← 返回 Skills 市场
codekungfu

Yiyan

作者 ClawKK · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ✓ 安全检测通过
194
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install yiyan
功能描述
提供百度文心一言公开页面的模型能力、定价和文档信息检索与摘要服务。
安全使用建议
This skill appears coherent and low-risk, but before installing confirm: (1) your agent environment is allowed to access the public web and can render JavaScript-driven pages (headless browser or equivalent), since the instructions expect dynamic rendering; (2) the agent will respect rate limits and not access private/account-only pages; and (3) scraped outputs will not be forwarded to external endpoints you don't control. If you need explicit guarantees about rendering or data retention, ask the skill author for implementation details (which headless browser/tool will be used, where extracted data is stored or transmitted).
功能分析
Type: OpenClaw Skill Name: yiyan Version: 0.1.0 The skill bundle (yiyan-hot-trend) contains instructions for an AI agent to retrieve and summarize public information from Baidu's Wenxin Yiyan and Qianfan platforms. The SKILL.md file explicitly restricts the agent from performing account-related operations, API calls, or permission bypasses, focusing solely on public documentation, pricing, and model features. No malicious code, data exfiltration, or suspicious behaviors were detected.
能力评估
Purpose & Capability
Name/description match the SKILL.md: the skill is explicitly about retrieving and summarizing public product/docs/pricing pages for Baidu Yiyan. It declares no unrelated environment variables, binaries, or installs.
Instruction Scope
Instructions stay within the stated purpose (visit public pages, extract model/pricing/docs info, respect rate limits, avoid account/API/permissions). One operational gap: the doc notes pages are dynamically loaded and need waiting/rendering, but it does not specify how to render JavaScript (headless browser, puppeteer, etc.). That is an implementation detail but could affect whether the agent can actually perform the task.
Install Mechanism
No install specification and no code files — lowest-risk instruction-only skill. Nothing in the metadata pulls external binaries or archives.
Credentials
No required env vars, credentials, or config paths are requested. This is proportionate to a public-web-scraping/summarization task.
Persistence & Privilege
always is false and the skill does not request persistent or elevated privileges. Autonomous invocation is allowed by default but not combined with other risky permissions here.
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 yiyan
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /yiyan 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
v0.1.0
Initial release of the "yiyan-hot-trend" skill for Baidu Wenxin Yiyan public information summarization. - Supports retrieval and summarization of information from Baidu Wenxin Yiyan product and documentation pages. - Extracts key data such as model capabilities, pricing, quotas, and documentation links from publicly available sources. - Focuses on lightweight, public content organization only—does not perform account operations or API calls. - Handles dynamic page loading and respects platform access limits. - Includes clearly defined data fields and sample usage flows for typical summarization tasks.
元数据
Slug yiyan
版本 0.1.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Yiyan 是什么?

提供百度文心一言公开页面的模型能力、定价和文档信息检索与摘要服务。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 194 次。

如何安装 Yiyan?

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

Yiyan 是免费的吗?

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

Yiyan 支持哪些平台?

Yiyan 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 Yiyan?

由 ClawKK(@codekungfu)开发并维护,当前版本 v0.1.0。

💬 留言讨论