CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

69

Quality

85%

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

82%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 skill body with strong validation checkpoints and error-recovery loops. Deduplicate the repeated naming/PAT warnings, add a confirmation step to the destructive delete path, and resolve the dangling script reference for a top score.

Suggestions

Remove duplicated guidance: the agent-* naming convention and the PAT/302 OAuth warning each appear in 2-3 sections; state them once and cross-reference.

Add an explicit confirmation/validation checkpoint before the destructive 'Delete and Recreate' flow (e.g., confirm the app name and that deletion of URL/OAuth/SP is intended).

Fix the dangling reference to scripts/grant_lakebase_permissions.py (no scripts/ bundle exists); either create the script, move the snippet inline, or drop the reference.

DimensionReasoningScore

Conciseness

The body is dense and high-signal with executable commands and terse 'Why this matters' callouts, but repeats the app-naming convention and the PAT/302 warning across the Naming, Query, FAQ, and Troubleshooting sections, offering minor trimming opportunities.

4 / 5

Actionability

It provides copy-paste-ready CLI commands, jq filters, curl requests with exact headers, and a Python import example with clearly marked placeholders, covering the common deploy/bind/query/debug cases.

5 / 5

Workflow Clarity

Multi-step flows are clearly numbered (Deploy 1-4, Bind Steps 1-5) with validation checkpoints (preflight, bundle validate) and error-recovery guidance, but the destructive 'Delete and Recreate' path lacks an explicit confirmation checkpoint.

4 / 5

Progressive Disclosure

Section headers organize a single SKILL.md well and most content is appropriately placed, though it references scripts/grant_lakebase_permissions.py and a cross-skill example file that are not present in the bundle, a minor navigation gap.

4 / 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.

A strong, specific description that clearly states its purpose and gives explicit multi-part trigger guidance in third-person voice. Minor tightening of the capability phrasing and a few additional trigger synonyms would push specificity and trigger quality to full marks.

DimensionReasoningScore

Specificity

The description names the domain ('Deploy agent to Databricks Apps using DAB') and enumerates several concrete capability areas (bind/unbind, debugging, querying endpoints), but the core capability statement leans on a single verb with the rest framed as use-case triggers, leaving minor coverage gaps relative to a fully comprehensive action list.

4 / 5

Completeness

It explicitly states what the skill does ('Deploy agent to Databricks Apps using DAB') and provides a numbered 'Use when:' clause with five concrete trigger scenarios, matching the anchor for clearly answering both what and when.

5 / 5

Trigger Term Quality

Includes natural user phrases like 'deploy', 'push to databricks', and 'bundle deploy' plus error-string and task-based triggers; coverage is good with some synonyms, though a few natural variations are absent.

4 / 5

Distinctiveness Conflict Risk

The description targets a narrow niche (Databricks Apps via DAB) with highly specific triggers, making conflict with unrelated skills unlikely.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
databricks/app-templates
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.