{ "markdown": "

\n \n \"DataRobot\n \n

\n

\n DataRobot Agent Skills\n

\n\n

\n Homepage\n ·\n Documentation\n ·\n Support\n

\n\n

\n \n \"Slack\n \n

\n\nAgentic skills for DataRobot enterprise AI and agent workflows.\n\n```bash\nnpx ai-agent-skills install datarobot-oss/datarobot-agent-skills\n```\n\n## Overview\n\nAgentic skills are modular, task-specific capability packages that help an AI agent move from general reasoning to reliable execution. Each skill bundles instructions, examples, and supporting resources so that the agent can load only what it needs for the current task, reducing context overload and improving tool use within a given workflow.\n\nDataRobot skills are Agent Context Protocol (ACP) definitions for enterprise AI and agent workflows, including building, deploying, and governing agents, as well as AI/ML tasks such as model training, deployment, predictions, feature engineering, and monitoring. They work with major coding agents, including OpenAI Codex, Anthropic Claude Code, Google Gemini CLI, Cursor, and VS Code Copilot.\n\n> [!NOTE]\n> \"Skills\" is an Anthropic term used in Claude AI and Claude Code, but the concept applies more broadly. OpenAI Codex uses `AGENTS.md` to define agent instructions, and Gemini uses `gemini-extension.json` for extensions. This repository is compatible with all of them, and more.\n\n## Quick start\n\n> [!NOTE]\n> Supported agents for DataRobot skills include: [Claude Code](https://www.anthropic.com/claude-code/), [Cursor](https://cursor.com), [Codex](https://developers.openai.com/codex/), [Amp](https://ampcode.com/), [VS Code Copilot (GitHub Copilot)](https://github.com/features/copilot), [Gemini CLI](https://geminicli.com/), [Goose](https://block.github.io/goose/), [Letta](https://www.letta.com/), [Kilo Code](https://kilocode.ai/), [OpenCode](https://opencode.ai/), and [Windsurf/Devin](https://devin.ai/).\n\nInstall all DataRobot skills, or only the ones you need, for **all** your AI agents with one command by using the [universal skills installer](https://github.com/skillcreatorai/Ai-Agent-Skills).\n\n**For all skills:**\n\n```bash\nnpx ai-agent-skills install datarobot-oss/datarobot-agent-skills\n```\n\n**For a specific skill:**\n\n```bash\nnpx ai-agent-skills install datarobot-oss/datarobot-agent-skills/skills/datarobot-predictions\n```\n\n**For a specific agent:**\n\n```bash\nnpx ai-agent-skills install datarobot-oss/datarobot-agent-skills --agent cursor\nnpx ai-agent-skills install datarobot-oss/datarobot-agent-skills --agent claude\n```\n\n> [!NOTE]\n> By default, the installer copies skills to all supported agents at the same time. No configuration is required.\n> For agent-specific installation methods, see the [Installation to your coding agent](#installation-to-your-coding-agent) section below.\n\n### How do skills work?\n\nSkills are self-contained folders that package instructions, scripts, and resources for a specific use case. Each folder includes a `SKILL.md` file with YAML frontmatter (`name` and `description`), followed by the guidance your coding agent uses while the skill is active.\n\n> [!NOTE]\n> All DataRobot skills follow the naming convention `datarobot-`, where `` describes the skill's focus area. This provides clear identification of DataRobot-specific skills, consistent naming across the skill library, and easy discovery and organization.\n\n### Installation to your coding agent\n\nDataRobot skills are compatible with Claude Code, Codex, Gemini CLI, Cursor, VS Code Copilot, Windsurf/Devin, and more. For the universal `npx` installer, see [Quick start](#quick-start) above.\n\nClick on the section that corresponds to your coding agent below for agent-specific installation instructions.\n\n
Claude Code\n\nInstall all DataRobot skills from the official Claude plugins marketplace.\n\nFrom your terminal:\n\n```bash\nclaude plugin install datarobot-agent-skills@claude-plugins-official\n```\n\nFrom within a Claude Code CLI session:\n\n```bash\n/plugin install datarobot-agent-skills@claude-plugins-official\n```\n\n**Alternative:** register the repository as a plugin marketplace from within a Claude Code CLI session:\n\n```bash\n/plugin marketplace add datarobot-oss/datarobot-agent-skills\n```\n\nTo install a specific skill, run:\n\n```bash\n/plugin install @datarobot-skills\n```\n\nFor example:\n\n```bash\n/plugin install datarobot-model-training@datarobot-skills\n```\n\n
\n\n
Codex\n\nCodex identifies the skills through the `AGENTS.md` file. You can verify that the instructions are loaded by running:\n\n```bash\ncodex --ask-for-approval never \"Summarize the current instructions.\"\n```\n\nFor more details, see the [Codex `AGENTS.md`](https://developers.openai.com/codex/guides/agents-md) documentation.\n\n
\n\n
Gemini CLI\n\nThis repository includes `gemini-extension.json` for Gemini CLI integration.\n\nInstall locally:\n\n```bash\ngemini extensions install . --consent\n```\n\nOr install from the GitHub URL:\n\n```bash\ngemini extensions install https://github.com/datarobot-oss/datarobot-agent-skills.git --consent\n```\n\nSee the [Gemini CLI extensions](https://geminicli.com/docs/extensions/) documentation for more information.\n\n
\n\n
Cursor\n\nCursor can automatically detect and use skills from this repository in two main ways:\n\n**Option 1: Use `AGENTS.md`**\n\n> NOTE: This option is the recommended approach.\n\nWhen you open this repository as your workspace, Cursor automatically reads the `AGENTS.md` file. The skills are available immediately without additional configuration.\n\nTo verify that the skills are loaded:\n\n1. Open Cursor in this repository.\n2. Open the AI chat panel (`Cmd/Ctrl + L`).\n3. Ask: \"What DataRobot skills are available?\"\n\n**Option 2: Use `.cursorrules`**\n\nYou can also reference specific skills in your `.cursorrules` file to make sure they are always loaded:\n\n```text\n# .cursorrules\nYou have access to DataRobot skills in this repository.\n\nAvailable skills (in datarobot-* folders):\n- datarobot-model-training: Model training and project creation\n- datarobot-predictions: Making predictions and generating templates\n- datarobot-model-deployment: Deploying and managing models\n- datarobot-feature-engineering: Feature analysis and engineering\n- datarobot-model-monitoring: Model performance monitoring\n- datarobot-model-explainability: Model explainability and diagnostics\n- datarobot-data-preparation: Data upload and validation\n- datarobot-app-framework-cicd: CI/CD pipelines for DataRobot application templates\n- datarobot-external-agent-monitoring: External agent OTel instrumentation for DataRobot monitoring\n- datarobot-agent-assist: Building and deploying agents\n- datarobot-setup: Local DataRobot development setup (SDK, dr-cli, Agent Assist)\n- datarobot-workload-api: Create, configure, debug, observe, and roll out container workloads on DataRobot's Workload API\n\nWhen asked to use a DataRobot skill, read the corresponding SKILL.md file for detailed guidance.\n```\n\n**Using skills in Cursor:**\n\n- \"Use the datarobot-predictions skill to generate a template for deployment abc123\"\n- \"Follow the datarobot-model-training skill to create a new project\"\n- \"Check the datarobot-model-monitoring skill to analyze data drift\"\n\n
\n\n
VS Code Copilot (GitHub Copilot)\n\nVS Code with GitHub Copilot can automatically detect and use skills from this repository through the `AGENTS.md` file.\n\n**Setup:**\n\n1. Open this repository in VS Code.\n2. Ensure that the GitHub Copilot extension is installed and activated.\n3. Skills are automatically available through the `AGENTS.md` file.\n\n**Verify that the skills are loaded:**\n\nOpen Copilot Chat (`Cmd/Ctrl + I`) and ask:\n\n- \"What DataRobot skills are available?\"\n- \"List the available skills in this repository\"\n\n**Using skills in VS Code Copilot:**\n\nIn Copilot Chat, reference skills naturally:\n\n- \"Use the datarobot-predictions skill to generate a template for deployment abc123\"\n- \"Following the datarobot-model-training skill, create a new project for customer churn prediction\"\n- \"Check the datarobot-model-monitoring skill and help me analyze data drift\"\n\n> [!TIP]\n> You can also use the `@workspace` agent in Copilot Chat to give it full context about the repository and available skills.\n\n
\n\n
OpenCode\n\nAdd to your `~/.config/opencode/opencode.json`:\n\n```json\n{\n \"plugin\": [\"opencode-datarobot-skills\"]\n}\n```\n\nOpenCode automatically installs the plugin on startup. The plugin also includes a DataRobot-branded theme with full dark and light variants. To activate it, add `\"theme\": \"datarobot\"` to your `opencode.json`.\n\n
\n\n
Windsurf/Devin\n\n[Windsurf](https://windsurf.com/) and [Devin](https://devin.ai/) support the Agent Skills format. Install DataRobot skills using the universal installer from [Quick start](#quick-start) above.\n\n**Install all skills:**\n\n```bash\nnpx ai-agent-skills install datarobot-oss/datarobot-agent-skills\n```\n\n**Install a specific skill:**\n\n```bash\nnpx ai-agent-skills install datarobot-oss/datarobot-agent-skills/skills/datarobot-predictions\n```\n\n
\n\n## Skills\n\nThis repository contains skills for common DataRobot workflows. You can also contribute your own skills.\n\n### Available skills\n\n| Skill Folder | Description | Documentation |\n| ------------ | ----------- | ------------- |\n| `skills/datarobot-model-training/` | Instructions and utilities for training models, managing projects, and running AutoML experiments. | [SKILL.md](skills/datarobot-model-training/SKILL.md) |\n| `skills/datarobot-model-deployment/` | Tools for deploying models, managing deployments, and configuring prediction environments. | [SKILL.md](skills/datarobot-model-deployment/SKILL.md) |\n| `skills/datarobot-predictions/` | Guidance for making predictions, batch scoring, real-time predictions, and generating prediction datasets. | [SKILL.md](skills/datarobot-predictions/SKILL.md) |\n| `skills/datarobot-feature-engineering/` | Instructions for feature engineering, feature discovery, and feature importance analysis. | [SKILL.md](skills/datarobot-feature-engineering/SKILL.md) |\n| `skills/datarobot-model-monitoring/` | Tools for monitoring model performance, tracking data drift, and managing model health. | [SKILL.md](skills/datarobot-model-monitoring/SKILL.md) |\n| `skills/datarobot-model-explainability/` | Tools for model explainability, prediction explanations, SHAP values, and model diagnostics. | [SKILL.md](skills/datarobot-model-explainability/SKILL.md) |\n| `skills/datarobot-data-preparation/` | Utilities for data upload, dataset management, and data validation. | [SKILL.md](skills/datarobot-data-preparation/SKILL.md) |\n| `skills/datarobot-app-framework-cicd/` | Set up CI/CD pipelines for DataRobot application templates with GitLab and GitHub Actions. | [SKILL.md](skills/datarobot-app-framework-cicd/SKILL.md) |\n| `skills/datarobot-external-agent-monitoring/` | Instrument any external AI agent with OpenTelemetry to send traces, logs, and metrics to DataRobot for monitoring and observability. Supports Google ADK, LangChain, LangGraph, CrewAI, LlamaIndex, PydanticAI, and generic Python agents. | [SKILL.md](skills/datarobot-external-agent-monitoring/SKILL.md) |\n| `skills/datarobot-agent-assist/` | Build AI agents and deploy them to DataRobot. Supports building LangGraph, CrewAI, LlamaIndex, NAT and Base agents. Created agents can be bundled with MCP server, backend APIs & React frontend. | [SKILL.md](skills/datarobot-agent-assist/SKILL.md) |\n\n## Using skills in your coding agent\n\nOnce a skill is installed, mention it directly in your instructions to the coding agent:\n\n- \"Use the DataRobot model training skill to create a new project and start AutoML training.\"\n- \"Use the DataRobot predictions skill to generate a prediction dataset template for deployment abc123.\"\n- \"Use the DataRobot feature engineering skill to analyze feature importance for my model.\"\n- \"Use the DataRobot model monitoring skill to check data drift for deployment xyz789.\"\n- \"Use the DataRobot external agent monitoring skill to instrument my agent for DataRobot monitoring.\"\n\nYour coding agent automatically loads the corresponding `SKILL.md` instructions and any helper scripts it needs while completing the task.\n\n### Helper scripts\n\nSome skills include helper scripts that an agent can run directly:\n\n- **datarobot-predictions**: `get_deployment_features.py`, `generate_prediction_data_template.py`, `validate_prediction_data.py`, `make_prediction.py`\n- **datarobot-model-training**: `create_project.py`, `start_training.py`, `list_models.py`\n- **datarobot-model-explainability**: `compute_shap_matrix.py`\n- **datarobot-data-preparation**: `upload_dataset.py`\n- **datarobot-external-agent-monitoring**: `create_shell_deployment.py`, `verify_otel_connection.py`\n- **datarobot-agent-assist**: `select_framework.py`, `clone_template.py`, `setup_template.py`, `list_llm_models.py`, `rehearsal.py`, `env_utils.py`\n\nThese scripts are located in each skill's `scripts/` directory and can be executed directly or used as references when writing code.\n\n## Additional documentation\n\n- [Agent framework integration](docs/AGENT_FRAMEWORK_INTEGRATION.md)—how to load and inject skills when building agents with LangGraph, PydanticAI, CrewAI, LlamaIndex, and similar frameworks.\n- [Contributing](CONTRIBUTING.md)—how to create skills, naming conventions, validation, and CI.\n\n## Additional references\n\n- Browse the latest instructions, scripts, and templates at [datarobot-oss/datarobot-agent-skills](https://github.com/datarobot-oss/datarobot-agent-skills).\n- Review the [DataRobot documentation](https://docs.datarobot.com/) for the libraries and workflows referenced in each skill.\n- See the [DataRobot Python SDK documentation](https://datarobot-public-api-client.readthedocs-hosted.com/) for API reference.\n", "bytes": 14726, "sha": "5bad7ff1593cb8ba55e8b1b290e618b1dc415e6270822be61a456f496c75a575", "repo_slug": "datarobot-oss/datarobot-agent-skills", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/plg_datarobot_oss_datarobot_agent_skills_1266a212/readme" }