Name: deploy
Rating: 64 (1 reviews)
Author: databricks

deploy

Deploy TypeScript LangChain agent to Databricks. Use when: (1) User wants to deploy, (2) User says 'deploy', 'push to databricks', 'production', (3) After making changes that need deployment.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./agent-langchain-ts/.claude/skills/deploy/SKILL.md

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 content is highly actionable with executable commands and config throughout and a well-checkpointed main deploy workflow. Its weaknesses are redundancy from repeated commands and a monolithic structure that inlines material better suited to separate reference files.

Suggestions

Deduplicate the repeated 'databricks bundle deploy -t dev' invocations and collapse the Quick Deploy block into a pointer to the Step-by-Step section to tighten token efficiency.

Move the CI/CD GitHub Actions example and the detailed troubleshooting entries into separate reference files (e.g., references/CI-CD.md, references/TROUBLESHOOTING.md) and link to them from the body to improve progressive disclosure.

Add an explicit validate/confirm checkpoint before destructive recovery actions (delete and recreate, --force-bind) so the workflow has feedback loops for risky operations.

Dimension	Reasoning	Score
Conciseness	The body is mostly commands and config with no concept over-explanation, but it repeats the same 'databricks bundle deploy -t dev' command across many sections and the Quick Deploy block duplicates the Step-by-Step flow, so it could be noticeably tightened.	3 / 5
Actionability	Provides fully executable, copy-paste-ready bash commands, YAML configs, curl examples, and a GitHub Actions workflow covering the common deployment, verification, and troubleshooting cases.	5 / 5
Workflow Clarity	The Step-by-Step flow is clearly sequenced with validate and verify checkpoints, but the destructive recovery paths (delete and recreate app, --force-bind) lack explicit validation feedback loops before execution, leaving minor validation gaps.	4 / 5
Progressive Disclosure	Section headers give reasonable structure, but the skill is a long monolithic SKILL.md with CI/CD examples, full configs, and troubleshooting all inlined and only one external reference (the shared MLFLOW.md); content that should be split into reference files is not.	3 / 5
	Total	15 / 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.

The description is strong: it clearly defines a specific niche, uses third-person voice, and explicitly covers both what the skill does and when to use it with concrete triggers. Its only weakness is listing a single action, leaving specificity slightly below comprehensive.

Suggestions

Add one or two more concrete actions (e.g., 'validate bundle configuration, deploy to dev or prod, and start the deployed app') to lift specificity from a single named action to several.

Include a couple of natural synonyms users might say (e.g., 'ship', 'publish', 'go live') to round out trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (TypeScript LangChain agent, Databricks) and one concrete action ('Deploy'), but lists no additional specific actions, matching the anchor for naming a domain with 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	Explicitly states what the skill does ('Deploy TypeScript LangChain agent to Databricks') and provides a concrete 'Use when' clause with three numbered trigger scenarios, clearly answering both what and when.	5 / 5
Trigger Term Quality	Includes natural user phrases like 'deploy', 'push to databricks', and 'production' that a user would actually say, but misses synonyms such as 'ship', 'publish', or 'go live', so it falls just below comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The narrow niche of deploying a TypeScript LangChain agent to Databricks with specific trigger phrases gives it a clear distinct identity with minimal conflict risk against other skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: databricks/app-templates
Path: agent-langchain-ts/.claude/skills/deploy/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.