Name: quickstart
Rating: 67.2 (1 reviews)
Author: databricks

quickstart

Set up Databricks agent development environment. Use when: (1) First time setup, (2) Configuring Databricks authentication, (3) User says 'quickstart', 'set up', 'authenticate', or 'configure databricks', (4) No .env file exists.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

71%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 with executable commands and a clearly sequenced, dependency-aware setup workflow backed by idempotency and error-handling guidance. Its main weaknesses are verbosity with repetition between the setup flow and the prompt tables, and the absence of any bundle files to offload the reference material that is currently inlined.

Suggestions

Consolidate the 'Setup Flow (for Claude)' steps and the 'Interactive Prompts (and How to Skip Them)' tables — they restate the same prompts — to remove repetition and trim length.

Move the Run Quickstart options reference and the Interactive Prompts tables into a references/ file (e.g. references/prompts.md) and link to it, so SKILL.md stays a lean overview.

Add an explicit per-step validation checkpoint (e.g. 'confirm the recorded flags before running') to raise workflow clarity from a clear sequence to one with explicit validate-then-proceed gates.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational and avoids explaining basic concepts Claude already knows, but at ~250 lines it is verbose and repeats information — the 'Setup Flow' steps and the later 'Interactive Prompts' tables cover overlapping ground. Not a 4 because the repetition and length are more than minor; not a 2 because it is not padded with irrelevant explanation.	3 / 5
Actionability	Provides fully executable, copy-paste commands throughout ('databricks auth profiles', 'uv run quickstart --profile ...') with four worked examples covering existing-profile, new-workspace, bind-app, and skip-lakebase cases, matching the top anchor. Not below 5 because examples cover the common cases concretely.	5 / 5
Workflow Clarity	Steps 1–4 are clearly sequenced with per-step dependencies stated, plus idempotency guidance and an explicit error feedback loop ('If the script exits non-zero, surface its error output verbatim and stop'). Not a 5 because validation checkpoints are implicit per step rather than an explicit validate-then-proceed checklist; not a 3 because error recovery and idempotency are present.	4 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), so all reference-style material — the Interactive Prompts tables and the Run Quickstart options reference — is inlined in a single 250-line file that could plausibly be split out. Not a 4 because content that belongs in a separate reference file is inline; not a 2 because section headers make it navigable rather than a structureless wall.	3 / 5
	Total	15 / 20 Passed

Description

90%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 states the capability plainly, gives an explicit enumerated 'Use when' clause with natural trigger phrases, and is scoped to a distinct Databricks niche. The only weakness is that 'specificity' lists just two actions (set up environment, configure auth) rather than the fuller set the skill actually performs.

Dimension	Reasoning	Score
Specificity	Quotes 'Set up Databricks agent development environment' and 'Configuring Databricks authentication' — the domain plus two concrete actions, but coverage is not comprehensive (no mention of app binding, Lakebase, MLflow wiring that the body covers). Not a 4 because it stops at two actions rather than listing several; not a 2 because the actions are concrete, not minimal/generic.	3 / 5
Completeness	Explicitly answers both: 'what' ('Set up Databricks agent development environment') and 'when' ('Use when: (1) First time setup ... (4) No .env file exists') with concrete trigger phrases, matching the top anchor. Not a 4 because the 'when' is explicit and specific, not merely present.	5 / 5
Trigger Term Quality	Quotes natural phrases users would say — 'quickstart', 'set up', 'authenticate', 'configure databricks' — plus synonyms and the '.env' file extension, matching the comprehensive-coverage anchor. Not below 5 because synonym and extension coverage is present.	5 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche ('Databricks agent development environment') with Databricks-specific triggers, giving minimal conflict risk with other skills. Not a 4 because the niche and triggers are distinct rather than only mostly distinct.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: databricks/app-templates
Path: agent-langgraph/.claude/skills/quickstart/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.