firecrawl-core-workflow-a
Execute Firecrawl primary workflow: scrape and crawl websites into LLM-ready markdown. Use when scraping single pages, crawling entire sites, or building content ingestion pipelines with Firecrawl's scrapeUrl and crawlUrl methods. Trigger with phrases like "firecrawl scrape", "firecrawl crawl site", "scrape page to markdown", "crawl documentation".
89
88%
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 strong skill description that clearly identifies the tool (Firecrawl), lists specific capabilities (scraping, crawling, markdown conversion), and provides explicit trigger guidance with natural user phrases. It uses proper third-person voice and is concise without being vague. The inclusion of specific API method names and example trigger phrases makes it highly actionable for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: scrape websites, crawl websites, convert to LLM-ready markdown, build content ingestion pipelines. Also names specific methods (scrapeUrl, crawlUrl). | 3 / 3 |
Completeness | Clearly answers both 'what' (scrape and crawl websites into LLM-ready markdown using Firecrawl's scrapeUrl and crawlUrl methods) and 'when' (explicit 'Use when' clause plus 'Trigger with phrases like' providing concrete trigger guidance). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'firecrawl scrape', 'firecrawl crawl site', 'scrape page to markdown', 'crawl documentation', plus method names like scrapeUrl and crawlUrl that technical users would reference. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific tool name 'Firecrawl', specific method names (scrapeUrl, crawlUrl), and the niche of converting web content to LLM-ready markdown. Unlikely to conflict with generic web scraping or other crawling skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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 executable TypeScript examples covering the full Firecrawl scrape/crawl workflow. The step-by-step progression and error handling table are strong. Minor weaknesses include some verbosity in comments and structure that could be tightened, and the additional examples section could be split into a separate reference file to improve progressive disclosure.
Suggestions
Trim inline comments that explain obvious behavior (e.g., '// strips nav, footer, sidebars') and remove the Overview section which largely restates the YAML description.
Move the 'Examples' section (multiple formats, webhook) into a separate EXAMPLES.md file and reference it from the main skill to reduce token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good code examples, but includes some unnecessary elements like the Overview section restating the description, comments explaining obvious things (e.g., '// Scrape a single page to clean markdown'), and the Prerequisites section listing things Claude would know to check. Could be tightened by ~20%. | 2 / 3 |
Actionability | Fully executable TypeScript code throughout — scrapeUrl, crawlUrl, asyncCrawlUrl with polling, and file processing are all copy-paste ready with real API patterns. The error handling table provides specific, actionable solutions for each failure mode. | 3 / 3 |
Workflow Clarity | Clear 4-step sequence from single-page scrape → multi-page crawl → async crawl with polling → process and store results. The async crawl includes an explicit polling loop with backoff and status checking, and the error handling table serves as a validation/recovery reference. The progression from simple to complex is well-structured. | 3 / 3 |
Progressive Disclosure | The skill is somewhat long with inline examples that could be separated. The main workflow steps are well-organized, but the additional examples section (multiple formats, webhook) adds bulk that could be in a separate file. The reference to 'firecrawl-core-workflow-b' is good progressive disclosure, but the document itself could benefit from splitting advanced patterns out. | 2 / 3 |
Total | 10 / 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.