New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Firecrawl

by HybridAIOne in HybridAIOne/hybridclaw

Scrape pages, crawl public sites, map URLs, and run JSON-schema extraction through managed or self-hosted Firecrawl.

MITAuto-check passedData & Analytics

Install Firecrawl

skills CLI
$ npx skills add HybridAIOne/hybridclaw --skill firecrawl -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HybridAIOne/hybridclaw firecrawl --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HybridAIOne/hybridclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/firecrawl .claude/skills/firecrawl && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
firecrawl
GitHub stars
159
Token cost
~2.2k tokens
SKILL.md length
704 words
Files
3
Skills in repo
72
Repo updated
First seen
Licence
MIT

At a glance

Scrape pages, crawl public sites, map URLs, and run JSON-schema extraction through managed or self-hosted Firecrawl.

  • Works in 3 steps: Browser admin: open the active… → Browser /chat or TUI fallback → Local console fallback
  • Tasks that involve Web scraping
  • SKILL.md covers Credential Rules, Operations, Command Contract and Policy Defaults, plus 1 more section
  • Runs JavaScript scripts from its folder; calls node; reaches api.firecrawl.dev; needs FIRECRAWL_API_KEY and FIRECRAWL_SELF_HOST_API_KEY

What it does

Firecrawl is an agent skill from HybridAIOne/hybridclaw. Scrape pages, crawl public sites, map URLs, and run JSON-schema extraction through managed or self-hosted Firecrawl.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files.

It sits in Data & Analytics, covering Web scraping. It works with Firecrawl. The repository describes itself as: Enterprise-ready self-hosted AI assistant runtime with sandboxed execution, secure credentials, approvals, and memory. The licence is MIT.

When your agent uses it

  • Tasks that involve Web scraping

Example prompts

  • “/firecrawl”

Requirements

  • A credential in FIRECRAWL_API_KEY
  • A credential in FIRECRAWL_SELF_HOST_API_KEY

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Browser admin: open the active HybridClaw admin URL ending in /admin/secrets and set
  2. Browser /chat or TUI fallback
  3. Local console fallback

What it can do on your machine

Read from SKILL.md and the folder at commit 8162701. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.firecrawl.dev

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • FIRECRAWL_API_KEY
    • FIRECRAWL_SELF_HOST_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Firecrawl loads about 2.2k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 704 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HybridAIOne/hybridclaw at commit 8162701, republished under its MIT licence (© HybridAIOne). 704 words, ~2,173 tokens.

Download SKILL.mdSave it as .claude/skills/firecrawl/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
firecrawl
description
Scrape pages, crawl public sites, map URLs, and run JSON-schema extraction through managed or self-hosted Firecrawl.
user-invocable
true
requires.bins
node

Firecrawl

Use this skill for unauthenticated public web ingestion when HTTP fetch and server-side parsing are enough. Firecrawl is the cheap path for public pages and docs. Use the browser skill instead when the task needs login, interaction, form filling, visual inspection, or client-side state. Do not use Firecrawl to bypass access controls.

Credential Rules

For managed mode, set or update the Firecrawl API key in this order:

  1. Browser admin: open the active HybridClaw admin URL ending in /admin/secrets and set FIRECRAWL_API_KEY.
  2. Browser /chat or TUI fallback: /secret set FIRECRAWL_API_KEY "<fc-api-key>".
  3. Local console fallback:
bash
hybridclaw secret set FIRECRAWL_API_KEY "<fc-api-key>"

For a self-hosted Firecrawl instance, set the gateway-reachable base URL in the runtime environment or pass it explicitly to the helper:

bash
export FIRECRAWL_SELF_HOST_BASE_URL="http://firecrawl:3002"

The helper accepts base URLs with or without /v2 and normalizes them to the v2 API path. If your self-hosted Firecrawl deployment enables API authentication, set that token separately in the same order:

  1. Browser admin: open the active HybridClaw admin URL ending in /admin/secrets and set FIRECRAWL_SELF_HOST_API_KEY.
  2. Browser /chat or TUI fallback: /secret set FIRECRAWL_SELF_HOST_API_KEY "<self-host-api-key>".
  3. Local console fallback:
bash
hybridclaw secret set FIRECRAWL_SELF_HOST_API_KEY "<self-host-api-key>"

Use HTTPS for any self-host endpoint outside a trusted private network, especially when --self-host-auth is enabled; plain HTTP can expose bearer tokens on untrusted networks.

For live calls, run the colocated helper to build an http_request payload and pass only the emitted httpRequest object to the built-in http_request tool. The helper sets bearerSecretName: "FIRECRAWL_API_KEY" so the gateway injects the managed token server-side. In self-host mode, pass --self-host-auth only when the deployment requires a bearer token; the helper then uses FIRECRAWL_SELF_HOST_API_KEY. Do not use bash/curl for live Firecrawl calls when http_request is available, and never ask the user to paste API keys into chat.

Operations

  • scrape.url: scrape one public URL. Default output is markdown.
  • crawl.site: start a public site crawl with conservative default limit 25.
  • crawl.status: fetch crawl progress and paginated crawl results by job id.
  • crawl.cancel: cancel a crawl job by id.
  • crawl.active: list active crawls for the authenticated Firecrawl team.
  • map.site: return a URL map with conservative default limit 500.
  • extract.structured: start a structured extraction job through POST /v2/extract.
  • extract.status: fetch extraction status and results by job id.

Both adapters target Firecrawl API v2. The managed adapter sends requests to https://api.firecrawl.dev/v2; the self-host adapter sends the same operations to the configured self-host base URL. Firecrawl self-host deployments may not enable every upstream managed feature; /agent and /browser are intentionally outside this skill surface.

For single-page JSON extraction during scraping, scrape.url can include --schema-json; for the R53.1/R53.2 extract endpoint, use extract.structured and then poll extract.status.

Show full SKILL.md (279 more words)Show less

Command Contract

Run the helper with Node:

bash
node skills/firecrawl/firecrawl.cjs --help

Build a managed single-page scrape request:

bash
node skills/firecrawl/firecrawl.cjs --format json http-request scrape.url \
  --url https://example.com/docs \
  --format-name markdown

Build the same request for self-hosted Firecrawl:

bash
node skills/firecrawl/firecrawl.cjs --format json --adapter self-host \
  --base-url http://firecrawl:3002 \
  http-request scrape.url \
  --url https://example.com/docs \
  --format-name markdown

Add --self-host-auth only if the self-hosted deployment requires FIRECRAWL_SELF_HOST_API_KEY.

Build a site crawl request:

bash
node skills/firecrawl/firecrawl.cjs --format json http-request crawl.site \
  --url https://example.com/docs \
  --limit 25 \
  --include-path 'docs/.*'

Check or cancel a crawl:

bash
node skills/firecrawl/firecrawl.cjs --format json http-request crawl.status \
  --id 00000000-0000-0000-0000-000000000000

node skills/firecrawl/firecrawl.cjs --format json http-request crawl.cancel \
  --id 00000000-0000-0000-0000-000000000000

Build a URL map request:

bash
node skills/firecrawl/firecrawl.cjs --format json http-request map.site \
  --url https://example.com \
  --limit 500 \
  --sitemap include

Build a structured extraction request:

bash
node skills/firecrawl/firecrawl.cjs --format json http-request extract.structured \
  --url 'https://example.com/pricing/*' \
  --schema-json '{"type":"object","properties":{"plans":{"type":"array"}}}' \
  --prompt "Extract plan names and prices."

Check an extraction job:

bash
node skills/firecrawl/firecrawl.cjs --format json http-request extract.status \
  --id 00000000-0000-0000-0000-000000000000

The helper prints a wrapper such as { "command": "http-request", "httpRequest": { ... } }. Pass only the httpRequest value to the built-in http_request tool.

Policy Defaults

  • Target URLs must be http or https and must not embed credentials.
  • Managed mode rejects custom API base URLs.
  • Self-host mode requires --base-url or FIRECRAWL_SELF_HOST_BASE_URL; API base URLs must be http or https and must not embed credentials.
  • crawl.site always emits ignoreRobotsTxt: false.
  • The helper rejects --ignore-robots-txt.
  • Crawl and map limits are explicit and bounded to reduce surprise cost.
  • Use --zero-data-retention only when the Firecrawl team has enabled it for the configured account or self-hosted deployment.

Error Interpretation

  • Gateway errors saying FIRECRAWL_API_KEY is not set, unavailable, missing, or unresolved mean the active HybridClaw runtime cannot resolve the stored secret. Ask the operator to set it in the same runtime/session.
  • Gateway errors saying FIRECRAWL_API_KEY is blocked by policy mean the secret exists but policy/runtime access blocked injection. Do not ask the operator to set the same secret again.
  • Firecrawl 401 or 403 responses mean the gateway injected a token but Firecrawl rejected it or the account cannot use the requested feature.
  • Firecrawl 402, 408, 429, or 5xx responses are upstream billing, timeout, rate limit, or service failures. Report the upstream response and retry only when the user asks.
  • Self-host errors saying FIRECRAWL_SELF_HOST_BASE_URL is missing mean the operator needs to configure the gateway-reachable Firecrawl API origin.

© HybridAIOne, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in skills/firecrawl of HybridAIOne/hybridclaw.

  • SKILL.md
  • firecrawl.cjs
  • index.cjs

Open the folder on GitHubat commit 8162701

Compare with similar skills

Firecrawl next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Firecrawl compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Firecrawl this skillHybridAIOne/hybridclaw159—~2.2kAutomated safety check: PassMIT
Firecrawl Scrapefirecrawl/skills117—~1.8kAutomated safety check: PassISC
Firecrawl Agentfirecrawl/skills117—~1.2kAutomated safety check: PassISC
Firecrawl Company Directoriesfirecrawl/skills117—~557Automated safety check: PassISC
Firecrawl Competitive Intelfirecrawl/skills117—~604Automated safety check: PassISC
Firecrawlzapier/connectors177—~4.2kAutomated safety check: PassElastic-2.0

Similar skills

  • Firecrawl Scrape

    firecrawl/skills

    Read a known webpage or execute a discovered workflow or data-provider capability.

    117 GitHub stars~1.8k tokensUpdated yesterday
    Data & AnalyticsAuto-check passed

  • Firecrawl Agent

    firecrawl/skills

    Autonomously navigate websites and extract structured data across pages.

    117 GitHub stars~1.2k tokensUpdated yesterday
    Data & AnalyticsAuto-check passed

  • Firecrawl Company Directories

    firecrawl/skills

    Extract structured company lists from directories with Firecrawl.

    117 GitHub stars~557 tokensUpdated yesterday
    Data & AnalyticsAuto-check passed

  • Firecrawl Competitive Intel

    firecrawl/skills

    Monitor competitor pricing, features, changelogs, dashboards, and product changes with Firecrawl.

    117 GitHub stars~604 tokensUpdated yesterday
    Data & AnalyticsAuto-check passed

  • Firecrawl

    zapier/connectors

    Official

    Agent-callable Firecrawl tools — scrape a URL to clean Markdown, crawl a site, search the web, map site URLs, and extract structured data.

    177 GitHub stars~4.2k tokensUpdated 1 mo ago
    Data & AnalyticsAuto-check passed

  • SEO Firecrawl

    seranking/seo-skills

    Ad-hoc web scraping, site mapping, and full-site crawling via Firecrawl MCP.

    161 GitHub stars~2.3k tokensUpdated 3 mo ago
    Data & AnalyticsAuto-check passed

More from HybridAIOne/hybridclaw

All 72 skills in this repo

  • Hermes3000 Writing

    HybridAIOne/hybridclaw

    Use Hermes3000 to plan, draft, revise, save, check consistency, and export long-form manuscripts through the Hermes3000 AI writing portal API.

    159 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

  • Manim Video

    HybridAIOne/hybridclaw

    Plan, script, render, and stitch Manim Community Edition videos in Python.

    159 GitHub stars~4.7k tokensUpdated today
    Auto-check: notes

  • Skill Creator

    HybridAIOne/hybridclaw

    Create and update SKILL.md-based skills with strong trigger metadata, lean docs, and reliable init, validate, package, and publish workflows.

    159 GitHub stars~2k tokensUpdated today
    Auto-check passed

  • XLSX

    HybridAIOne/hybridclaw

    Create, edit, inspect, and analyze .xlsx spreadsheets and Excel workbooks.

    159 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Excalidraw

    HybridAIOne/hybridclaw

    Create and revise editable .excalidraw diagrams as Excalidraw JSON for architecture diagrams, flowcharts, sequence diagrams, concept maps, and other hand-drawn explainers.

    159 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Google Ads

    HybridAIOne/hybridclaw

    Manage Google Ads accounts with safe GAQL reporting, campaign planning, guarded mutations, and gateway-proxied REST API calls.

    159 GitHub stars~4k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Firecrawl

What does Firecrawl do?

Scrape pages, crawl public sites, map URLs, and run JSON-schema extraction through managed or self-hosted Firecrawl. Firecrawl is an agent skill from HybridAIOne/hybridclaw. Scrape pages, crawl public sites, map URLs, and run JSON-schema extraction through managed or self-hosted Firecrawl.

When should I use Firecrawl?

Firecrawl fits situations like: tasks that involve Web scraping.

How do I install Firecrawl in Claude Code?

Run `npx skills add HybridAIOne/hybridclaw --skill firecrawl -a claude-code`. Or copy the skill folder (skills/firecrawl in HybridAIOne/hybridclaw) into .claude/skills/firecrawl in your project. Claude Code loads it when a task matches its description.

How do I install Firecrawl in Codex?

Run `npx skills add HybridAIOne/hybridclaw --skill firecrawl -a codex`. Or copy the skill folder (skills/firecrawl in HybridAIOne/hybridclaw) into .agents/skills/firecrawl in your project. Codex loads it when a task matches its description.

Can I use Firecrawl in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HybridAIOne/hybridclaw --skill firecrawl -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/firecrawl, .gemini/skills/firecrawl, .github/skills/firecrawl and .opencode/skills/firecrawl in your project.

What does Firecrawl need to run?

Going by SKILL.md and its folder, Firecrawl needs JavaScript for the scripts in its folder, the command-line tools its instructions call (node) and credentials named FIRECRAWL_API_KEY and FIRECRAWL_SELF_HOST_API_KEY. Our summary lists: A credential in FIRECRAWL_API_KEY; A credential in FIRECRAWL_SELF_HOST_API_KEY.

Does Firecrawl access the network?

SKILL.md names 1 domain. In commands or code: api.firecrawl.dev; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Firecrawl safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Firecrawl use?

Firecrawl is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Firecrawl use?

About 2.2k tokens (SKILL.md is roughly 8.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Firecrawl?

Skills that share tags, products or a category with Firecrawl: Firecrawl Scrape (firecrawl/skills, 117 stars), Firecrawl Agent (firecrawl/skills, 117 stars), Firecrawl Company Directories (firecrawl/skills, 117 stars) and Firecrawl Competitive Intel (firecrawl/skills, 117 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Firecrawl?

HybridAIOne (a GitHub organization) maintains it in HybridAIOne/hybridclaw, which has 159 GitHub stars. The repository holds 72 skills in this directory. The repository was last updated on October 9, 2026.

Source: HybridAIOne/hybridclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.