firecrawl-performance-tuning
Optimize Firecrawl scraping performance with caching, batch scraping, and format selection. Use when experiencing slow scrapes, optimizing credit usage per page, or building high-throughput scraping pipelines. Trigger with phrases like "firecrawl performance", "optimize firecrawl", "firecrawl latency", "firecrawl caching", "firecrawl slow", "firecrawl batch".
84
82%
Does it follow best practices?
Impact
Pending
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 (Firecrawl performance optimization), lists concrete capabilities (caching, batch scraping, format selection), provides explicit 'Use when' triggers, and includes a comprehensive set of natural trigger phrases. It uses proper third-person voice throughout and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: caching, batch scraping, and format selection. Also mentions specific outcomes like optimizing credit usage per page and building high-throughput scraping pipelines. | 3 / 3 |
Completeness | Clearly answers both 'what' (optimize Firecrawl scraping with caching, batch scraping, format selection) and 'when' (experiencing slow scrapes, optimizing credit usage, building high-throughput pipelines) with an explicit 'Use when' clause and trigger phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms explicitly listed: 'firecrawl performance', 'optimize firecrawl', 'firecrawl latency', 'firecrawl caching', 'firecrawl slow', 'firecrawl batch'. Also includes natural phrases like 'slow scrapes' and 'credit usage' that users would say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific tool (Firecrawl) and a specific concern (performance optimization). The trigger terms are all Firecrawl-specific, making it very unlikely to conflict with general web scraping or other tool 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 the key performance optimization techniques for Firecrawl. Its main weaknesses are the lack of validation/error-handling within code examples (no try/catch, no retry logic, no verification steps) and the somewhat monolithic structure that could benefit from splitting detailed implementations into separate files. The content is mostly concise but has room for tightening.
Suggestions
Add try/catch blocks and retry logic to code examples, especially for batch scraping and cached scraping, to provide proper error recovery feedback loops.
Add a validation checkpoint after Step 4 (batch scrape) to verify results before proceeding — e.g., check success count vs total URLs and handle partial failures.
Consider moving the full caching implementation and performance comparison script to separate referenced files to keep the main skill leaner and improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good code examples, but includes some unnecessary commentary (e.g., '// Typical savings: 50-80% credit reduction' is speculative, inline comments like '// 3 API calls' and '// 1 API call, internally parallelized' are obvious). The latency benchmarks table adds value but the numbers are approximate and potentially misleading. Some code blocks could be tighter. | 2 / 3 |
Actionability | Excellent executable TypeScript examples throughout — every step has copy-paste ready code with real imports, real API calls, and concrete patterns (LRU caching, batch scraping, timed scraping). The error handling table maps specific issues to specific solutions. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced from highest-impact to measurement, which is good. However, there are no validation checkpoints or feedback loops — for example, no guidance on verifying that format reduction actually improved performance, no check that batch scrape succeeded before proceeding, and no error handling within the code examples themselves (no try/catch, no retry logic). | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a resources section linking to external docs. However, the skill is quite long (~150 lines of content) and some sections like the full caching implementation or the performance comparison script could be split into referenced files. The 'Next Steps' reference to 'firecrawl-cost-tuning' is good but the main body is somewhat monolithic. | 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
c8a915c
- 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.