CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

67

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

64%

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

The body is highly actionable with complete, executable code and clear cost tables across six sequenced steps. It is slightly padded with redundant prose/comments, and lacks explicit validation checkpoints for batch credit operations; progressive disclosure is only partial since there are no bundle files and the lone external reference is unsignaled.

Suggestions

Trim redundant prose: the Overview's credit-per-operation sentences duplicate the Credit Cost Table — keep only the table and the one-line savings claim.

Add an explicit validation checkpoint in Step 1/Step 5 (e.g., 'query credits before crawling; if insufficient, stop') to give batch credit operations a validate->retry feedback loop.

Either create the referenced 'firecrawl-reference-architecture' as a real bundle file with a signaled path, or remove the Next Steps pointer to avoid a dangling reference.

DimensionReasoningScore

Conciseness

Mostly efficient with executable code and tight tables, but the Overview restates the credit table in prose and several comments ('Cost: potentially 100,000+ credits', 'Typical savings: 50-80%') restate what the tables already show, adding modest padding.

2 / 3

Actionability

Provides fully executable TypeScript/bash snippets — crawlUrl with limit/maxDepth, batchScrapeUrls, mapUrl, a working cache helper, a CreditBudget class, and curl calls — copy-paste ready with concrete parameters.

3 / 3

Workflow Clarity

Six numbered steps give a clear sequence, but batch/credit-spending operations lack explicit validation checkpoints (e.g., 'verify balance before crawling'); the credit-budget snippet is illustrative rather than an enforced validate->retry loop, capping it at 2.

2 / 3

Progressive Disclosure

Well-organized sections, but content is entirely inline with no bundle files; the single 'Next Steps' pointer to an external skill 'firecrawl-reference-architecture' is unsignaled (no path, no bundle) and references that do not exist in the bundle, so structure is only partly realized.

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.

The description is specific, complete, and well-triggered: it states concrete cost-reduction techniques, gives a 'Use when' clause, and lists natural trigger phrases tied to the Firecrawl product. It is concise and distinct from other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'crawl limits, format selection, caching, and credit monitoring' and 'credit budget alerts' — naming specific techniques rather than vague language.

3 / 3

Completeness

Explicitly answers both 'what' (optimize costs via limits/format/caching/monitoring) and 'when' with a 'Use when...' clause plus explicit trigger phrases.

3 / 3

Trigger Term Quality

Provides good coverage of natural phrases a user would say — 'firecrawl cost', 'firecrawl billing', 'reduce firecrawl costs', 'firecrawl pricing', 'firecrawl credits', 'firecrawl budget'.

3 / 3

Distinctiveness Conflict Risk

Has a clear Firecrawl-cost niche with distinct, product-specific triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.