CtrlK
BlogDocsLog inGet started
Tessl Logo

quickstart

Set up the Databricks chatbot app for local development and deployment. Use when: (1) First time setup, (2) User says 'quickstart', 'set up', 'authenticate', or 'configure databricks', (3) No .env file exists, (4) User says 'enable feedback', 'feedback widget', or 'MLFLOW_EXPERIMENT_ID'.

70

Quality

88%

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

90%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 dense, highly actionable quickstart: every section is either a runnable command, a concrete config snippet, or a decision point, and the troubleshooting table handles realistic failure modes. The only refinement would be an explicit verification checkpoint after the manual deploy step.

DimensionReasoningScore

Conciseness

Lean and efficient throughout: no explanations of concepts Claude already knows, and every line is a command, config snippet, or decision-relevant detail (e.g., 'max 30 chars', '~5-10 min, costs apply'). The quickstart-preview and manual-feedback sections cover two distinct paths rather than duplicating content.

5 / 5

Actionability

Fully executable guidance: copy-paste commands ('./scripts/quickstart.sh', 'npx tsx scripts/get-experiment-id.ts --endpoint <name>', 'databricks bundle deploy') and complete .env, databricks.yml, and app.yaml snippets with clearly chained placeholders, plus a troubleshooting table covering the common failure modes (403 permission, auth error, non-unique instance).

5 / 5

Workflow Clarity

Both sequences are clearly numbered and chained (the experiment name from step 1 feeds steps 2-4), the script 'validates it exists' for the endpoint, and the troubleshooting table provides error recovery. However, the manual feedback path lacks an explicit post-deploy verification step — the widget-appearing check is only addressed reactively in troubleshooting — so it sits at 'clear sequence with minor validation gaps' rather than the top anchor.

4 / 5

Progressive Disclosure

Well-organized sections (What It Configures, Enabling Feedback After Initial Setup, Troubleshooting) with nothing inlined that clearly belongs in a separate file, and script references are clearly signaled. At ~78 lines it exceeds the under-50-line simple-skill exception, and no reference files exist, so 'good structure, appropriately placed' (4) fits better than the top anchor.

4 / 5

Total

18

/

20

Passed

Description

82%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 description with an explicit what/when structure and multiple concrete quoted trigger phrases including a file-state condition. Its only weakness is that the 'what' stays at the level of one or two actions rather than enumerating the specific capabilities (auth, endpoint config, feedback, database, deploy).

Suggestions

Enumerate the concrete setup capabilities in the 'what' clause (e.g., 'configures Databricks auth, serving endpoint, feedback widget, chat history database, and deploys the bundle') to raise specificity.

Add 'deploy' and 'install' to the trigger phrases, since deployment is half of the stated purpose but has no corresponding 'use when' term.

DimensionReasoningScore

Specificity

Names the domain ('Databricks chatbot app') and 1-2 concrete actions ('Set up ... for local development and deployment'), matching the anchor for domain plus a couple of actions rather than the several listed actions required for 4.

3 / 5

Completeness

Explicitly answers both 'what' (set up the app for local development and deployment) and 'when' with four concrete numbered trigger conditions including quoted user phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Good coverage of natural phrases users would say ('quickstart', 'set up', 'authenticate', 'configure databricks', 'enable feedback', 'feedback widget', 'MLFLOW_EXPERIMENT_ID') plus a state-based trigger ('No .env file exists'), but 'deploy' and 'install' — natural terms for the deployment half of the stated capability — are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche (this specific app's setup) with distinct triggers like 'MLFLOW_EXPERIMENT_ID' and 'feedback widget'; minimal conflict risk with other skills.

5 / 5

Total

17

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 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.