Name: deploy
Rating: 71.2 (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

87%

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

78%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 highly actionable, well-sequenced deployment runbook with strong validation on the primary bind path. Its main weaknesses are a monolithic structure with no progressive disclosure and a dangling reference to a script that is not present in the bundle.

Suggestions

Move the FAQ and Troubleshooting table into a separate reference file (e.g., references/troubleshooting.md) and link to it from the body, so the main flow stays lean.

Add an explicit confirmation checkpoint before the destructive `databricks apps delete` in Option 2 (e.g., 'Confirm with the user before deleting — this permanently destroys the app URL, OAuth credentials, and service principal').

Resolve the dangling `scripts/grant_lakebase_permissions.py` reference — either add the script to a scripts/ bundle directory or remove the reference.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and command-oriented with domain-specific guidance (e.g., bundle run is required after deploy), but a few prose callouts and the FAQ/Troubleshooting sections could be trimmed without losing clarity.	4 / 5
Actionability	Fully executable throughout — copy-paste bash commands, YAML snippets, curl examples, and a Python snippet cover the common deploy, bind, query, and debug cases.	5 / 5
Workflow Clarity	The deploy flow is explicitly numbered with validation checkpoints (preflight, bundle validate, check-if-bound) and error-recovery notes; the destructive delete path has a warning but lacks an explicit confirmation checkpoint, a minor validation gap.	4 / 5
Progressive Disclosure	The ~245-line body is a monolithic runbook with good section headers but no reference files; content like the FAQ, troubleshooting table, and Lakebase post-deploy could be split out, and the referenced scripts/grant_lakebase_permissions.py has no corresponding bundle file.	3 / 5
	Total	16 / 20 Passed

Description

96%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, third-person description that states a concrete capability and pairs it with explicit, varied use-when triggers. Its only weakness is that the primary trigger term 'deploy' is generic enough to risk collision with unrelated deploy skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — deploy, bind/unbind existing apps, debug, and query deployed endpoints — against the Databricks Apps/DAB domain, giving comprehensive coverage rather than a single generic verb.	5 / 5
Completeness	Explicitly answers both 'what' (Deploy agent to Databricks Apps using DAB) and 'when' via a numbered list of five concrete trigger scenarios.	5 / 5
Trigger Term Quality	Includes natural phrases users say ('deploy', 'push to databricks', 'bundle deploy') plus error-string and scenario triggers, covering synonyms and the actual CLI verb.	5 / 5
Distinctiveness Conflict Risk	The DAB/Databricks Apps niche is distinct, but the leading trigger 'User says deploy' is generic and could overlap with other deployment skills; minor overlap risk rather than a fully clean niche.	4 / 5
	Total	19 / 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-langgraph/.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.