← 返回 Skills 市场
anycrawl
作者
TobeyRebecca
· GitHub ↗
· v1.0.2
· MIT-0
115
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install toby-anycrawl
功能描述
Perform web scraping, crawling, and Google search with multi-engine support and structured data extraction via SkillBoss API Hub.
安全使用建议
This skill implements web scraping by forwarding requests and scraped content to api.skillboss.co and requires a SKILLBOSS_API_KEY environment variable (index.js will throw if it's missing). The registry metadata failing to declare that required env var is an inconsistency you should resolve before trusting the skill. Before installing: (1) confirm you trust SkillBoss (privacy, retention, and TOS) because scraped pages and search queries will be transmitted off your system; (2) avoid using it with private/internal URLs or credentials unless you accept that data leaving your environment is allowed; (3) set the API key using a secure method (not pasted into public shells) and consider scoping/rotating the key; (4) verify the skill's source/repository and publisher identity (registry lists an owner ID but homepage is missing); and (5) if you need to restrict network egress or keep data local, do not install this skill. The primary technical fix needed is to update the registry metadata to declare SKILLBOSS_API_KEY so installers understand the requirement.
能力标签
能力评估
Purpose & Capability
Name/description (web scraping, crawling, search) align with the included code (index.js) and SKILL.md which call the SkillBoss API. The functions implemented (scrape, search, crawl, job status/results, cancel, search+scrape) match the described capability.
Instruction Scope
SKILL.md and index.js only instruct the agent to call https://api.skillboss.co/v1/pilot with user-provided parameters and to set SKILLBOSS_API_KEY; they do not request unrelated local files or other credentials. However, the skill sends scraped page content and search inputs to an external endpoint (SkillBoss) — expected for the purpose but a clear privacy/data-exfiltration vector that users must consider.
Install Mechanism
There is no install spec that downloads arbitrary code — this is an instruction + code bundle. package.json lists no external dependencies. No risky download URLs or extract operations are present.
Credentials
SKILL.md and index.js require SKILLBOSS_API_KEY (the code throws if it's absent), but the registry metadata lists no required env vars — a clear inconsistency. Requesting a single API key is proportionate for this skill, but it is undeclared in the registry and the key grants an external service ability to receive scraped content, which has privacy implications.
Persistence & Privilege
always:false (no forced inclusion), no config paths or requests to modify other skills, and normal model invocation behavior. No elevated persistence or cross-skill config changes are requested.
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 toby-anycrawl - 安装完成后，直接呼叫该 Skill 的名称或使用
/toby-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
v1.0.2
Version 1.0.2
- No changes detected in the files for this release.
- Functionality and documentation remain unchanged.
v1.0.1
- Updated URLs from heybossai.com to skillboss.co in documentation and setup instructions.
- No changes to the API, functionality, or usage.
- Ensures documentation links point to the current service domain.
v1.0.0
Initial release
元数据
常见问题
anycrawl 是什么？
Perform web scraping, crawling, and Google search with multi-engine support and structured data extraction via SkillBoss API Hub. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 115 次。
如何安装 anycrawl？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install toby-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 TobeyRebecca（@tobeyrebecca）开发并维护，当前版本 v1.0.2。
推荐 Skills