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.

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

80%

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 clear, validated workflows and executable commands throughout. It is somewhat dense and could benefit from offloading peripheral detail (Lakebase, OBO, FAQ) into reference files to improve token efficiency and progressive disclosure.

Suggestions

Move the Lakebase autoscaling, OBO authentication, and FAQ sections into separate reference files and link to them one level deep, keeping the core deploy/bind/query flow in SKILL.md.

Tighten the FAQ and repeated deploy-vs-run notes; the key insight (run is required after deploy) is already in the Note callout and troubleshooting table and need not be restated.

Verify referenced bundle paths (e.g., scripts/grant_lakebase_permissions.py) exist or convert them into inline snippets so guidance is self-contained.

DimensionReasoningScore

Conciseness

The body is mostly efficient with command-centric structure, but explanations like the FAQ entry on 200 OK and repeated restating of the deploy-vs-run distinction add some length that assumes Claude needs more handholding than necessary.

2 / 3

Actionability

Provides fully executable, copy-paste-ready commands (preflight, bundle validate/deploy/run, apps get/bind/unbind, OAuth token + curl) with concrete jq filters and yaml snippets.

3 / 3

Workflow Clarity

Multi-step processes are explicitly sequenced with numbered steps, validation checkpoints (preflight, bundle validate, summary check before bind), and feedback loops for error recovery (e.g., 'App already exists' decision tree and troubleshooting table).

3 / 3

Progressive Disclosure

Content is well-sectioned but heavily inline; references to other skills and a bundle file path (scripts/grant_lakebase_permissions.py, .claude/skills/add-tools/examples/lakebase-autoscaling.yaml) are textual pointers without a clean one-level-deep reference structure, and no references/ assets/ bundle exists to offload detail.

2 / 3

Total

10

/

12

Passed

Description

100%

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 concise, concrete, and clearly delineates both the skill's purpose and the specific conditions under which it should trigger. It uses appropriate third-person voice and avoids fluff. No suggestions for improvement.

DimensionReasoningScore

Specificity

Lists multiple concrete actions including deploy/bind/unbind existing apps, debugging deployed apps, and querying deployed app endpoints, alongside the core DAB deploy action.

3 / 3

Completeness

Clearly states what the skill does (deploy agent to Databricks Apps via DAB) and includes an explicit 'Use when' clause enumerating five distinct trigger conditions.

3 / 3

Trigger Term Quality

Captures natural user phrases like 'deploy', 'push to databricks', 'bundle deploy', and the recognizable 'App already exists' error, which are terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Targets a narrow niche (Databricks Apps deployment via DAB) with distinct, domain-specific triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.