[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6F6673KBS4TXG2AF9JBTMQG":3,"skill-same:01M6F6673KBS4TXG2AF9JBTMQG":77},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":60,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M6F6673KBS4TXG2AF9JBTMQG","databricks-core-workflow-b",null,"Execute Databricks secondary workflow: MLflow model training and deployment.\nUse when building ML pipelines, training models, or deploying to production.\nTrigger with phrases like \"databricks ML\", \"mlflow training\",\n\"databricks model\", \"feature store\", \"model registry\".","Dicklesworthstone\u002Fpi_agent_rust","Dicklesworthstone","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F35050222?v=4","01M6CG26AR942CSVMN1M5E3DSE","Jeff Emanuel","01M6CG26EPP71PSHW1VDS71121",1991,"MIT","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fsaas-packs\u002Fdatabricks-pack\u002Fskills\u002Fdatabricks-core-workflow-b\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"databricks","workflow","databricks core workflow b","core","when","deploying to production","ML Pipelines","Model Registry","trigger","io","feature","mlflow","use","edit","write","read","model","Bash","registry","deployment","training","2026-11-10 10:12:30",false,"---\nname: databricks-core-workflow-b\ndescription: |\n  Execute Databricks secondary workflow: MLflow model training and deployment.\n  Use when building ML pipelines, training models, or deploying to production.\n  Trigger with phrases like \"databricks ML\", \"mlflow training\",\n  \"databricks model\", \"feature store\", \"model registry\".\nallowed-tools: Read, Write, Edit, Bash(databricks:*), Grep\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\n---\n\n# Databricks Core Workflow B: MLflow Training\n\n## Overview\nBuild ML pipelines with MLflow experiment tracking, model registry, and deployment.\n\n## Prerequisites\n- Completed `databricks-install-auth` setup\n- Familiarity with `databricks-core-workflow-a` (data pipelines)\n- MLflow and scikit-learn installed\n- Unity Catalog for model registry (recommended)\n\n## Instructions\n\n### Step 1: Feature Engineering with Feature Store\n```python\n# src\u002Fml\u002Ffeatures.py\nfrom databricks.feature_engineering import FeatureEngineeringClient\nfrom pyspark.sql import SparkSession, DataFrame\nfrom pyspark.sql.functions import col, avg, count, datediff, current_date\n\ndef create_customer_features(spark: SparkSession, orders_table: str) -> DataFrame:\n    \"\"\"Create customer features from order history.\"\"\"\n    orders_df = spark.table(orders_table)\n\n    features_df = (\n        orders_df\n        .groupBy(\"customer_id\")\n        .agg(\n            count(\"*\").alias(\"total_orders\"),\n            avg(\"amount\").alias(\"avg_order_value\"),\n            sum(\"amount\").alias(\"lifetime_value\"),\n            max(\"order_date\").alias(\"last_order_date\"),\n            min(\"order_date\").alias(\"first_order_date\"),\n        )\n        .withColumn(\n            \"days_since_last_order\",\n            datediff(current_date(), col(\"last_order_date\"))\n        )\n        .withColumn(\n            \"customer_tenure_days\",\n            datediff(current_date(), col(\"first_order_date\"))\n        )\n    )\n\n    return features_df\n\ndef register_feature_table(\n    spark: SparkSession,\n    df: DataFrame,\n    feature_table_name: str,\n    primary_keys: list[str],\n    description: str,\n) -> None:\n    \"\"\"Register DataFrame as Feature Store table.\"\"\"\n    fe = FeatureEngineeringClient()\n\n    fe.create_table(\n        name=feature_table_name,\n        primary_keys=primary_keys,\n        df=df,\n        description=description,\n        tags={\"team\": \"data-science\", \"domain\": \"customer\"},\n    )\n```\n\n### Step 2: MLflow Experiment Tracking\n```python\n# src\u002Fml\u002Ftraining.py\nimport mlflow\nimport mlflow.sklearn\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score\nimport pandas as pd\n\ndef train_churn_model(\n    spark,\n    feature_table: str,\n    label_column: str = \"churned\",\n    experiment_name: str = \"\u002FExperiments\u002Fchurn-prediction\",\n) -> str:\n    \"\"\"\n    Train churn prediction model with MLflow tracking.\n\n    Returns:\n        run_id: MLflow run ID\n    \"\"\"\n    # Set experiment\n    mlflow.set_experiment(experiment_name)\n\n    # Load features\n    fe = FeatureEngineeringClient()\n    df = spark.table(feature_table).toPandas()\n\n    # Prepare data\n    feature_cols = [c for c in df.columns if c not in [label_column, \"customer_id\"]]\n    X = df[feature_cols]\n    y = df[label_column]\n\n    X_train, X_test, y_train, y_test = train_test_split(\n        X, y, test_size=0.2, random_state=42\n    )\n\n    # Train with MLflow tracking\n    with mlflow.start_run() as run:\n        # Log parameters\n        params = {\n            \"n_estimators\": 100,\n            \"max_depth\": 10,\n            \"min_samples_split\": 5,\n            \"random_state\": 42,\n        }\n        mlflow.log_params(params)\n\n        # Train model\n        model = RandomForestClassifier(**params)\n        model.fit(X_train, y_train)\n\n        # Evaluate\n        y_pred = model.predict(X_test)\n        metrics = {\n            \"accuracy\": accuracy_score(y_test, y_pred),\n            \"precision\": precision_score(y_test, y_pred),\n            \"recall\": recall_score(y_test, y_pred),\n            \"f1\": f1_score(y_test, y_pred),\n        }\n        mlflow.log_metrics(metrics)\n\n        # Log model with signature\n        from mlflow.models import infer_signature\n        signature = infer_signature(X_train, y_pred)\n\n        mlflow.sklearn.log_model(\n            model,\n            artifact_path=\"model\",\n            signature=signature,\n            input_example=X_train.head(5),\n            registered_model_name=\"churn-prediction-model\",\n        )\n\n        # Log feature importance\n        importance_df = pd.DataFrame({\n            \"feature\": feature_cols,\n            \"importance\": model.feature_importances_\n        }).sort_values(\"importance\", ascending=False)\n        mlflow.log_table(importance_df, \"feature_importance.json\")\n\n        print(f\"Run ID: {run.info.run_id}\")\n        print(f\"Metrics: {metrics}\")\n\n        return run.info.run_id\n```\n\n### Step 3: Model Registry and Versioning\n```python\n# src\u002Fml\u002Fregistry.py\nfrom mlflow import MlflowClient\nfrom mlflow.entities.model_registry import ModelVersion\n\ndef promote_model(\n    model_name: str,\n    version: int,\n    stage: str = \"Production\",\n    archive_existing: bool = True,\n) -> ModelVersion:\n    \"\"\"\n    Promote model version to specified stage.\n\n    Args:\n        model_name: Registered model name\n        version: Model version number\n        stage: Target stage (Staging, Production, Archived)\n        archive_existing: Archive current production model\n    \"\"\"\n    client = MlflowClient()\n\n    # Archive existing production model\n    if archive_existing and stage == \"Production\":\n        for mv in client.search_model_versions(f\"name='{model_name}'\"):\n            if mv.current_stage == \"Production\":\n                client.transition_model_version_stage(\n                    name=model_name,\n                    version=mv.version,\n                    stage=\"Archived\",\n                )\n\n    # Promote new version\n    model_version = client.transition_model_version_stage(\n        name=model_name,\n        version=version,\n        stage=stage,\n    )\n\n    # Add description\n    client.update_model_version(\n        name=model_name,\n        version=version,\n        description=f\"Promoted to {stage} on {pd.Timestamp.now()}\",\n    )\n\n    return model_version\n\ndef compare_model_versions(model_name: str) -> pd.DataFrame:\n    \"\"\"Compare metrics across model versions.\"\"\"\n    client = MlflowClient()\n    versions = client.search_model_versions(f\"name='{model_name}'\")\n\n    comparisons = []\n    for v in versions:\n        run = client.get_run(v.run_id)\n        comparisons.append({\n            \"version\": v.version,\n            \"stage\": v.current_stage,\n            \"accuracy\": run.data.metrics.get(\"accuracy\"),\n            \"f1\": run.data.metrics.get(\"f1\"),\n            \"created\": v.creation_timestamp,\n        })\n\n    return pd.DataFrame(comparisons)\n```\n\n### Step 4: Model Serving and Inference\n```python\n# src\u002Fml\u002Fserving.py\nfrom databricks.sdk import WorkspaceClient\nfrom databricks.sdk.service.serving import (\n    EndpointCoreConfigInput,\n    ServedEntityInput,\n    TrafficConfig,\n    Route,\n)\n\ndef deploy_model_endpoint(\n    model_name: str,\n    endpoint_name: str,\n    model_version: str = None,  # None = latest\n    scale_to_zero: bool = True,\n    workload_size: str = \"Small\",\n) -> str:\n    \"\"\"\n    Deploy model to Databricks Model Serving endpoint.\n\n    Returns:\n        endpoint_url: Serving endpoint URL\n    \"\"\"\n    w = WorkspaceClient()\n\n    # Create or update endpoint\n    endpoint = w.serving_endpoints.create_and_wait(\n        name=endpoint_name,\n        config=EndpointCoreConfigInput(\n            served_entities=[\n                ServedEntityInput(\n                    name=f\"{model_name}-entity\",\n                    entity_name=model_name,\n                    entity_version=model_version,\n                    workload_size=workload_size,\n                    scale_to_zero_enabled=scale_to_zero,\n                )\n            ],\n            traffic_config=TrafficConfig(\n                routes=[\n                    Route(\n                        served_model_name=f\"{model_name}-entity\",\n                        traffic_percentage=100,\n                    )\n                ]\n            ),\n        ),\n    )\n\n    return endpoint.name\n\ndef batch_inference(\n    spark,\n    model_uri: str,\n    input_table: str,\n    output_table: str,\n    feature_columns: list[str],\n) -> None:\n    \"\"\"Run batch inference with logged model.\"\"\"\n    import mlflow.pyfunc\n\n    # Load model\n    model = mlflow.pyfunc.spark_udf(spark, model_uri)\n\n    # Read input data\n    input_df = spark.table(input_table)\n\n    # Run inference\n    predictions_df = input_df.withColumn(\n        \"prediction\",\n        model(*[col(c) for c in feature_columns])\n    )\n\n    # Write predictions\n    predictions_df.write \\\n        .format(\"delta\") \\\n        .mode(\"overwrite\") \\\n        .saveAsTable(output_table)\n```\n\n## Output\n- Feature table in Unity Catalog\n- MLflow experiment with tracked runs\n- Registered model with versions\n- Model serving endpoint\n\n## Error Handling\n| Error | Cause | Solution |\n|-------|-------|----------|\n| `Model not found` | Wrong model name\u002Fversion | Verify in Model Registry |\n| `Feature mismatch` | Schema changed | Retrain with updated features |\n| `Endpoint timeout` | Cold start | Disable scale-to-zero for latency |\n| `Memory error` | Large batch | Reduce batch size or increase cluster |\n\n## Examples\n\n### Complete ML Pipeline Job\n```python\n# jobs\u002Ftrain_pipeline.py\nfrom src.ml import features, training, registry\n\n# 1. Create features\nfeatures_df = features.create_customer_features(spark, \"catalog.silver.orders\")\nfeatures.register_feature_table(\n    spark, features_df,\n    \"catalog.ml.customer_features\",\n    [\"customer_id\"],\n    \"Customer behavior features\"\n)\n\n# 2. Train model\nrun_id = training.train_churn_model(\n    spark,\n    \"catalog.ml.customer_features\",\n    experiment_name=\"\u002FExperiments\u002Fchurn-v2\"\n)\n\n# 3. Compare and promote\ncomparison = registry.compare_model_versions(\"churn-prediction-model\")\nbest_version = comparison.sort_values(\"f1\", ascending=False).iloc[0][\"version\"]\nregistry.promote_model(\"churn-prediction-model\", best_version, \"Production\")\n```\n\n## Resources\n- [MLflow on Databricks](https:\u002F\u002Fdocs.databricks.com\u002Fmlflow\u002Findex.html)\n- [Feature Engineering](https:\u002F\u002Fdocs.databricks.com\u002Fmachine-learning\u002Ffeature-store\u002Findex.html)\n- [Model Serving](https:\u002F\u002Fdocs.databricks.com\u002Fmachine-learning\u002Fmodel-serving\u002Findex.html)\n- [Unity Catalog ML](https:\u002F\u002Fdocs.databricks.com\u002Fmachine-learning\u002Fmanage-model-lifecycle\u002Findex.html)\n\n## Next Steps\nFor common errors, see `databricks-common-errors`.\n","# Databricks Core Workflow B: MLflow Training\n\n## Overview\nBuild ML pipelines with MLflow experiment tracking, model registry, and deployment.\n\n## Prerequisites\n- Completed `databricks-install-auth` setup\n- Familiarity with `databricks-core-workflow-a` (data pipelines)\n- MLflow and scikit-learn installed\n- Unity Catalog for model registry (recommended)\n\n## Instructions\n\n### Step 1: Feature Engineering with Feature Store\n```python\n# src\u002Fml\u002Ffeatures.py\nfrom databricks.feature_engineering import FeatureEngineeringClient\nfrom pyspark.sql import SparkSession, DataFrame\nfrom pyspark.sql.functions import col, avg, count, datediff, current_date\n\ndef create_customer_features(spark: SparkSession, orders_table: str) -> DataFrame:\n    \"\"\"Create customer features from order history.\"\"\"\n    orders_df = spark.table(orders_table)\n\n    features_df = (\n        orders_df\n        .groupBy(\"customer_id\")\n        .agg(\n            count(\"*\").alias(\"total_orders\"),\n            avg(\"amount\").alias(\"avg_order_value\"),\n            sum(\"amount\").alias(\"lifetime_value\"),\n            max(\"order_date\").alias(\"last_order_date\"),\n            min(\"order_date\").alias(\"first_order_date\"),\n        )\n        .withColumn(\n            \"days_since_last_order\",\n            datediff(current_date(), col(\"last_order_date\"))\n        )\n        .withColumn(\n            \"customer_tenure_days\",\n            datediff(current_date(), col(\"first_order_date\"))\n        )\n    )\n\n    return features_df\n\ndef register_feature_table(\n    spark: SparkSession,\n    df: DataFrame,\n    feature_table_name: str,\n    primary_keys: list[str],\n    description: str,\n) -> None:\n    \"\"\"Register DataFrame as Feature Store table.\"\"\"\n    fe = FeatureEngineeringClient()\n\n    fe.create_table(\n        name=feature_table_name,\n        primary_keys=primary_keys,\n        df=df,\n        description=description,\n        tags={\"team\": \"data-science\", \"domain\": \"customer\"},\n    )\n```\n\n### Step 2: MLflow Experiment Tracking\n```python\n# src\u002Fml\u002Ftraining.py\nimport mlflow\nimport mlflow.sklearn\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score\nimport pandas as pd\n\ndef train_churn_model(\n    spark,\n    feature_table: str,\n    label_column: str = \"churned\",\n    experiment_name: str = \"\u002FExperiments\u002Fchurn-prediction\",\n) -> str:\n    \"\"\"\n    Train churn prediction model with MLflow tracking.\n\n    Returns:\n        run_id: MLflow run ID\n    \"\"\"\n    # Set experiment\n    mlflow.set_experiment(experiment_name)\n\n    # Load features\n    fe = FeatureEngineeringClient()\n    df = spark.table(feature_table).toPandas()\n\n    # Prepare data\n    feature_cols = [c for c in df.columns if c not in [label_column, \"customer_id\"]]\n    X = df[feature_cols]\n    y = df[label_column]\n\n    X_train, X_test, y_train, y_test = train_test_split(\n        X, y, test_size=0.2, random_state=42\n    )\n\n    # Train with MLflow tracking\n    with mlflow.start_run() as run:\n        # Log parameters\n        params = {\n            \"n_estimators\": 100,\n            \"max_depth\": 10,\n            \"min_samples_split\": 5,\n            \"random_state\": 42,\n        }\n        mlflow.log_params(params)\n\n        # Train model\n        model = RandomForestClassifier(**params)\n        model.fit(X_train, y_train)\n\n        # Evaluate\n        y_pred = model.predict(X_test)\n        metrics = {\n            \"accuracy\": accuracy_score(y_test, y_pred),\n            \"precision\": precision_score(y_test, y_pred),\n            \"recall\": recall_score(y_test, y_pred),\n            \"f1\": f1_score(y_test, y_pred),\n        }\n        mlflow.log_metrics(metrics)\n\n        # Log model with signature\n        from mlflow.models import infer_signature\n        signature = infer_signature(X_train, y_pred)\n\n        mlflow.sklearn.log_model(\n            model,\n            artifact_path=\"model\",\n            signature=signature,\n            input_example=X_train.head(5),\n            registered_model_name=\"churn-prediction-model\",\n        )\n\n        # Log feature importance\n        importance_df = pd.DataFrame({\n            \"feature\": feature_cols,\n            \"importance\": model.feature_importances_\n        }).sort_values(\"importance\", ascending=False)\n        mlflow.log_table(importance_df, \"feature_importance.json\")\n\n        print(f\"Run ID: {run.info.run_id}\")\n        print(f\"Metrics: {metrics}\")\n\n        return run.info.run_id\n```\n\n### Step 3: Model Registry and Versioning\n```python\n# src\u002Fml\u002Fregistry.py\nfrom mlflow import MlflowClient\nfrom mlflow.entities.model_registry import ModelVersion\n\ndef promote_model(\n    model_name: str,\n    version: int,\n    stage: str = \"Production\",\n    archive_existing: bool = True,\n) -> ModelVersion:\n    \"\"\"\n    Promote model version to specified stage.\n\n    Args:\n        model_name: Registered model name\n        version: Model version number\n        stage: Target stage (Staging, Production, Archived)\n        archive_existing: Archive current production model\n    \"\"\"\n    client = MlflowClient()\n\n    # Archive existing production model\n    if archive_existing and stage == \"Production\":\n        for mv in client.search_model_versions(f\"name='{model_name}'\"):\n            if mv.current_stage == \"Production\":\n                client.transition_model_version_stage(\n                    name=model_name,\n                    version=mv.version,\n                    stage=\"Archived\",\n                )\n\n    # Promote new version\n    model_version = client.transition_model_version_stage(\n        name=model_name,\n        version=version,\n        stage=stage,\n    )\n\n    # Add description\n    client.update_model_version(\n        name=model_name,\n        version=version,\n        description=f\"Promoted to {stage} on {pd.Timestamp.now()}\",\n    )\n\n    return model_version\n\ndef compare_model_versions(model_name: str) -> pd.DataFrame:\n    \"\"\"Compare metrics across model versions.\"\"\"\n    client = MlflowClient()\n    versions = client.search_model_versions(f\"name='{model_name}'\")\n\n    comparisons = []\n    for v in versions:\n        run = client.get_run(v.run_id)\n        comparisons.append({\n            \"version\": v.version,\n            \"stage\": v.current_stage,\n            \"accuracy\": run.data.metrics.get(\"accuracy\"),\n            \"f1\": run.data.metrics.get(\"f1\"),\n            \"created\": v.creation_timestamp,\n        })\n\n    return pd.DataFrame(comparisons)\n```\n\n### Step 4: Model Serving and Inference\n```python\n# src\u002Fml\u002Fserving.py\nfrom databricks.sdk import WorkspaceClient\nfrom databricks.sdk.service.serving import (\n    EndpointCoreConfigInput,\n    ServedEntityInput,\n    TrafficConfig,\n    Route,\n)\n\ndef deploy_model_endpoint(\n    model_name: str,\n    endpoint_name: str,\n    model_version: str = None,  # None = latest\n    scale_to_zero: bool = True,\n    workload_size: str = \"Small\",\n) -> str:\n    \"\"\"\n    Deploy model to Databricks Model Serving endpoint.\n\n    Returns:\n        endpoint_url: Serving endpoint URL\n    \"\"\"\n    w = WorkspaceClient()\n\n    # Create or update endpoint\n    endpoint = w.serving_endpoints.create_and_wait(\n        name=endpoint_name,\n        config=EndpointCoreConfigInput(\n            served_entities=[\n                ServedEntityInput(\n                    name=f\"{model_name}-entity\",\n                    entity_name=model_name,\n                    entity_version=model_version,\n                    workload_size=workload_size,\n                    scale_to_zero_enabled=scale_to_zero,\n                )\n            ],\n            traffic_config=TrafficConfig(\n                routes=[\n                    Route(\n                        served_model_name=f\"{model_name}-entity\",\n                        traffic_percentage=100,\n                    )\n                ]\n            ),\n        ),\n    )\n\n    return endpoint.name\n\ndef batch_inference(\n    spark,\n    model_uri: str,\n    input_table: str,\n    output_table: str,\n    feature_columns: list[str],\n) -> None:\n    \"\"\"Run batch inference with logged model.\"\"\"\n    import mlflow.pyfunc\n\n    # Load model\n    model = mlflow.pyfunc.spark_udf(spark, model_uri)\n\n    # Read input data\n    input_df = spark.table(input_table)\n\n    # Run inference\n    predictions_df = input_df.withColumn(\n        \"prediction\",\n        model(*[col(c) for c in feature_columns])\n    )\n\n    # Write predictions\n    predictions_df.write \\\n        .format(\"delta\") \\\n        .mode(\"overwrite\") \\\n        .saveAsTable(output_table)\n```\n\n## Output\n- Feature table in Unity Catalog\n- MLflow experiment with tracked runs\n- Registered model with versions\n- Model serving endpoint\n\n## Error Handling\n| Error | Cause | Solution |\n|-------|-------|----------|\n| `Model not found` | Wrong model name\u002Fversion | Verify in Model Registry |\n| `Feature mismatch` | Schema changed | Retrain with updated features |\n| `Endpoint timeout` | Cold start | Disable scale-to-zero for latency |\n| `Memory error` | Large batch | Reduce batch size or increase cluster |\n\n## Examples\n\n### Complete ML Pipeline Job\n```python\n# jobs\u002Ftrain_pipeline.py\nfrom src.ml import features, training, registry\n\n# 1. Create features\nfeatures_df = features.create_customer_features(spark, \"catalog.silver.orders\")\nfeatures.register_feature_table(\n    spark, features_df,\n    \"catalog.ml.customer_features\",\n    [\"customer_id\"],\n    \"Customer behavior features\"\n)\n\n# 2. Train model\nrun_id = training.train_churn_model(\n    spark,\n    \"catalog.ml.customer_features\",\n    experiment_name=\"\u002FExperiments\u002Fchurn-v2\"\n)\n\n# 3. Compare and promote\ncomparison = registry.compare_model_versions(\"churn-prediction-model\")\nbest_version = comparison.sort_values(\"f1\", ascending=False).iloc[0][\"version\"]\nregistry.promote_model(\"churn-prediction-model\", best_version, \"Production\")\n```\n\n## Resources\n- [MLflow on Databricks](https:\u002F\u002Fdocs.databricks.com\u002Fmlflow\u002Findex.html)\n- [Feature Engineering](https:\u002F\u002Fdocs.databricks.com\u002Fmachine-learning\u002Ffeature-store\u002Findex.html)\n- [Model Serving](https:\u002F\u002Fdocs.databricks.com\u002Fmachine-learning\u002Fmodel-serving\u002Findex.html)\n- [Unity Catalog ML](https:\u002F\u002Fdocs.databricks.com\u002Fmachine-learning\u002Fmanage-model-lifecycle\u002Findex.html)\n\n## Next Steps\nFor common errors, see `databricks-common-errors`.\n",{"name":5,"author":50,"license":15,"version":51,"description":52,"allowed-tools":53},"Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Execute Databricks secondary workflow: MLflow model training and deployment.\nUse when building ML pipelines, training models, or deploying to production.\nTrigger with phrases like \"databricks ML\", \"mlflow training\",\n\"databricks model\", \"feature store\", \"model registry\".\n","Read, Write, Edit, Bash(databricks:*), Grep","main","90b50ed0778745a80fd5bfb13b1843d45b9e82f7","tests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fsaas-packs\u002Fdatabricks-pack\u002Fskills\u002Fdatabricks-core-workflow-b",234,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust","https:\u002F\u002Fgithub.com\u002FDicklesworthstone","https:\u002F\u002Fwww.jeffreyemanuel.com\u002F","Building in NY","2026-11-13 11:50:27",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add Dicklesworthstone\u002Fpi_agent_rust --skill databricks-core-workflow-b",{"tool":69,"command":70},"bunx","bunx skills add Dicklesworthstone\u002Fpi_agent_rust --skill databricks-core-workflow-b",{"tool":72,"command":73},"pnpm","pnpm dlx skills add Dicklesworthstone\u002Fpi_agent_rust --skill databricks-core-workflow-b","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fsaas-packs\u002Fdatabricks-pack\u002Fskills\u002Fdatabricks-core-workflow-b\u002FSKILL.md",true,[],[78,116,141,167,192,214],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":89,"publishedAt":45},"01M6FEGPPK0ZTKCCM0R3E3KS33","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[86],{"categoryNo":87,"categoryName":88,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,36,108,109,110,111,112,113,114,115],"web artifacts builder","web","artifacts","artifacts builder","builder","frontend","css","components","react","component","routing","state management","state","shadcn","file","ui","Tools","Tailwind","html","single-file","simple","ui components","multi","for","jsx","suite",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":127,"publishedAt":45},"01M6FEE9VTK1W4GY21AKREJXRG","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[123,126],{"categoryNo":124,"categoryName":125,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":87,"categoryName":88,"taxonomyType":21,"taxonomyTypeDesc":22},[128,129,130,95,131,132,91,133,134,135,105,136,137,138,139,140,113],"testing","webapp testing","webapp","screenshots","playwright","debugging","toolkit","browser","logs","applications","behavior","local","with",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":145,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":45},"01M6FE20F7ZTQBFWKF4MPJ2SBX","neuropixels-analysis","Neuropixels neural recording analysis. Load SpikeGLX\u002FOpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen\u002FIBL curation, AI-assisted visual analysis, for Neuropixels 1.0\u002F2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FSKILL.md",[],[149,150,151,152,153,154,155,156,36,157,158,159,160,161,162,163,140,164,165,166,113,28],"analysis","neuropixels analysis","spike","metrics","data","open","quality","user","recordings","Neural","motion","visual","quality metrics","unit","sorting","curation","recording","load",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":171,"sourceHtmlUrl":172,"categories":173,"keywords":175,"publishedAt":45},"01M6FDP0PDK6F1GGX395C7625Z","skill-creator","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fskill-creator\u002FSKILL.md",[174],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[176,177,178,179,180,181,182,183,184,185,186,187,188,189,140,113,190,28,191],"skill creator","creator","workflows","create","update","capabilities","knowledge","tool","integrations","specialized","guide","new skill","existing skill","users","Existing","new",{"skillNo":193,"name":194,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":196,"sourceHtmlUrl":197,"categories":198,"keywords":200,"publishedAt":45},"01M6FDM8Y7VK7NYG9SM7QPA3PW","notebooklm","Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fnotebooklm\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fnotebooklm\u002FSKILL.md",[199],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[194,201,202,203,204,205,206,135,207,208,36,209,210,211,212,113,213],"google","browser automation","gemini","automation","auth","code","library","management","only","document","query","Citation","source",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":218,"sourceHtmlUrl":219,"categories":220,"keywords":227,"publishedAt":45},"01M6FDHPXE10J3XGTCH5HBHS1M","slack-gif-creator","Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like \"make me a GIF of X doing Y for Slack.\"","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fenterprise-communication\u002Fslack-gif-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fenterprise-communication\u002Fslack-gif-creator\u002FSKILL.md",[221,224],{"categoryNo":222,"categoryName":223,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000005","邮件与沟通",{"categoryNo":225,"categoryName":226,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[228,229,230,177,231,106,232,233,182,36,234,189,235,236,237,113,238,28],"slack gif creator","slack","gif","validation","constraints","Animation","me","make","Utilities","concepts","request"]