databricks/app-templates
16 skills338 installs2.9k starsGitHub
Install
npx skills add https://github.com/databricks/app-templatesSkills in this repo
1Agent MemoryThe agent-memory skill guides setting up persistent agent memory using Databricks Lakebase in app-templates agents. It covers provisioning Lakebase databases, wiring memory backends in agent configuration, and databricks.yml resource declarations with permission grants required at deploy time. Works with the broader app-templates quickstart and add-tools skills for bundle deploy and runtime permissions. Use when agents need durable conversation or state memory on Databricks infrastructure.31installs2Discover ToolsThe discover-tools skill helps enumerate tools available to Databricks app-templates agents including MCP servers, Genie spaces, vector search indexes, Unity Catalog functions, SQL warehouses, and serving endpoints. It supports inspecting configured tool sources before wiring them in agent_server/agent.py and declaring matching databricks.yml resources with permissions. Use when planning agent capabilities, auditing existing tool connections, or troubleshooting missing tool access at runtime.31installs3Add ToolsThe add-tools skill connects Genie, vector search, UC functions, warehouses, endpoints, and custom MCP apps in agent_server/agent.py then declares matching databricks.yml resources with permissions, requiring bundle deploy and bundle run to apply.30installs4QuickstartThe quickstart skill bootstraps app-templates agents with uv, Node 20.19+, Databricks CLI v0.283+, sequential profile and app target collection, and uv run quickstart with flags including OAuth for new workspaces.29installs5DeployThe deploy skill runs databricks bundle deploy and bundle run after code or yml changes so new permissions and code reach the running Databricks App, with --profile on all CLI commands.28installs6Lakebase SetupThe lakebase-setup skill provisions Lakebase for agent memory in app-templates, declaring lakebase or lakebase-autoscaling resources in databricks.yml with deploy-time permission grants and integration with agent-memory patterns.28installs7Modify AgentThe modify-agent skill guides changing agent_server agent code, prompts, tool wiring, and related configuration in app-templates projects before redeploying with bundle deploy and run.28installs8Run LocallyThe run-locally skill explains local development workflows for app-templates agents including environment setup, uv dependencies, and local server execution before bundle deploy to Databricks Apps.28installs9Agent Openai MemoryThe agent-openai-memory skill sets up OpenAI-style memory integration for app-templates agents, wiring memory clients and databricks.yml resources with deploy permissions similar to Lakebase memory patterns.27installs10Migrate From Model ServingThe migrate-from-model-serving skill guides moving workloads from Databricks model serving endpoints to app-templates LangGraph agents including endpoint mapping, tool migration, and bundle configuration updates.27installs11Supervisor Api Background Modesupervisor-api-background-mode extends Databricks Supervisor API with background polling for long-running agent tasks. Submits responses.create with background=True, polls retrieve on an interval, and streams chunked results to the frontend past HTTP timeouts.10installs12Supervisor Apisupervisor-api skill documents Replace the client-side agent loop with Databricks Supervisor API (hosted tools + client-side function tools). Use when: (1) User asks about Supervisor API, (2) User wants Databricks to run the agent loop server-side, (3) Connecting Genie spaces, UC functions, agent endpoints, or MCP servers as host. name: supervisor-api description: "Replace the client-side agent loop with Databricks Supervisor API (hosted tools + client-side function tools). Use when: (1) User asks about Supervisor API, (2) User wants Databricks to run the agent loop server-side, (3) Connecting Genie spaces, UC functions, agent endpoints, or MCP servers as hosted tools, (4) Mixing client-side function tools (Python callables9installs13Create Toolscreate-tools skill documents Create Databricks resources that agents connect to as tools. Use when: (1) User needs to create a Genie space, vector search index, UC function, or UC connection, (2) User says 'create tool', 'set up genie', 'create vector search', 'register MCP server', (3) Before add-tools when the resource doesn'. name: create-tools description: "Create Databricks resources that agents connect to as tools. Use when: (1) User needs to create a Genie space, vector search index, UC function, or UC connection, (2) User says 'create tool', 'set up genie', 'create vector search', 'register MCP server', (3) Before add-tools when the resource doesn't exist yet, (4) User asks 'what do I need to create before adding8installs14Load Testingload-testing skill documents Load test a Databricks App to find its maximum QPS. Use when: (1) User says 'load test', 'benchmark', 'QPS', 'throughput', or 'performance test', (2) User wants to find how many queries per second their app can handle, (3) User wants to set up load testing scripts for their agent, (4) User wants to . name: load-testing description: "Load test a Databricks App to find its maximum QPS. Use when: (1) User says 'load test', 'benchmark', 'QPS', 'throughput', or 'performance test', (2) User wants to find how many queries per second their app can handle, (3) User wants to set up load testing scripts for their agent, (4) User wants to view load test results/dashboard."8installs15Long Running Serverlong-running-server skill documents Enable long-running background task support with LongRunningAgentServer. Use when: (1) Agent tasks may exceed HTTP timeout (~120s), (2) User wants background/async execution, (3) User says 'long running', 'background tasks', or 'async agent'.. name: long-running-server description: "Enable long-running background task support with LongRunningAgentServer. Use when: (1) Agent tasks may exceed HTTP timeout (~120s), (2) User wants background/async execution, (3) User says 'long running', 'background tasks', or 'async agent'."8installs16Supervisor Api Client Function Callingsupervisor-api-client-function-calling skill documents Add client-side function tools to the Supervisor API. Use when: (1) User wants to mix Python callables with hosted tools, (2) User asks about function tools with Supervisor API, (3) User needs to execute custom business logic alongside hosted tool calls.. name: supervisor-api-client-function-calling description: "Add client-side function tools to the Supervisor API. Use when: (1) User wants to mix Python callables with hosted tools, (2) User asks about function tools with Supervisor API, (3) User needs to execute custom business logic alongside hosted tool calls."8installs