github.com/databricks/app-templates
| Skill | Added | Review |
|---|---|---|
supervisor-api-background-mode .claude/skills/supervisor-api-background-mode/SKILL.md Enable Supervisor API background mode for long-running agent tasks. Use when: (1) Agent needs to run tasks longer than HTTP timeout limits, (2) User says 'background mode', 'long-running', 'supervisor api', (3) Converting from streaming to background polling pattern, (4) Agent needs resilience to connection drops during execution. | 69 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3826450 | |
supervisor-api-client-function-calling .claude/skills/supervisor-api-client-function-calling/SKILL.md 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. | 65 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3826450 | |
supervisor-api-client-function-calling agent-openai-agents-sdk-multiagent/.claude/skills/supervisor-api-client-function-calling/SKILL.md 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. | 65 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3826450 | |
supervisor-api-client-function-calling agent-openai-agents-sdk/.claude/skills/supervisor-api-client-function-calling/SKILL.md 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. | 65 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3826450 | |
supervisor-api-client-function-calling agent-openai-advanced/.claude/skills/supervisor-api-client-function-calling/SKILL.md 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. | 65 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3826450 | |
supervisor-api .claude/skills/supervisor-api/SKILL.md 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 callables your app executes) with hosted tools. | 72 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 3826450 | |
sync-check .claude/skills/sync-check/SKILL.md Verify every per-template duplicated/synced file is byte-identical to its source of truth. Use when reviewing a PR that touches a template or a shared source file (.scripts/source/, .claude/skills/), or before pushing such a change, to catch drift — a copy edited directly, or a sync not re-run. Repo-dev tool — NOT synced into templates. | 76 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3826450 | |
validate-templates .claude/skills/validate-templates/SKILL.md Deploy-validate and functionally exercise the app templates against a shared Databricks App. Use when: (1) reviewing a PR that changes templates, (2) checking which templates deploy and serve, (3) running the e2e/deploy-validation or functional-e2e suites, (4) regenerating the validation report. Repo-dev tool — NOT synced into templates. | 73 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3826450 |