CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

quickstart

Set up TypeScript LangChain 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

84%

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-organized quickstart guide that is nearly all executable commands with useful troubleshooting coverage. Minor room to trim explanatory asides, add an explicit post-quickstart verification step, and consider splitting reference material into bundle files.

DimensionReasoningScore

Conciseness

The body is dominated by executable commands and config with almost no concept explanation, but contains minor trimmable asides ('This compiles TypeScript to JavaScript...', 'npm (comes with Node.js)') and a pinned version number ('Databricks CLI v0.283.0+') outside any deprecated section.

4 / 5

Actionability

Fully executable throughout: 'npm run quickstart', the manual 'databricks auth login' fallback, a complete copy-paste-ready .env template, and concrete troubleshooting commands including a jq-piped experiments create command.

5 / 5

Workflow Clarity

Clear sequence from CLI version check through quickstart, fallback auth with an explicit 'Verify' step, install, build, and next steps with a health-check command; however the primary quickstart flow delegates validation to the wizard and post-setup verification is only implicit.

4 / 5

Progressive Disclosure

Well-organized sections with correct pointers to sibling skills (run-locally, deploy), but the ~130-line body is entirely self-contained with no bundle files; the full .env template, model list, and troubleshooting sections could be split into references.

4 / 5

Total

17

/

20

Passed

Description

78%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 and well-phrased trigger clause in third-person voice. The main gap is specificity: it summarizes the outcome ('set up development environment') rather than enumerating the concrete configuration actions the quickstart performs.

Suggestions

Expand the 'what' portion to list 2-3 concrete actions, e.g. 'Set up TypeScript LangChain agent development environment: install dependencies, configure Databricks authentication, create .env and MLflow experiment.'

Add natural trigger synonyms such as 'setup', 'get started', or 'log in' to broaden keyword coverage for the trigger clause.

DimensionReasoningScore

Specificity

Names the domain ('TypeScript LangChain agent development environment') and mentions 1-2 actions ('Set up', 'Configuring Databricks authentication') but does not enumerate the several concrete setup actions (model endpoint, MLflow experiment, .env creation) that the skill actually performs.

3 / 5

Completeness

Clearly states what the skill does and includes an explicit 'Use when:' clause with four conditions, two of which contain concrete quoted trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Explicit natural trigger phrases ('quickstart', 'set up', 'authenticate', 'configure databricks') match what users would say, though common synonyms like 'setup', 'get started', or 'log in' are missing.

4 / 5

Distinctiveness Conflict Risk

The Databricks/LangChain/quickstart niche is distinct with specific triggers, but generic triggers like 'First time setup' and 'set up' carry minor overlap risk with closely related sibling skills (run-locally, deploy).

4 / 5

Total

16

/

20

Passed

Validation

100%

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-langchain-ts/.claude/skills/quickstart/SKILL.md

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.