databricks-rate-limits
Implement Databricks API rate limiting, backoff, and idempotency patterns. Use when handling rate limit errors, implementing retry logic, or optimizing API request throughput for Databricks. Trigger with phrases like "databricks rate limit", "databricks throttling", "databricks 429", "databricks retry", "databricks backoff".
84
82%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a well-crafted skill description that clearly defines its scope (Databricks API rate limiting and retry patterns), provides explicit 'Use when' guidance, and includes natural trigger phrases. It uses proper third-person voice and is concise without being vague. It serves as a strong example of how to write a skill description that enables accurate skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'rate limiting', 'backoff', and 'idempotency patterns' — these are distinct, concrete technical capabilities rather than vague abstractions. | 3 / 3 |
Completeness | Clearly answers both 'what' (implement rate limiting, backoff, and idempotency patterns for Databricks API) and 'when' (handling rate limit errors, implementing retry logic, optimizing API request throughput), with explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'databricks rate limit', 'databricks throttling', 'databricks 429', 'databricks retry', 'databricks backoff'. These are realistic phrases a developer would use when encountering these issues. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped specifically to Databricks API rate limiting and retry patterns. The combination of 'Databricks' + 'rate limiting/backoff/idempotency' creates a clear niche unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, highly actionable skill with excellent executable code examples covering rate limiting, backoff, batching, and idempotency for Databricks APIs. Its main weaknesses are the lack of validation checkpoints for destructive operations (bulk cluster deletion) and the monolithic structure that could benefit from splitting detailed implementations into referenced files. Minor verbosity in prerequisites and output sections could be trimmed.
Suggestions
Add a validation/dry-run step before the bulk cluster cleanup example (e.g., list clusters to delete first, confirm count, then proceed) to prevent accidental destructive operations.
Consider splitting the detailed code implementations (Steps 3-5) into a separate PATTERNS.md file, keeping SKILL.md as a concise overview with the backoff decorator and error table.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with executable code and useful tables, but includes some unnecessary elements like the 'Prerequisites' section (Claude knows what databricks-sdk is), the 'Understanding of async patterns' note, and the 'Output' section which just restates what was already shown. The rate limit tiers table is useful domain knowledge Claude wouldn't have, but some print statements and comments are slightly verbose. | 2 / 3 |
Actionability | All code examples are fully executable, copy-paste ready Python with proper imports, concrete class/function definitions, and realistic usage patterns. The retry decorator, RateLimiter class, batch processor, and idempotent submission function are all complete and immediately usable. | 3 / 3 |
Workflow Clarity | The steps are clearly sequenced from understanding limits through implementing increasingly sophisticated patterns (backoff → rate limiting → batching → idempotency). However, for destructive operations like the bulk cluster cleanup example, there's no validation/confirmation step before permanent deletion, and the batch job runner lacks error aggregation or a verification step to confirm all jobs submitted successfully. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a logical progression, but at ~180 lines it's a monolithic file that could benefit from splitting the detailed code examples (batch processing, idempotency patterns) into separate referenced files. The single reference to 'databricks-security-basics' is appropriate, but the main file carries too much inline detail for an overview. | 2 / 3 |
Total | 9 / 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.