← 返回 Skills 市场
Anycrawl
作者
QuincyGunter
· GitHub ↗
· v1.0.0
· MIT-0
57
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install qui-anycrawl
功能描述
Provides web scraping, crawling, and Google search with multi-engine support via the SkillBoss API for structured data extraction and automation.
安全使用建议
This skill appears to implement what it claims: it proxies scraping/search tasks to https://api.heybossai.com and requires SKILLBOSS_API_KEY. However, the registry metadata fails to list that required credential — treat that as a red flag. Before installing: verify the publisher and the external API (heybossai.com) are trustworthy; confirm why the registry omitted SKILLBOSS_API_KEY; avoid using high-privilege or reusable keys (create a scoped/test key if possible); review legal/TOS implications of scraping target sites; and consider running the skill in a restricted/sandboxed environment first. If you cannot verify the publisher or the API provider, do not supply your API key.
功能分析
Type: OpenClaw Skill
Name: qui-anycrawl
Version: 1.0.0
The AnyCrawl skill is a legitimate integration for the SkillBoss API Hub (heybossai.com), providing web scraping, crawling, and search capabilities. The implementation in index.js correctly routes requests to the official API endpoint (api.heybossai.com) using the user-provided API key. While the documentation suggests persisting the API key in ~/.bashrc, this is a standard configuration practice for CLI-based tools and is presented transparently without any signs of malicious intent or data exfiltration.
能力标签
能力评估
Purpose & Capability
The name/description (web scraping, crawling, multi-engine search) match the implementation: index.js calls an external API (https://api.heybossai.com/v1/pilot) to perform scraping, crawling, and search. The skill's declared multi-engine support is plausible as the API likely proxies different engines. However, the registry metadata claims no required env vars/credentials while both SKILL.md and index.js explicitly require SKILLBOSS_API_KEY — this metadata omission is an inconsistency.
Instruction Scope
SKILL.md instructs the agent to set SKILLBOSS_API_KEY and shows functions limited to search/scrape/crawl actions. The runtime instructions and code only read the SKILLBOSS_API_KEY environment variable and call the external API; they do not instruct reading arbitrary local files, shell history, credentials, or transmitting data to other endpoints beyond the documented api.heybossai.com.
Install Mechanism
There is no install specification (instruction-only installation), which is low risk for filesystem writes. Note: a code file (index.js) is included and is what will run; no install step downloads additional binaries or archives from unknown hosts.
Credentials
The skill requires a single API credential (SKILLBOSS_API_KEY) which is proportionate to the claimed functionality. The problem: registry metadata lists no required env vars or primary credential, while both SKILL.md and index.js demand SKILLBOSS_API_KEY and the code throws if it is missing. That mismatch could be a publishing/metadata error or deliberate omission — either way you should not trust the registry metadata alone when granting credentials.
Persistence & Privilege
The skill is not marked always:true, does not request persistent platform privileges, and does not attempt to modify other skills or system-wide configuration in its code or instructions.
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 qui-anycrawl - 安装完成后，直接呼叫该 Skill 的名称或使用
/qui-anycrawl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
- Initial release of AnyCrawl skill for fast, multi-engine web scraping and site crawling via SkillBoss API Hub.
- Supports scraping, crawling, and Google search using multiple engines (cheerio, playwright, puppeteer).
- Provides functions for individual URL scraping, search + scrape, full site crawl (with progress and results APIs), and crawl job management.
- Highly configurable scraping and crawling features, including engine, content formats, selectors, proxies, and JSON extraction.
- Detailed setup documentation and usage examples included.
元数据
常见问题
Anycrawl 是什么？
Provides web scraping, crawling, and Google search with multi-engine support via the SkillBoss API for structured data extraction and automation. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 57 次。
如何安装 Anycrawl？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install qui-anycrawl」即可一键安装，无需额外配置。
Anycrawl 是免费的吗？
是的，Anycrawl 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Anycrawl 支持哪些平台？
Anycrawl 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 Anycrawl？
由 QuincyGunter（@quincygunter）开发并维护，当前版本 v1.0.0。
推荐 Skills