← 返回 Skills 市场
208
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install tra-extract-text
功能描述
Extract readable text, markdown, HTML, JSON, or XML content from web pages using the trafilatura CLI tool with optional metadata and output formatting.
安全使用建议
This skill is coherent and simply documents how to install and use the trafilatura CLI. Before installing, consider: (1) 'pip install trafilatura' will fetch code from PyPI—verify the package's reputation and optionally pin a specific version; (2) there is no homepage/source repo listed in the skill metadata—if you care about provenance, check PyPI and the project's source to confirm authenticity; (3) run the tool in a sandboxed environment if you are concerned about executing third-party code; (4) be cautious when extracting content from internal or sensitive URLs (this can expose internal data to the agent environment); and (5) ensure you respect site terms/robots and copyright when scraping. If you want stricter controls, add an explicit install spec (trusted package source and pinned version) or pre-install trafilatura in a controlled environment rather than letting the agent run pip at runtime.
功能分析
Type: OpenClaw Skill
Name: tra-extract-text
Version: 1.0.0
The skill bundle provides standard instructions and examples for using the legitimate 'trafilatura' Python library and CLI tool to extract text from web pages. The SKILL.md file contains typical usage patterns (markdown, text, and metadata extraction) and lacks any indicators of malicious intent, data exfiltration, or prompt injection.
能力评估
Purpose & Capability
Name/description (extract web page text/markdown/HTML/JSON/XML) match the SKILL.md which documents using the trafilatura CLI and its options. There are no unrelated credentials, binaries, or config paths requested.
Instruction Scope
Runtime instructions are narrowly scoped to installing trafilatura and running the trafilatura CLI against user-provided URLs; they do not ask the agent to read unrelated files, environment variables, or to transmit results to any unexpected external endpoint.
Install Mechanism
There is no formal install spec, but SKILL.md instructs running 'pip install trafilatura' (PyPI). This is expected for a Python CLI tool but means the agent or user will download code from PyPI at install time — a moderate, expected risk. The skill does not pin a version or point to an authoritative homepage/source repo.
Credentials
The skill requests no environment variables, secrets, or config paths. That is proportionate to its stated purpose.
Persistence & Privilege
The skill is instruction-only, not always-enabled, and does not request system-wide changes or persistent privileges. Autonomous invocation is permitted (platform default) but not combined with other concerning privileges.
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 tra-extract-text - 安装完成后，直接呼叫该 Skill 的名称或使用
/tra-extract-text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 tra-extract-text.
- Extracts readable text, markdown, or raw HTML from web pages using the trafilatura CLI tool.
- Supports output in multiple formats: Markdown, plain text, HTML, JSON, and XML.
- Includes options for adding metadata (title, author, date) to extracted content.
- Simple command-line interface for extracting, formatting, and saving web content.
元数据
常见问题
tra-extract-text 是什么？
Extract readable text, markdown, HTML, JSON, or XML content from web pages using the trafilatura CLI tool with optional metadata and output formatting. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 208 次。
如何安装 tra-extract-text？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install tra-extract-text」即可一键安装，无需额外配置。
tra-extract-text 是免费的吗？
是的，tra-extract-text 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
tra-extract-text 支持哪些平台？
tra-extract-text 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 tra-extract-text？
由 Jay（@goog）开发并维护，当前版本 v1.0.0。
推荐 Skills