CtrlK
BlogDocsLog inGet started
Tessl Logo

databricks-apps-python

Python backend for Databricks Apps — FastAPI (default), Flask, Dash, Streamlit, Gradio, Reflex. **Default for a new Databricks App is `databricks-apps` (AppKit — Node/TypeScript/React) — reach for it first.** Use this skill only when the user asks for a Python backend, extends an existing Python app, or the team is Python-only. Covers OAuth auth, app resources, SQL warehouse and Lakebase connectivity, foundation-model / Vector Search / model-serving APIs (via `databricks-python-sdk`), and deployment via CLI or DABs.

70

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, executable skill body that routes clearly to six well-labeled reference files. It is held back from top marks by mild redundancy and a broken local 'examples/' reference that does not resolve to any bundle file.

Suggestions

Either add the referenced examples/ folder (fm-minimal-chat.py, fm-parallel-calls.py, fm-structured-outputs.py, llm_config.py) to the bundle or remove the two mentions in the body so no referenced path is missing.

De-duplicate runtime facts: keep them in one place (Quick Reference or Platform Constraints) and link rather than restating, and consolidate the databricks-apps redirection to a single prominent notice.

Add an explicit inline validation checkpoint (e.g., verify deploy via 'databricks apps logs <name>' / health check) into the Workflow's deployment step rather than only deferring verification to references/4-deployment.md.

DimensionReasoningScore

Conciseness

Dense, reference-style content with no concept over-explanation, but the databricks-apps redirection recurs in three places and runtime facts (Python 3.11, Ubuntu 22.04, 2 vCPU/6 GB) are duplicated between the Quick Reference and Platform Constraints tables.

4 / 5

Actionability

Inline code is copy-paste executable (backend toggle, SQL warehouse connection, Pydantic models) and the framework table gives concrete app.yaml commands, but framework-specific auth/deployment code is deferred to the reference files rather than shown inline.

4 / 5

Workflow Clarity

The Workflow is a clear sequenced decision tree plus a pre-flight Required Steps checklist, with troubleshooting and post-deploy verification noted; it stops short of explicit inline validate→fix→retry checkpoints in the main sequence.

4 / 5

Progressive Disclosure

Six one-level-deep references are each well-signaled with a 'Use [references/N.md] when…' line plus keyword lists, but the body twice references a non-existent local 'examples/' folder (fm-minimal-chat.py, fm-parallel-calls.py, fm-structured-outputs.py, llm_config.py) that is not present in the bundle.

4 / 5

Total

16

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: comprehensive concrete capabilities, explicit when-to-use triggers with concrete conditions, and explicit boundary guidance that distinguishes it from the sibling default skill. Every dimension sits at the top anchor.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'OAuth auth, app resources, SQL warehouse and Lakebase connectivity, foundation-model / Vector Search / model-serving APIs ... deployment via CLI or DABs' — alongside six named frameworks, giving comprehensive coverage rather than just a few actions.

5 / 5

Completeness

Explicitly answers both 'what' (the capabilities above) and 'when' via a concrete trigger clause: 'Use this skill only when the user asks for a Python backend, extends an existing Python app, or the team is Python-only.'

5 / 5

Trigger Term Quality

Natural user-facing terms are comprehensive for the domain: 'Databricks Apps', 'Python backend', and the framework names (FastAPI, Flask, Dash, Streamlit, Gradio, Reflex) plus 'DABs'/'CLI' synonyms that users actually say.

5 / 5

Distinctiveness Conflict Risk

Has a clear Python-backend niche and actively redirects away from the default Node skill ('Default for a new Databricks App is databricks-apps — reach for it first'), minimizing wrong-skill triggering.

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 8 suspicious

Warning

Total

14

/

16

Passed

Repository
databricks/databricks-agent-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.