firecrawl-core-workflow-b
Execute Firecrawl secondary workflow: LLM extraction, batch scraping, and site mapping. Use when extracting structured data from pages, batch scraping known URLs, or discovering site structure with the map endpoint. Trigger with phrases like "firecrawl extract", "firecrawl batch scrape", "firecrawl map site", "firecrawl structured data", "firecrawl JSON extract".
67
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 a strong, well-crafted skill description that clearly identifies its scope as a secondary Firecrawl workflow covering three specific capabilities. It includes explicit 'Use when' guidance and concrete trigger phrases, making it easy for Claude to select appropriately. The Firecrawl-prefixed trigger terms and specific action verbs make it highly distinctive and unlikely to conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: LLM extraction, batch scraping, and site mapping. Further elaborates with 'extracting structured data from pages', 'batch scraping known URLs', and 'discovering site structure with the map endpoint'. | 3 / 3 |
Completeness | Clearly answers both 'what' (LLM extraction, batch scraping, site mapping) and 'when' (explicit 'Use when...' clause with specific scenarios, plus a 'Trigger with phrases like...' section providing concrete trigger terms). | 3 / 3 |
Trigger Term Quality | Includes highly specific natural trigger phrases like 'firecrawl extract', 'firecrawl batch scrape', 'firecrawl map site', 'firecrawl structured data', 'firecrawl JSON extract', plus natural terms like 'structured data', 'batch scraping', and 'site structure'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive by specifying 'Firecrawl secondary workflow' and using Firecrawl-prefixed trigger terms. The description carves out a clear niche (LLM extraction, batch scraping, site mapping) that is unlikely to conflict with a general web scraping skill or a primary Firecrawl workflow skill. | 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 full range of Firecrawl's secondary features. Its main weaknesses are the lack of validation/error-recovery steps within the workflows (especially for batch and async operations) and some redundancy in the examples section. The content could be tightened by removing the redundant e-commerce example and adding inline validation checks.
Suggestions
Add validation checkpoints to batch and async workflows — e.g., check for failed pages in batch results, add timeout handling to the polling loop, and verify extraction results are non-empty before proceeding.
Remove or move the redundant e-commerce extract example to a separate EXAMPLES.md file, since Step 1 already demonstrates the same pattern with a complete schema.
Add error handling within code blocks (try/catch) especially for the async batch polling loop, which currently has no timeout or failure recovery.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with executable code examples, but includes some unnecessary commentary (e.g., 'Secondary workflow complementing the scrape/crawl workflow', 'Understanding of JSON Schema (for extract)' prerequisite, and the Output section which just restates what the steps already show). The e-commerce example at the end is largely redundant with Step 1. | 2 / 3 |
Actionability | All steps contain fully executable TypeScript code with concrete API calls, real URLs, and complete JSON schemas. The code is copy-paste ready with clear patterns for each use case (extract with schema, extract with prompt, batch, async batch, map, and combined pipeline). | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced and build logically from simple extraction to combined pipelines. However, there are no validation checkpoints — no verification that extraction results match the schema, no error handling within the code blocks, and the async polling loop lacks timeout/failure handling. For batch operations this is a notable gap. | 2 / 3 |
Progressive Disclosure | The content has good section structure and an error handling table, plus external resource links. However, the skill is quite long (~170 lines of content) with the redundant e-commerce example inline rather than in a separate file. The reference to 'firecrawl-common-errors' is good but the body could benefit from splitting detailed examples into a separate 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
a04d1a2
- 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.