← 返回 Skills 市场
50
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install firecrawl-agent
功能描述
AI-powered autonomous data extraction that navigates complex sites and returns structured JSON. Use this skill when the user wants structured data from websi...
使用说明 (SKILL.md)
firecrawl agent
AI-powered autonomous extraction. The agent navigates sites and extracts structured data (takes 2-5 minutes).
When to use
- You need structured data from complex multi-page sites
- Manual scraping would require navigating many pages
- You want the AI to figure out where the data lives
Quick start
# Extract structured data
firecrawl agent "extract all pricing tiers" --wait -o .firecrawl/pricing.json
# With a JSON schema for structured output
firecrawl agent "extract products" --schema '{"type":"object","properties":{"name":{"type":"string"},"price":{"type":"number"}}}' --wait -o .firecrawl/products.json
# Focus on specific pages
firecrawl agent "get feature list" --urls "\x3Curl>" --wait -o .firecrawl/features.json
Options
| Option | Description |
|---|---|
--urls \x3Curls> |
Starting URLs for the agent |
--model \x3Cmodel> |
Model to use: spark-1-mini or spark-1-pro |
--schema \x3Cjson> |
JSON schema for structured output |
--schema-file \x3Cpath> |
Path to JSON schema file |
--max-credits \x3Cn> |
Credit limit for this agent run |
--wait |
Wait for agent to complete |
--pretty |
Pretty print JSON output |
-o, --output \x3Cpath> |
Output file path |
Tips
- Always use
--waitto get results inline. Without it, returns a job ID. - Use
--schemafor predictable, structured output — otherwise the agent returns freeform data. - Agent runs consume more credits than simple scrapes. Use
--max-creditsto cap spending. - For simple single-page extraction, prefer
scrape— it's faster and cheaper.
See also
- firecrawl-scrape — simpler single-page extraction
- firecrawl-interact — scrape + interact for manual page interaction (more control)
- firecrawl-crawl — bulk extraction without AI
安全使用建议
Install this if you intend to use Firecrawl for autonomous website data extraction. Use trusted target URLs, set an explicit output path in a dedicated directory, consider --max-credits to control cost, and review generated JSON before using it downstream.
能力评估
Purpose & Capability
The stated purpose is autonomous multi-page website extraction to structured JSON, and the documented Firecrawl commands, schema options, URL targeting, credit limits, and JSON output all align with that purpose.
Instruction Scope
Some trigger examples are broad if read in isolation, but the surrounding description scopes use to structured website data extraction and does not instruct unrelated or hidden actions.
Install Mechanism
The artifact contains only a SKILL.md file and no executable installer, scripts, dependency bundle, or persistence mechanism.
Credentials
Allowed tools are limited to firecrawl CLI invocations, which is proportionate for a Firecrawl extraction skill, though use implies external website access and service credit consumption.
Persistence & Privilege
The skill writes extraction results to user-specified output paths such as .firecrawl/*.json, which is expected and disclosed; no background persistence, privilege escalation, credential harvesting, or destructive behavior is present.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install firecrawl-agent - 安装完成后，直接呼叫该 Skill 的名称或使用
/firecrawl-agent触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
firecrawl-agent v1.0.0
- Initial release of firecrawl-agent skill for AI-powered structured data extraction from complex, multi-page websites.
- Supports autonomous navigation and JSON output with user-provided schemas.
- Command-line options include targeted URLs, model selection, schema input, credit limits, and output formatting.
- Recommended for extracting pricing tiers, product lists, directories, and similar structured content across websites.
元数据
常见问题
Firecrawl Agent 是什么？
AI-powered autonomous data extraction that navigates complex sites and returns structured JSON. Use this skill when the user wants structured data from websi... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 50 次。
如何安装 Firecrawl Agent？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install firecrawl-agent」即可一键安装，无需额外配置。
Firecrawl Agent 是免费的吗？
是的，Firecrawl Agent 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Firecrawl Agent 支持哪些平台？
Firecrawl Agent 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Firecrawl Agent？
由 eohmig（@eohmig）开发并维护，当前版本 v1.0.0。
推荐 Skills