Dominodatalab

Skills (26)

Claude uses these on its own when your request matches.

• domino-ai-gatewayAccess external LLM providers through Domino AI Gateway - a secure proxy with centralized API key management, usage monitoring, and compliance. Supports OpenAI, AWS Bedrock, Azure OpenAI, Anthropic, and more. Use when calling LLMs from Domino, configuring AI Gateway endpoints,…
• domino-appsDeploy web applications to Domino Data Lab with expertise in React apps (Vite) behind Domino's reverse proxy. Covers app.sh configuration, port configuration, base path handling for SPAs, CI/CD with GitHub Actions, and proxy troubleshooting. Use when deploying apps to Domino,…
• domino-data-connectivityConnect Domino workloads to external data sources including AWS S3 (via Mountpoint CSI driver), credential propagation with AWS IRSA and Azure Entra ID, and External Data Volumes. Use when configuring S3 access, setting up credential propagation, or connecting to cloud data…
• domino-datasetsWork with Domino Datasets - high-performance, versioned filesystem storage. Covers dataset creation, snapshots for versioning, sharing across projects, mounting paths (/domino/datasets/), and performance optimization. Use when managing data storage, creating reproducible data…
• domino-distributed-computingWork with distributed computing frameworks in Domino including Apache Spark, Ray, and Dask clusters. Covers cluster configuration, on-demand clusters, choosing between frameworks, PySpark usage, and scaling workloads. Use when processing large datasets, parallel ML training, or…
• domino-api-introIntroduction to calling Domino platform APIs. Covers authentication (API proxy, PAT, service account), which host to use for which API, pagination limits, and common errors. Use before any other Domino API, SDK, app, extension, or governance automation skill.
• domino-data-sdkUse the domino-data Python SDK (dominodatalab-data) for programmatic data access in Domino. Covers DataSourceClient for SQL queries and object storage, DatasetClient for dataset files, TrainingSets for ML data versioning, Feature Store, and VectorDB (Pinecone) integration. Use…
• domino-extensionsBuild and operate Domino UI Extensions (mount Domino Apps in the shell with page context). Covers extension_manifest.json, official installer vs manual Extension API, publish and identity requirements, auth and host splits, and beta REST routes. Use when creating an Extension,…
• domino-governanceManage model risk governance in Domino using policies, bundles, and evidence. Covers creating governance bundles, attaching model artifacts and MLflow results as evidence, progressing through policy stages, and documenting findings. Use when the user mentions governance,…
• domino-model-servingDeploy, invoke, and retire Domino model APIs and registered models via REST. Covers modelServing lifecycle, registered-models v1 vs v2 paths, MLflow tracking vs registry API, inference URLs vs management API, and GenAI endpoint vanity URLs. Use when automating model deployment,…
• domino-ui-bootstrapBootstrap or retrofit a Vite + React 18 + TypeScript project so it uses the Domino design system (`@dominodatalab/extensions-tools`). Scoped to projects that are (or will be) a fully standalone SPA frontend for a Domino application or extension — not snippets, library…
• domino-ui-designBuild Domino-styled web applications matching the Domino Design System. Use when creating or styling Domino apps (Dash, Streamlit, Flask, FastAPI+HTML), generating UI components, reviewing UX, or when the user mentions "Domino app", "Domino UI", "Domino dashboard", or "Domino…
• domino-environmentsCreate and customize Domino Compute Environments - Docker containers defining tools, packages, and configurations. Covers Dockerfile customization, package installation, IDE configuration, DSE (Domino Standard Environments), and troubleshooting build failures. Use when…
• domino-experiment-trackingTrack traditional ML experiments in Domino using the MLflow-based Experiment Manager. Covers experiment setup, auto-logging for sklearn/TensorFlow/PyTorch, manual logging, artifact storage, run comparison, and model registration. Use when training ML models, logging metrics and…
• domino-flowsOrchestrate multi-step ML workflows using Domino Flows (built on Flyte). Define DAGs with typed inputs/outputs, heterogeneous environments, automatic lineage, and reproducibility. Use when building data pipelines, multi-stage training workflows, or processes requiring…
• domino-genai-tracingTrace and evaluate GenAI applications including LLM calls, agents, RAG pipelines, and multi-step AI systems in Domino. Uses the Domino SDK (@add_tracing decorator, DominoRun context) with MLflow 3.2.0. Captures token usage, latency, cost, tool calls, and errors. Supports…
• domino-jobsCreate, run, and manage Domino Jobs - batch executions for scripts, training, and data processing. Covers job configuration, hardware tiers, scheduled jobs (cron), monitoring status, viewing logs, and API-driven execution. Use when running batch workloads, scheduling recurring…
• domino-launchersCreate Domino Launchers - parameterized web forms for self-service job execution. Enable business users to run analyses, generate reports, and trigger batch predictions without coding. Covers parameter types, email notifications, result delivery, and access control. Use when…
• domino-model-endpointsDeploy and monitor model API endpoints in Domino. Covers creating prediction endpoints, version management, Grafana dashboards for latency/errors/resources, alerting, and GPU inference with NVIDIA Triton. Use when deploying models as APIs, monitoring production endpoints, or…
• domino-model-monitoringMonitor deployed models in Domino including drift detection, model quality tracking, and alerting. Covers data drift analysis, prediction capture, baseline comparison, alert configuration, and remediation workflows. Use when monitoring production models, detecting drift, or…
• domino-modeling-assistantEnable AI-assisted model development within Domino by writing needed model and training code and using MCP (Model Context Protocol) servers to execute domino jobs. AI coding assistants like Cursor and GitHub Copilot can execute commands as Domino jobs, maintaining security,…
• netapp-volumesWork with Domino Volumes for NetApp ONTAP - enterprise-grade, multi-terabyte storage with near-instant snapshots. Covers volume creation, snapshot versioning with commit messages, cross-project sharing, mount paths (/mnt/netapp-volumes/ or /domino/netapp-volumes/), and the…
• domino-projectsWork with Domino Projects including Git integration, DFS vs Git-based projects, collaboration, and version control. Covers project creation, Git provider setup (GitHub, GitLab, Bitbucket), branch management, collaborator permissions, and project settings. Use when creating…
• domino-python-sdkProgrammatically interact with Domino using python-domino SDK and REST APIs. Covers authentication, running jobs, managing projects, file operations, model deployment, and automation. Use when automating Domino workflows, integrating with CI/CD, or building custom tooling…
• tags-and-propertiesManage Domino tags and properties via the Taxonomy API. Covers tags/namespaces (create, list, update, delete; tag entities — project, model, dataset, app, project_template, netapp_volume; query by tag; autocomplete; merge; CSV import/export) AND properties (typed metadata…
• domino-workspacesWork with Domino Workspaces - interactive development environments including Jupyter, JupyterLab, VS Code, and RStudio. Covers launching workspaces, configuring hardware tiers, environment selection, volume mounting, SSH access, and package installation. Use when setting up…

MCP server

Added to Claude Code when you install the plugin. You sign in to Dominodatalab the first time it is used.

• domino_serverLocaluv --directory $/mnt/code/.claude/mcp-servers/domino_mcp_server run domino_mcp_server.py

Agents (3)

Specialized helpers Claude can hand work to.

• domino-debugSpecialized agent for debugging Domino issues including app deployment problems, job failures, environment build errors, and connectivity issues. Use PROACTIVELY when troubleshooting errors or unexpected behavior in Domino.
• domino-deploySpecialized agent for deploying applications, models, and endpoints to Domino. Use PROACTIVELY when deploying React/Streamlit/Dash apps, publishing model APIs, or configuring deployments.
• domino-setupSpecialized agent for setting up new Domino projects, environments, and configurations. Use PROACTIVELY when starting a new project, configuring experiment tracking, setting up GenAI tracing, or initializing project structure.

Commands (4)

Shortcuts you type in Claude Code.

• /domino-app-initInitialize a new Domino-ready web application with Vite+React, Streamlit, Dash, or Flask. Configures proxy-compatible settings and app.sh.
• /domino-debug-proxyDebug Domino proxy and routing issues for web applications. Analyzes vite.config.js, package.json, and app.sh for misconfigurations.
• /domino-experiment-setupSet up MLflow experiment tracking for traditional ML. Configures unique experiment names and auto-logging.
• /domino-trace-setupSet up GenAI tracing for an agent or LLM application. Adds Domino SDK imports, @add_tracing decorators, and DominoRun context.

Install

claude plugin install dominodatalab@claude-plugins-official

/plugin install dominodatalab@claude-plugins-official