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".

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%Weight 40%Scale 1-5

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

A high-quality, executable skill body with clear multi-step workflows, polling feedback loops, and a practical error-handling table. The main improvement is adding validation around the destructive file-write step and optionally splitting detailed examples into reference files.

Suggestions

Add a validation checkpoint in Step 4 before writeFileSync (e.g. confirm outputDir, guard against overwriting existing files, verify write success) to close the destructive/batch-operation validation gap.

Consider moving the multi-format and webhook Examples plus the Error Handling table into a reference file linked from SKILL.md to improve progressive disclosure for this 170-line skill.

Trim illustrative console.log lines in the code blocks to reduce token load without losing the executable guidance.

Dimension	Reasoning	Score
Conciseness	Code-forward and lean with purposeful inline comments; assumes Claude's competence without explaining Firecrawl or JS basics. A few console.log demos and the error table could be trimmed slightly, so it sits just below the leanest anchor.	4 / 5
Actionability	Provides fully executable, copy-paste TypeScript covering single-page scrape, sync crawl, async crawl with polling, result processing/storage, multi-format scrape, and webhook flow — matching the top anchor for concrete coverage of common cases.	5 / 5
Workflow Clarity	Step 1–4 sequencing is explicit with checkpoints (result.success, status polling loop with backoff, completed/failed branch) and a recovery error table; the destructive batch writeFileSync in Step 4 lacks pre-overwrite or post-write verification, a minor validation gap that keeps it below 5.	4 / 5
Progressive Disclosure	Well-organized single-file structure with clear section headers and one-level external doc links plus a Next Steps pointer; no nested references. With no bundle files and content over 50 lines, the inline error/examples blocks could be split out, so it does not reach the top anchor.	4 / 5
	Total	17 / 20 Passed

Description

87%Weight 40%Scale 1-5

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 clearly states capability and trigger conditions with concrete method names and natural trigger phrases. Minor gains are possible by adding async/webhook variants and a few more synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ("scrape and crawl websites into LLM-ready markdown", scrapeUrl, crawlUrl, "building content ingestion pipelines"); async crawl and webhook flows are not surfaced, leaving minor coverage gaps rather than full comprehensiveness.	4 / 5
Completeness	Explicitly answers both what ("scrape and crawl websites into LLM-ready markdown") and when ("Use when scraping single pages, crawling entire sites, or building content ingestion pipelines") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Lists natural phrases a user would say ("firecrawl scrape", "firecrawl crawl site", "scrape page to markdown", "crawl documentation") with good coverage, though common synonyms like "extract web content" or "scrape to text" are absent.	4 / 5
Distinctiveness Conflict Risk	"Firecrawl" plus its named methods carve a clear niche with distinct "firecrawl ..." triggers, minimizing overlap with general scraping or unrelated skills.	5 / 5
	Total	18 / 20 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
Path: plugins/saas-packs/firecrawl-pack/skills/firecrawl-core-workflow-a/SKILL.md
Commit: 8585d6d

Reviewed: 14 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.