instantly-rate-limits
Implement Instantly.ai rate limiting, backoff, and request throttling patterns. Use when handling 429 errors, implementing retry logic, or building high-throughput Instantly integrations. Trigger with phrases like "instantly rate limit", "instantly 429", "instantly throttle", "instantly backoff", "instantly retry".
84
82%
Does it follow best practices?
Impact
—
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 around Instantly.ai rate limiting patterns. It excels in all dimensions: specific capabilities, natural trigger terms, completeness with explicit 'Use when' and 'Trigger with' clauses, and strong distinctiveness through product-specific terminology. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: rate limiting, backoff, request throttling patterns. These are distinct, actionable capabilities rather than vague language. | 3 / 3 |
Completeness | Clearly answers both 'what' (implement rate limiting, backoff, and request throttling patterns for Instantly.ai) and 'when' (handling 429 errors, implementing retry logic, building high-throughput Instantly integrations) with explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'instantly rate limit', 'instantly 429', 'instantly throttle', 'instantly backoff', 'instantly retry', plus contextual terms like '429 errors' and 'retry logic' that users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive by targeting a specific product (Instantly.ai) combined with a specific technical concern (rate limiting/throttling). The trigger terms are product-specific ('instantly rate limit', 'instantly 429') making conflicts with other skills very unlikely. | 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 complete, executable TypeScript implementations for rate limiting patterns. Its main weaknesses are length (the full implementations could be split into referenced files) and the lack of explicit validation checkpoints for batch operations. The error handling table and known rate limits table are excellent additions that add real value.
Suggestions
Add a validation/dry-run step to the batch operations pattern (Step 4) — e.g., validate lead data before submission and add a checkpoint to review results after the first batch before continuing.
Extract the full class implementations (RequestQueue, ThrottledEmailFetcher) into separate referenced files, keeping SKILL.md as a concise overview with usage examples and links to the detailed implementations.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with good use of tables and code, but includes some unnecessary elements like the 'Prerequisites' section mentioning 'Understanding of exponential backoff patterns' (Claude knows this), and some comments in code that explain obvious things. The code blocks are fairly lengthy but mostly justified by being complete implementations. | 2 / 3 |
Actionability | All code examples are fully executable TypeScript with complete implementations — the backoff function, request queue, throttled email fetcher, and batch operations pattern are all copy-paste ready with concrete defaults, error handling, and usage examples. | 3 / 3 |
Workflow Clarity | The steps are clearly sequenced and build on each other (backoff → queue → throttled fetcher → batch), and the error handling table is excellent. However, there are no explicit validation checkpoints — for batch operations involving potentially destructive lead imports, there's no verify/dry-run step or feedback loop for checking results before proceeding. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a good error handling table, but at ~200 lines it's quite long for a SKILL.md. The detailed implementations of RequestQueue, ThrottledEmailFetcher, and batch operations could be split into referenced files, keeping SKILL.md as a concise overview with patterns and links. | 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.