← 返回 Skills 市场
ericsantos

Jina Reader

作者 Eric Santos · GitHub ↗ · v0.0.2 · MIT-0
cross-platform ✓ 安全检测通过
6711
总下载
5
收藏
71
当前安装
4
版本数
在 OpenClaw 中安装
/install jina-reader
功能描述
Web content extraction via Jina AI Reader API. Three modes: read (URL to markdown), search (web search + full content), ground (fact-checking). Extracts clea...
安全使用建议
Install only if you are comfortable sending requested URLs, search queries, CSS selectors, and fact-check text to Jina AI. Avoid secrets, private intranet links, regulated data, personal data, credentials, or confidential business material unless that third-party processing is acceptable.
能力评估
Purpose & Capability
The script's capabilities match the stated purpose: it uses Jina Reader, Search, and Grounding endpoints to fetch web content, run searches, and fact-check statements.
Instruction Scope
The documentation says the skill works via the Jina AI Reader API and documents API key use, but it does not give a prominent privacy warning that URLs, queries, selectors, and statements leave the local environment.
Install Mechanism
The artifact contains a markdown skill file and one shell script requiring curl and jq; there are no install hooks, package installs, obfuscation, or hidden setup steps.
Credentials
Network access and optional bearer-token use are proportionate for a Jina API integration, but users should treat submitted inputs as shared with a third-party service.
Persistence & Privilege
No background workers, privilege escalation, destructive actions, or broad local file access were found; the only local credential behavior is reading JINA_API_KEY or ~/.config/jina/api_key when present.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install jina-reader
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /jina-reader 触发
  4. 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
v0.0.2
API key now resolves from $JINA_API_KEY env or ~/.config/jina/api_key file (canonical local path)
v0.0.1
Initial release. - Web content extraction via Jina AI Reader API with three modes: read, search, and ground. - Supports clean content extraction to markdown, HTML, text, or screenshot. - Allows region-specific extraction, removal, and waiting with CSS selectors. - Enables web search with full content and fact-checking from the command line. - Protects server IP and supports geo-proxying. - Free tier API key with 10M tokens (no signup required).
v1.1.0
Web content extraction via Jina AI: read, search, ground modes
v1.0.0
Initial release: 3 modes (read, search, ground), CSS selectors, geo-proxy, cache control
元数据
Slug jina-reader
版本 0.0.2
许可证 MIT-0
累计安装 211
当前安装数 71
历史版本数 4
常见问题

Jina Reader 是什么?

Web content extraction via Jina AI Reader API. Three modes: read (URL to markdown), search (web search + full content), ground (fact-checking). Extracts clea... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 6711 次。

如何安装 Jina Reader?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install jina-reader」即可一键安装,无需额外配置。

Jina Reader 是免费的吗?

是的,Jina Reader 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Jina Reader 支持哪些平台?

Jina Reader 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 Jina Reader?

由 Eric Santos(@ericsantos)开发并维护,当前版本 v0.0.2。

💬 留言讨论