cluster data, reduce dimensions with PCA or t-SNE, cross-validate, compute ROC and AUC, select features, optimize hyperparameters, analyze survival data, plot Kaplan-Meier curves, handle missing data, interpret with SHAP or LIME. Domains - biomarker discovery, clinical trials, patient outcome prediction, diagnostic classification, gene expression, proteomics, epidemiology, survival analysis, treatment comparison."