CtrlK
BlogDocsLog inGet started
Tessl Logo

databricks-migration-deep-dive

Execute comprehensive platform migrations to Databricks from legacy systems. Use when migrating from on-premises Hadoop, other cloud platforms, or legacy data warehouses to Databricks. Trigger with phrases like "migrate to databricks", "hadoop migration", "snowflake to databricks", "legacy migration", "data warehouse migration".

64

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

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable with complete executable code and a clear sequenced workflow including validation and rollback, but it is verbose and fails to leverage its reference file: implementation.md is neither linked from the body nor used to offload the duplicated detailed code.

Suggestions

Link references/implementation.md from the body (e.g. a '## Implementation details' section pointing to it) and move the duplicated detailed code there, keeping SKILL.md as a lean overview.

Add an explicit validate->fix->retry loop to the batch migration path (when migrate_table reports MISMATCH, diagnose via the error-handling table and re-run) to satisfy the feedback-loop expectation for destructive/batch operations.

Tighten the six code blocks to the essential, copy-paste-ready snippets and drop the duplicated discovery/schema/cutover implementations already present in the reference file.

DimensionReasoningScore

Conciseness

The body is mostly executable code that earns its place with little concept-explanation padding, but at ~340 lines across six full code blocks it is verbose, and much of the content duplicates references/implementation.md rather than being kept lean.

2 / 3

Actionability

Every step ships complete, copy-paste-ready Python/SQL (e.g. assess_hive_metastore, migrate_table, the Auto Loader streaming block) with concrete Spark SQL and DDL rather than pseudocode.

3 / 3

Workflow Clarity

The six steps are clearly sequenced and validation exists (row-count checks, cutover rollback, error-handling table), but the batch/destructive migration only records OK/MISMATCH without an explicit validate->fix->retry feedback loop, which caps this dimension at 2 per the rubric.

2 / 3

Progressive Disclosure

A bundle reference (references/implementation.md) exists but is never signaled or linked from the body, and the body inlines full code for all six steps that overlaps that reference — content that should be split out is inline and the reference path is not clearly navigated.

2 / 3

Total

9

/

12

Passed

Description

90%

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 explicit 'what' and 'when' clauses and natural trigger phrases, clearly scoped to Databricks migrations. The only weakness is a single broad action verb rather than a list of concrete capabilities.

DimensionReasoningScore

Specificity

The description names the domain and a single high-level action ('Execute comprehensive platform migrations to Databricks from legacy systems') but does not enumerate multiple concrete actions, and 'comprehensive' reads as mild over-claim rather than a score-3 list of specific actions.

2 / 3

Completeness

It explicitly states both what it does ('Execute comprehensive platform migrations to Databricks') and when to use it ('Use when migrating from on-prem Hadoop, other cloud platforms, or legacy data warehouses to Databricks').

3 / 3

Trigger Term Quality

Trigger phrases like 'migrate to databricks', 'hadoop migration', 'snowflake to databricks', 'legacy migration', and 'data warehouse migration' are natural terms a user would actually say, giving good coverage.

3 / 3

Distinctiveness Conflict Risk

The Databricks-migration niche with source-specific triggers (Hadoop, Snowflake, legacy DW) is distinct and unlikely to conflict with unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.