CtrlK
BlogDocsLog inGet started
Tessl Logo

databricks-data-handling

Implement Delta Lake data management patterns including GDPR, PII handling, and data lifecycle. Use when implementing data retention, handling GDPR requests, or managing data lifecycle in Delta Lake. Trigger with phrases like "databricks GDPR", "databricks PII", "databricks data retention", "databricks data lifecycle", "delete user data".

72

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

80%

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

The content is lean and highly actionable with fully executable SQL and Python across all six steps. Its weak spots are workflow clarity — destructive batch operations need explicit validation/feedback loops beyond dry-run — and progressive disclosure, where the bundled reference is unsignaled and duplicative.

Suggestions

Add an explicit validate-then-fix feedback loop for destructive operations: after dry-run, surface affected rows, require confirmation, execute, then verify the audit log row count matches.

Link references/implementation.md from the body (e.g., under an 'Advanced' section) and de-duplicate it against the inline steps so the reference adds depth rather than repeating them.

Replace f-string SQL interpolation in process_deletion and enforce with parameterized queries or spark.sql(...).collect() input validation to guard against injection in user_id.

DimensionReasoningScore

Conciseness

The body is code-forward and assumes Claude's competence, avoiding tutorials on what Delta Lake or PII is. The deprecation banner is legitimately scoped metadata rather than padding, and every section earns its place. It is not verbose like the 'PDF is a common file format...' example.

3 / 3

Actionability

Every step ships executable SQL and Python (e.g., ALTER TABLE SET TAGS, GDPRHandler.process_deletion, mask_email functions) that is copy-paste ready with real catalog/table paths. It is not pseudocode or abstract description.

3 / 3

Workflow Clarity

The destructive batch operations (GDPR deletion, retention enforcement) rely on a dry-run flag but lack an explicit validate-then-fix feedback loop, and deletion uses string-interpolated SQL with no checkpoint beyond dry-run. The rubric caps destructive/batch workflows lacking feedback loops at 2.

2 / 3

Progressive Disclosure

The body never signals the bundled references/implementation.md (grep finds no link) and that file largely duplicates inline content, so the split is not clearly signaled or well-organized. Structure exists but content that should be separated stays inline, matching the 'could be better organized' anchor.

2 / 3

Total

10

/

12

Passed

Description

100%

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 concise, specific, and complete, clearly stating what the skill does and when to use it with natural trigger phrases. It occupies a distinct databricks-compliance niche with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'GDPR', 'PII handling', 'data retention', and 'data lifecycle' — matching the rubric's anchor for several specific concrete actions. It is not vague like 'Helps with documents' and is comprehensive for its domain.

3 / 3

Completeness

Explicitly answers both 'what' (Delta Lake data management patterns including GDPR, PII handling, data lifecycle) and 'when' (an explicit 'Use when implementing...' clause plus a 'Trigger with phrases like' list).

3 / 3

Trigger Term Quality

Provides natural trigger phrases users would say: 'databricks GDPR', 'databricks PII', 'databricks data retention', 'databricks data lifecycle', 'delete user data'. Good coverage of natural language variations rather than technical jargon.

3 / 3

Distinctiveness Conflict Risk

The databricks/Delta Lake/Unity Catalog niche with databricks-prefixed triggers is a clear, distinct niche unlikely to conflict with unrelated skills. It is far more specific than 'Helps with code and documents'.

3 / 3

Total

12

/

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.