Skip to main content
firecrawl-data-handling Process, validate, and store Firecrawl scraped content with deduplication and chunking.
Use when handling scraped markdown, implementing content pipelines, building RAG knowledge
bases, or processing crawl results for downstream consumption.
Trigger with phrases like "firecrawl data", "firecrawl content processing",
"firecrawl markdown cleaning", "firecrawl storage", "firecrawl RAG pipeline".
跳到安装 Skills Marketplace 发现并探索由社区构建的 Agent Skills
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/jeremylongshore/claude-code-plugins-plus-skills --skill firecrawl-data-handling命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
下载 Zip 下载中... 同仓库更多 Skills Implement user sign-up and sign-in flows with Clerk.
Use when building authentication UI, customizing sign-in experience,
or implementing OAuth social login.
Trigger with phrases like "clerk sign-in", "clerk sign-up",
"clerk login flow", "clerk OAuth", "clerk social login".
Implement session management and middleware with Clerk.
Use when managing user sessions, configuring route protection,
or implementing token refresh and custom JWT templates.
Trigger with phrases like "clerk session", "clerk middleware",
"clerk route protection", "clerk token", "clerk JWT".
Configure enterprise SSO, role-based access control, and organization management.
Use when implementing SSO integration, configuring role-based permissions,
or setting up organization-level controls.
Trigger with phrases like "clerk SSO", "clerk RBAC",
"clerk enterprise", "clerk roles", "clerk permissions", "clerk organizations".
jeremylongshore
jeremylongshore/claude-code-plugins-plus-skills
打开 GitHub 仓库 name firecrawl-data-handling description Process, validate, and store Firecrawl scraped content with deduplication and chunking.
Use when handling scraped markdown, implementing content pipelines, building RAG knowledge
bases, or processing crawl results for downstream consumption.
Trigger with phrases like "firecrawl data", "firecrawl content processing",
"firecrawl markdown cleaning", "firecrawl storage", "firecrawl RAG pipeline".
allowed-tools Read, Write, Edit version 1.11.0 license MIT author Jeremy Longshore <jeremy@intentsolutions.io> tags ["saas","firecrawl","compliance"] compatibility Designed for Claude Code, also compatible with Codex and OpenClaw
Firecrawl Data Handling
Overview
Process scraped web content from Firecrawl pipelines. Covers markdown cleaning, structured data extraction with Zod validation, content deduplication, chunking for LLM/RAG, and storage patterns for crawled content.
Instructions
Step 1: Content Cleaning
import FirecrawlApp from "@mendable/firecrawl-js" ;
const firecrawl = new FirecrawlApp ({
apiKey : process.env .FIRECRAWL_API_KEY !,
});
async function scrapeClean (url : string const result = await firecrawl.scrapeUrl (url, {
formats : ["markdown" ],
onlyMainContent : true ,
excludeTags : ["script" , "style" , "nav" , "footer" , "iframe" ],
waitFor : 2000 ,
});
return {
url : result.metadata ?.sourceURL || url,
title : result.metadata ?.title || "" ,
markdown : cleanMarkdown (result.markdown || "" ),
scrapedAt : new
Date
toISOString
function
cleanMarkdown
md : string
string
return
replace
/\n{3,}/g
"\n\n"
replace
/\[.*?\]\(javascript:.*?\)/g
""
replace
/!\[.*?\]\(data:.*?\)/g
""
replace
/<!--[\s\S]*?-->/g
""
replace
/<script[\s\S]*?<\/script>/gi
""
trim
Step 2: Structured Extraction with Validation import { z } from "zod" ;
const ArticleSchema = z.object ({
title : z.string ().min (1 ),
author : z.string ().optional (),
publishedDate : z.string ().optional (),
content : z.string ().min (50 ),
wordCount : z.number (),
});
async function extractArticle (url : string const result = await firecrawl.scrapeUrl (url, {
formats : ["extract" ],
extract : {
schema : {
type : "object" ,
properties : {
title : { type : "string" },
author : { type : "string" },
publishedDate : { type : "string" },
content : { type : "string" },
},
required : ["title" , "content" ],
},
},
});
if (!result.extract ) throw new Error (`Extraction failed for ${url} ` );
return ArticleSchema .parse ({
...result.extract ,
wordCount : (result.extract .content || "" ).split (/\s+/ ).length ,
});
}
Step 3: Content Deduplication import { createHash } from "crypto" ;
function contentHash (text : string string {
return createHash ("sha256" )
.update (text.trim ().toLowerCase ())
.digest ("hex" );
}
function deduplicatePages (pages : Array <{ url: string ; markdown: string }>const seen = new Map <string , string >();
const unique : typeof pages = [];
const duplicates : Array <{ url : string ; duplicateOf : string }> = [];
for (const page of pages) {
const hash = contentHash (page.markdown );
if (seen.has (hash)) {
duplicates.push ({ url : page.url , duplicateOf : seen.get (hash)! });
} else {
seen.set (hash, page.url );
unique.push (page);
}
}
console .log (`Dedup: ${pages.length} input, ${unique.length} unique, ${duplicates.length} duplicates` );
return { unique, duplicates };
}
Step 4: Chunk for LLM / RAG interface ContentChunk {
url : string ;
title : string ;
chunkIndex : number ;
content : string ;
wordCount : number ;
}
function chunkForRAG (
url : string ,
title : string ,
markdown : string ,
maxWords = 800
): ContentChunk [] {
const sections = markdown.split (/\n(?=#{1,3}\s)/ );
const chunks : ContentChunk [] = [];
let current = "" ;
let index = 0 ;
for (const section of sections) {
const combined = current ? `${current} \n\n${section} ` : section;
if (combined.split (/\s+/ ).length > maxWords && current) {
chunks.push ({
url, title, chunkIndex : index++,
content : current.trim (),
wordCount : current.split (/\s+/ ).length ,
});
current = section;
} else {
current = combined;
}
}
if (current.trim ()) {
chunks.push ({
url, title, chunkIndex : index,
content : current.trim (),
wordCount : current.split (/\s+/ ).length ,
});
}
return chunks;
}
Step 5: Crawl and Store Pipeline import { writeFileSync, mkdirSync } from "fs" ;
import { join } from "path" ;
async function crawlAndStore (baseUrl : string , outputDir : string , opts ?: {
maxPages?: number ;
paths?: string [];
}mkdirSync (outputDir, { recursive : true });
const crawlResult = await firecrawl.crawlUrl (baseUrl, {
limit : opts?.maxPages || 50 ,
includePaths : opts?.paths ,
scrapeOptions : { formats : ["markdown" ], onlyMainContent : true },
});
const pages = (crawlResult.data || []).map (page =>url : page.metadata ?.sourceURL || baseUrl,
markdown : cleanMarkdown (page.markdown || "" ),
}));
const { unique } = deduplicatePages (pages);
const manifest = unique.map (page =>const slug = new URL (page.url ).pathname
.replace (/\//g , "_" ).replace (/^_|_$/g , "" ) || "index" ;
const filename = `${slug} .md` ;
writeFileSync (join (outputDir, filename), page.markdown );
return { url : page.url , file : filename, size : page.markdown .length };
});
writeFileSync (join (outputDir, "manifest.json" ), JSON .stringify (manifest, null , 2 ));
return manifest;
}
Error Handling Issue Cause Solution Empty content JS not rendered Increase waitFor, use onlyMainContent Garbage in markdown Bad HTML cleanup Add excludeTags for problematic elements Duplicate pages URL aliases or redirects Content-hash deduplication Oversized chunks Long single sections Add word limit to chunking logic Extract returns null Page too complex for LLM Simplify schema, use shorter prompt
Examples
Documentation Scraper with RAG Output const docs = await crawlAndStore ("https://docs.example.com" , "./scraped-docs" , {
maxPages : 50 ,
paths : ["/docs/*" , "/api/*" ],
});
for (const doc of docs) {
const content = readFileSync (`./scraped-docs/${doc.file} ` , "utf-8" );
const chunks = chunkForRAG (doc.url , doc.file , content);
console .log (`${doc.url} : ${chunks.length} chunks` );
}
Resources
Next Steps For access control, see firecrawl-enterprise-rbac.
