Name: deploy
Rating: 70.39999999999999 (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

86%

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 and workflow-clear, with executable commands and well-sequenced validation checkpoints for a destructive deploy flow. Its weak spot is progressive disclosure: it leans on inline reference material and cites bundle files that are not present.

Suggestions

Create the referenced scripts/grant_lakebase_permissions.py (or remove the reference) so the 'See scripts/...' pointer is not dangling.

Verify or remove the .claude/skills/add-tools/examples/lakebase-autoscaling.yaml cross-skill reference, which points outside the skill bundle.

Move the FAQ and the 11-row troubleshooting table into a references/ file (e.g. TROUBLESHOOTING.md) and link to it from the body to reduce inline bulk.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean — copy-paste commands with tight 'Why this matters' callouts that earn their tokens — but it repeats the agent-* naming convention in two sections and the troubleshooting table duplicates several FAQ points, so a little trimming is possible.	4 / 5
Actionability	Commands are copy-paste ready with real flags, jq filters, and full curl request bodies covering the common cases (deploy, bind, query with OAuth, query with memory), matching the fully-executable anchor.	5 / 5
Workflow Clarity	The deploy flow is explicitly numbered with a preflight/validate checkpoint before deploy, and the destructive 'App already exists' branch includes a check-then-bind step, a recommended path, and a warning on the delete option — clear validation and recovery loops throughout.	5 / 5
Progressive Disclosure	Sections are well organized, but no bundle directories exist while the body references scripts/grant_lakebase_permissions.py and .claude/skills/add-tools/examples/lakebase-autoscaling.yaml — both are dangling pointers — and the bulk troubleshooting reference material is inlined rather than split into a referenced file.	3 / 5
	Total	17 / 20 Passed

Description

87%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 strong: it pairs a concrete capability statement with an explicit, multi-case 'Use when' trigger list and tool-specific keywords that keep conflict risk low. Minor gains are possible by adding a couple of natural synonyms, but it already clearly answers both what and when.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — deploy, bind/unbind existing apps, debug deployed apps, query deployed app endpoints — with only minor coverage gaps, matching the 'lists several specific actions; minor gaps' anchor.	4 / 5
Completeness	Clearly states what it does ('Deploy agent to Databricks Apps using DAB') and answers 'when' explicitly with a five-item 'Use when: (1)...(5)' trigger list, fully matching the what-and-when anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('deploy', 'push to databricks', 'bundle deploy') plus error-driven triggers, giving good keyword coverage, though it leans on tooling terminology and misses a few common synonyms.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Databricks Apps via Asset Bundles) with distinct, tool-specific triggers, giving minimal overlap with other skills.	5 / 5
	Total	18 / 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-advanced/.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.