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".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable with real, executable Firecrawl code and a clear step sequence, but it is a long single-file monolith with some redundant examples and missing inline validation checkpoints for its batch/crawl operations.

Suggestions

Consolidate Step 6's timedScrape helper with the Examples 'Performance Comparison Script' — they measure the same thing and one copy would trim tokens.

Add an explicit validation checkpoint to the batch/crawl steps (e.g., check batchResult.success and handle partial failures before proceeding), which would lift workflow clarity above 2.

Move the latency benchmark table and detailed comparison examples into a references file (e.g., references/benchmarks.md) linked from the Overview to reduce the inline wall of content.

Dimension	Reasoning	Score
Conciseness	The body is action-oriented code without conceptual padding, but ~190 lines with overlapping examples (Step 6's timedScrape vs the Examples 'Performance Comparison Script', plus repeated onlyMainContent/formats blocks) could be tightened to earn every token.	2 / 3
Actionability	Fully executable TypeScript using real SDK methods (scrapeUrl, batchScrapeUrls, mapUrl, crawlUrl) with specific options and contrast comments — copy-paste ready.	3 / 3
Workflow Clarity	Six steps are clearly sequenced and an error-handling table gives recovery guidance, but the batch (Step 4) and crawl (Step 5) operations lack explicit inline validation checkpoints, capping clarity at 2 per the batch-operations guideline.	2 / 3
Progressive Disclosure	Sections are well-organized, but the file is a ~190-line monolith with no bundle files; content like the detailed examples and benchmarks could be split into one-level-deep references rather than kept inline.	2 / 3
	Total	9 / 12 Passed

Description

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.

A strong, third-person description that names concrete actions, provides explicit 'Use when' triggers, and stays scoped to a distinct Firecrawl niche. Voice is correctly third person with no vague padding.

Dimension	Reasoning	Score
Specificity	Names three concrete techniques — 'caching, batch scraping, and format selection' — directly tied to the optimization goal, matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly states what it does ('Optimize Firecrawl scraping performance with caching, batch scraping, and format selection') and when to use it ('Use when experiencing slow scrapes... Trigger with phrases like...'), answering both what and when.	3 / 3
Trigger Term Quality	Explicit trigger phrases like 'firecrawl slow', 'optimize firecrawl', and 'firecrawl latency' are natural terms a user would say when needing this skill, giving good coverage.	3 / 3
Distinctiveness Conflict Risk	All triggers are Firecrawl-specific, carving a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 6e3a65f

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.