firecrawl-rate-limits
Implement Firecrawl rate limiting, backoff, and request queuing patterns. Use when handling 429 errors, implementing retry logic, or optimizing API request throughput for Firecrawl. Trigger with phrases like "firecrawl rate limit", "firecrawl throttling", "firecrawl 429", "firecrawl retry", "firecrawl backoff".
84
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 an excellent skill description that clearly defines its scope, provides explicit trigger conditions, and lists natural user phrases. It uses third-person voice correctly, is concise without being vague, and carves out a very specific niche (Firecrawl rate limiting) that would be easily distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: rate limiting, backoff, request queuing patterns, handling 429 errors, implementing retry logic, and optimizing API request throughput. These are all concrete, well-defined technical actions. | 3 / 3 |
Completeness | Clearly answers both 'what' (implement rate limiting, backoff, and request queuing patterns) and 'when' (handling 429 errors, implementing retry logic, optimizing throughput) with an explicit 'Use when' clause and explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger phrases users would say: 'firecrawl rate limit', 'firecrawl throttling', 'firecrawl 429', 'firecrawl retry', 'firecrawl backoff'. These are highly specific and cover common variations of how users would describe this need. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific combination of 'Firecrawl' as the target API and the narrow focus on rate limiting/retry patterns. The 'firecrawl' prefix on all trigger terms makes it very unlikely to conflict with generic rate limiting or other API 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, actionable skill with excellent executable code examples covering multiple rate-limiting strategies. Its main weaknesses are moderate verbosity (explaining concepts Claude already knows, like what 429 means), lack of explicit validation/verification steps in the workflow, and inline density that could benefit from progressive disclosure into supporting files.
Suggestions
Remove explanatory text Claude already knows (e.g., what 429 means, what rate limits are) and trim the overview to just the rate limit tiers table and key constraints.
Add explicit validation checkpoints, such as verifying batch results count matches input URLs count, or logging/checking that retry logic actually resolved the 429 before proceeding.
Consider splitting the detailed code examples (Steps 2-4, RateLimitMonitor) into a separate EXAMPLES.md or PATTERNS.md file, keeping SKILL.md as a concise overview with pointers.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The rate limit tiers table and some commentary (e.g., 'This skill covers backoff strategies, request queuing, and proactive throttling') add moderate overhead. The code examples are mostly lean but the overall document could be tightened—the overview section explains what 429 means, which Claude already knows. | 2 / 3 |
Actionability | All four steps provide fully executable TypeScript code with concrete imports, configuration, and usage examples. The code is copy-paste ready with clear patterns for backoff, queuing, proactive throttling, and batch scraping. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced and build on each other (backoff → queue → throttle → batch), but there are no explicit validation checkpoints or feedback loops for verifying that rate limiting is working correctly. For operations involving batch/destructive API calls, the absence of a 'verify results' step is a gap. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a reference to another skill at the end, but the document is fairly long (~150 lines of code) and could benefit from splitting detailed code examples into a separate reference file while keeping the SKILL.md as a concise overview with pointers. | 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.