← 返回 Skills 市场
yuyonghao-123

Summarize

作者 yuyonghao-123 · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ✓ 安全检测通过
863
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install yuyonghao-summarize
功能描述
Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).
安全使用建议
This skill is a wrapper around an external CLI that will send content to whatever model provider you configure. Before installing: 1) verify you trust the Homebrew tap (steipete/tap) or inspect the brew formula to ensure it installs the expected binary; 2) prefer storing API keys in environment variables rather than plaintext config files; 3) understand that any data you summarize will be transmitted to external model providers (OpenAI, Anthropic, xAI, Google) or third‑party services (Apify/Firecrawl) if enabled; and 4) test the CLI in a controlled environment if you need to confirm its behavior and network endpoints.
功能分析
Type: OpenClaw Skill Name: yuyonghao-summarize Version: 0.1.0 The skill is a standard wrapper for the 'summarize' CLI tool, facilitating the summarization of URLs, PDFs, and YouTube videos. It installs dependencies via a reputable Homebrew tap (steipete/tap/summarize) and utilizes standard environment variables for LLM API keys. No evidence of malicious intent, data exfiltration, or prompt injection was found in SKILL.md or the configuration files.
能力评估
Purpose & Capability
Name/description match the declared runtime requirement (the 'summarize' binary). The brew install (steipete/tap/summarize) and CLI examples correspond to summarizing URLs, files, and YouTube links; there are no unrelated credentials or unusual binaries requested.
Instruction Scope
SKILL.md correctly instructs the agent to invoke the summarize CLI and documents optional configuration (~/.summarize/config.json) and provider API keys. Be aware that using the CLI will send content to the chosen model provider (OpenAI, Anthropic, xAI, Google) and optionally to services like Apify or Firecrawl when those tokens are set; that network transmission is expected for this skill but is important privacy context for users.
Install Mechanism
Install uses Homebrew (steipete/tap/summarize). Homebrew is a common installer, but this uses a third‑party tap rather than an official core formula, which is reasonable for many CLIs but slightly higher trust/verification burden than an official package.
Credentials
The skill does not require any environment variables by default. SKILL.md documents optional provider API keys (OPENAI_API_KEY, ANTHROPIC_API_KEY, XAI_API_KEY, GEMINI_API_KEY, APIFY_API_TOKEN, FIRECRAWL_API_KEY) that are clearly related to the documented features and are optional.
Persistence & Privilege
The skill does not request permanent presence (always:false) and has no instructions to modify other skills or global agent settings. The only file path mentioned is an optional per-user config (~/.summarize/config.json).
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 yuyonghao-summarize
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /yuyonghao-summarize 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 Summarize skill. - Supports summarizing web URLs, PDFs, images, audio files, and YouTube links via the CLI. - Allows choosing models from OpenAI, Anthropic, xAI, or Google Gemini; defaults to Gemini 3 Flash Preview. - Includes flexible output controls (summary length, token limits, JSON output). - Provides fallback extraction via Firecrawl and YouTube extraction with Apify. - Configurable using API keys and optional config file.
元数据
Slug yuyonghao-summarize
版本 0.1.0
许可证 MIT-0
累计安装 3
当前安装数 2
历史版本数 1
常见问题

Summarize 是什么?

Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube). 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 863 次。

如何安装 Summarize?

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

Summarize 是免费的吗?

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

Summarize 支持哪些平台?

Summarize 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 Summarize?

由 yuyonghao-123(@yuyonghao-123)开发并维护,当前版本 v0.1.0。

💬 留言讨论