firecrawl-cost-tuning
Optimize Firecrawl costs through crawl limits, format selection, caching, and credit monitoring. Use when analyzing Firecrawl billing, reducing API costs, or implementing credit budget alerts. Trigger with phrases like "firecrawl cost", "firecrawl billing", "reduce firecrawl costs", "firecrawl pricing", "firecrawl credits", "firecrawl budget".
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 a well-crafted skill description that clearly defines its scope (Firecrawl cost optimization), lists concrete actions, provides explicit 'Use when' guidance, and includes natural trigger phrases. It follows the third-person voice convention and is concise without being vague. The narrow domain focus makes it highly distinctive and unlikely to conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: crawl limits, format selection, caching, credit monitoring, billing analysis, API cost reduction, and credit budget alerts. | 3 / 3 |
Completeness | Clearly answers both 'what' (optimize Firecrawl costs through crawl limits, format selection, caching, credit monitoring) and 'when' (explicit 'Use when' clause plus a 'Trigger with phrases like' section with specific terms). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'firecrawl cost', 'firecrawl billing', 'reduce firecrawl costs', 'firecrawl pricing', 'firecrawl credits', 'firecrawl budget'. These are realistic phrases a user would type. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific niche (Firecrawl cost optimization) with domain-specific trigger terms that are 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 the full spectrum of Firecrawl cost optimization. Its main weaknesses are moderate verbosity (explanatory comments and overview text that Claude doesn't need) and the lack of explicit validation/verification steps after implementing cost-saving measures. The content would benefit from being trimmed and having some reference material split into separate files.
Suggestions
Remove the overview paragraph and let the credit cost table speak for itself — Claude doesn't need an explanation of what credits are or marketing claims about savings percentages.
Add a validation step after implementing budget tracking, e.g., 'Verify budget is working: run a small crawl with limit: 5, check that budget.remaining() decreases by 5, then check the /team/credits endpoint to confirm actual usage matches.'
Consider moving the detailed CreditBudget class implementation and caching code into a separate reference file, keeping only the key patterns (limit + includePaths, map-then-scrape) inline in SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The overview paragraph explaining what Firecrawl credits are and the '50-80% savings' marketing-style claim is unnecessary padding. The code examples themselves are well-structured but include some redundant comments (e.g., '// Free — no API call', '// Typical savings: 50-80%'). The cost comparison comments in each step add some verbosity but are arguably useful for motivation. | 2 / 3 |
Actionability | Every step includes fully executable TypeScript or bash code with concrete examples. The code is copy-paste ready with real API calls, proper imports, and complete class implementations. The credit cost table and error handling table provide specific, actionable reference information. | 3 / 3 |
Workflow Clarity | The steps are clearly sequenced and logically ordered from most impactful (set limits) to supplementary (choose formats). However, there are no explicit validation checkpoints or feedback loops — for example, after implementing caching or budget tracking, there's no step to verify the savings or validate that the budget tracker is working correctly. Given that unbounded crawls are described as potentially destructive (thousands of credits in minutes), validation steps would be important. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and tables, but it's quite long (~150 lines of substantive content) and could benefit from splitting the detailed code examples into a separate reference file. The 'Next Steps' reference to firecrawl-reference-architecture is good, but the inline content is heavy for a SKILL.md overview. The credit cost table and error handling table could be in a reference file. | 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.