databricks-performance-tuning
Optimize Databricks cluster and query performance. Use when jobs are running slowly, optimizing Spark configurations, or improving Delta Lake query performance. Trigger with phrases like "databricks performance", "spark tuning", "databricks slow", "optimize databricks", "cluster performance".
83
81%
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 excellent trigger terms and completeness. Its main weakness is that the 'what' portion is somewhat high-level—it says 'optimize performance' without listing specific concrete actions like adjusting shuffle partitions, configuring autoscaling, or analyzing query plans. Adding 2-3 specific actions would elevate it further.
Suggestions
Add specific concrete actions to the first sentence, e.g., 'Optimize Databricks cluster and query performance by tuning Spark configurations, adjusting shuffle partitions, configuring autoscaling, and improving Delta Lake file compaction.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Databricks cluster and query performance) and mentions some areas like Spark configurations and Delta Lake query performance, but doesn't list specific concrete actions (e.g., 'tune shuffle partitions', 'configure autoscaling', 'optimize file compaction'). | 2 / 3 |
Completeness | Clearly answers both 'what' (optimize Databricks cluster and query performance) and 'when' (jobs running slowly, optimizing Spark configurations, improving Delta Lake query performance) with explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Includes a strong set of natural trigger terms users would actually say: 'databricks performance', 'spark tuning', 'databricks slow', 'optimize databricks', 'cluster performance'. These cover common user phrasings well. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around Databricks/Spark/Delta Lake performance tuning. The specific platform and technology references make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%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, highly actionable skill with excellent concrete guidance for Databricks performance tuning across multiple workload types. Its main weaknesses are moderate verbosity (could trim ~20% without losing value) and the lack of explicit validation checkpoints in the workflow, which is important given that operations like OPTIMIZE and VACUUM affect production tables. The error handling table and before/after comparison example are standout features.
Suggestions
Add explicit validation gates after key steps — e.g., 'Run DESCRIBE DETAIL and verify numFiles decreased before proceeding to VACUUM' and 'Check spark.sql(query).explain() confirms broadcast join before running at scale'.
Trim the Prerequisites and Output sections, and reduce inline comments that explain obvious things (e.g., '# 128MB' next to the byte value is fine, but comments like '# triggers expensive shuffle' could be cut since the BAD/GOOD labels already convey this).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of tables and code blocks, but includes some unnecessary elements like the 'Prerequisites' section (Claude knows it needs access), the 'Output' section restating what was covered, and minor verbosity in comments. The recommend_cluster function, while useful, adds bulk that could be trimmed. | 2 / 3 |
Actionability | Excellent actionability throughout — every step includes executable SQL or Python code with specific commands, concrete instance types, real config keys, and copy-paste ready examples. The before/after comparison script and query history analysis are particularly practical. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced, but there are no explicit validation checkpoints or feedback loops. For operations like OPTIMIZE and VACUUM (which can be destructive/long-running on large tables), there's no 'verify before proceeding' step. The DESCRIBE DETAIL check after OPTIMIZE is mentioned but not enforced as a gate. | 2 / 3 |
Progressive Disclosure | Content is well-structured with clear sections, tables for quick reference, and external resource links for deeper dives. The skill appropriately keeps actionable content inline while pointing to official docs for comprehensive references. The 'Next Steps' section provides clear navigation to related skills. | 3 / 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
70e9fa4
- 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.