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".
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description with strong trigger terms and completeness. It clearly defines when to use the skill with explicit trigger phrases and a 'Use when' clause. The main weakness is that the capability description stays at a pattern/category level rather than listing specific concrete actions the skill performs.
Suggestions
Add more specific concrete actions to improve specificity, e.g., 'Delete user records for GDPR right-to-erasure requests, anonymize PII columns, configure table retention policies, implement data purge workflows.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Delta Lake data management) and mentions patterns like GDPR, PII handling, and data lifecycle, but doesn't list specific concrete actions (e.g., 'delete user records', 'anonymize PII columns', 'set retention policies'). The actions remain at a pattern/category level rather than concrete operations. | 2 / 3 |
Completeness | Clearly answers both 'what' (implement Delta Lake data management patterns including GDPR, PII handling, data lifecycle) and 'when' (explicit 'Use when' clause plus 'Trigger with phrases like' providing concrete trigger guidance). | 3 / 3 |
Trigger Term Quality | Includes explicit trigger phrases like 'databricks GDPR', 'databricks PII', 'databricks data retention', 'databricks data lifecycle', 'delete user data' — these are natural terms users would actually say and cover good variations of the domain. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of Delta Lake/Databricks with GDPR/PII/data lifecycle creates a very specific niche. The trigger terms are domain-specific enough (e.g., 'databricks GDPR', 'databricks data retention') that conflicts with other skills are unlikely. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill with well-sequenced steps, executable code, and built-in safety mechanisms (dry-run defaults, audit logging). Its main weakness is length—the inline class definitions make it verbose for a SKILL.md that could benefit from splitting detailed implementations into bundle files. The error handling table and resources section add practical value.
Suggestions
Extract the GDPRHandler and RetentionEnforcer class implementations into separate bundle files (e.g., gdpr_handler.py, retention_enforcer.py) and reference them from the SKILL.md to improve progressive disclosure and reduce body length.
Remove the Output section as it merely restates what each step already describes, saving tokens without losing information.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with executable code and minimal fluff, but some sections are longer than necessary—e.g., the full class definitions could be tightened, and the Output section largely restates what the steps already cover. There's minimal explanation of concepts Claude already knows, but the overall length (~200+ lines) could be reduced. | 2 / 3 |
Actionability | All guidance is concrete with fully executable SQL and Python code. The GDPR handler class, retention enforcer, masking functions, and row-level security are all copy-paste ready with specific table/column names and usage examples. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced from classification through deletion, retention, masking, security, and SAR reporting. Critical validation is built in via dry-run patterns (dry_run=True by default) with explicit audit logging, and the error handling table addresses common failure modes with solutions. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a resources section linking to external docs, but the skill is monolithic—all code is inline with no bundle files to offload detailed implementations. The class definitions for GDPRHandler and RetentionEnforcer could be in separate referenced files, keeping the SKILL.md as a concise overview. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
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 | 9 / 11 Passed | |
- Commit
3a2d27d
- 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.