Name: deploy
Rating: 74.4 (1 reviews)
Author: databricks

deploy

Deploy agent to Databricks Apps using DAB (Databricks Asset Bundles). Use when: (1) User says 'deploy', 'push to databricks', or 'bundle deploy', (2) 'App already exists' error occurs, (3) Need to bind/unbind existing apps, (4) Debugging deployed apps, (5) Querying deployed app endpoints.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

85%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.

The body is highly actionable with an excellent sequenced workflow and validation feedback loops, but it is a monolithic 244 lines that references bundle files which are not present, leaving structure and navigation only partially realized.

Suggestions

Create the referenced scripts/grant_lakebase_permissions.py and add-tools/examples/lakebase-autoscaling.yaml files, or remove the dangling references, so progressive disclosure points to real resources.

Split the lengthy 'App Already Exists' bind procedure and the troubleshooting table into a separate reference file (e.g. references/troubleshooting.md) and link to it from SKILL.md to reduce inline bulk.

De-duplicate the FAQ and 'Important Notes' sections against the troubleshooting table and naming-convention guidance to tighten token use.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with copy-paste commands and value-adding 'Why this matters' callouts, but the FAQ overlaps the troubleshooting table and 'Important Notes' repeats the naming convention, so minor trimming is possible. It assumes Claude's intelligence and does not explain basic concepts.	4 / 5
Actionability	Fully executable throughout — concrete CLI commands with --profile flags, jq filters, curl requests with headers and payloads, and a runnable Python snippet, covering the common deploy/bind/query cases.	5 / 5
Workflow Clarity	Clear sequenced workflow (preflight, validate, deploy, run) with explicit validation checkpoints, a critical 'run is REQUIRED' note, and a numbered bind procedure with feedback loops for error recovery.	5 / 5
Progressive Disclosure	No bundle files exist, yet the body references nonexistent paths (scripts/grant_lakebase_permissions.py, .claude/skills/add-tools/examples/lakebase-autoscaling.yaml); the ~244-line monolith also inlines sections like the large error-handling flow and troubleshooting table that could live in separate files.	3 / 5
	Total	17 / 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.

The description is exemplary: concise, concrete, and complete, clearly stating what the skill does and when to invoke it with natural trigger phrases. It avoids fluff and over-claims entirely.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across five enumerated capabilities — 'Deploy agent to Databricks Apps', 'bind/unbind existing apps', 'Debugging deployed apps', 'Querying deployed app endpoints' — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (Deploy agent to Databricks Apps using DAB) and 'when' via a concrete numbered 'Use when' list with five trigger conditions.	5 / 5
Trigger Term Quality	Includes natural user phrasings ('deploy', 'push to databricks', 'bundle deploy') plus error-state triggers ('App already exists' error occurs) that a user would genuinely say or encounter.	5 / 5
Distinctiveness Conflict Risk	Clear niche of Databricks Apps deployment via DAB with distinct triggers and a specific error condition, giving minimal overlap risk with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: databricks/app-templates
Path: agent-openai-agents-sdk-multiagent/.claude/skills/deploy/SKILL.md
Commit: fdc1b49

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.