← 返回 Skills 市场

anytocopy-extractor

Name: anytocopy-extractor
Author: darker314159

作者 balckbeeai · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

103

总下载

当前安装

版本数

在 OpenClaw 中安装

/install anytocopy-extractor

功能描述

使用 anytocopy.com 在线提取抖音、小红书等平台的视频文案。当用户发送抖音、小红书等链接，想要提取文案时使用此技能。支持50+平台：无水印视频下载、视频转音频、图片去水印等。

使用说明 (SKILL.md)

AnyToCopy 文案提取器

使用 AnyToCopy 在线提取抖音、小红书等平台的视频文案。

工作流

Step 1：打开网站

使用 browser 工具导航到 AnyToCopy 首页：

https://www.anytocopy.com/

Step 2：输入链接

找到输入框（textbox），输入用户提供的链接。

Step 3：点击提取

找到并点击 "Start Extract" 按钮。

Step 4：等待结果

等待页面加载出结果（文案内容）。可能需要等待几秒钟。

Step 5：提取文案

从页面中提取文案内容，返回给用户。

注意事项

这是一个基于浏览器的自动化方案，适合临时使用
如果 AnyToCopy 网站有变化，需要更新 selectors
提取是免费的，无需登录
支持 50+ 平台：抖音、小红书、快手、B站、微博等

输出格式

向用户返回提取到的文案内容，包括：

标题
正文/脚本
如果有视频/图片链接也可以一并提供

安全使用建议

This skill appears internally consistent, but before installing/checking: (1) confirm your agent environment provides a browser/automation tool (the SKILL.md assumes one); (2) be aware it depends on anytocopy.com — if the site changes or becomes unavailable the skill will break; (3) respect copyright and terms of service for the content you extract and avoid sending private/sensitive links to the skill; (4) since it is instruction-only, no code is installed locally, but the skill will cause the agent to visit an external website to perform extraction.

功能分析

Type: OpenClaw Skill Name: anytocopy-extractor Version: 1.0.0 The skill bundle provides instructions for an AI agent to automate a browser to extract video transcripts from social media links via the anytocopy.com website. The logic in SKILL.md is transparent and strictly follows the stated purpose of web-based content extraction without any evidence of data exfiltration, malicious execution, or prompt injection attacks.

能力评估

ℹ Purpose & Capability

Name/description match the runtime instructions (navigate to anytocopy.com, input link, click extract, return text). One minor mismatch: the SKILL.md assumes the agent has a 'browser' automation tool available at runtime, but the skill's metadata declares no required binaries or tools. This is plausible for a platform-provided browser tool, but it is an implicit requirement that should be verified before use.

✓ Instruction Scope

Instructions are narrowly scoped to visiting the anytocopy.com site, entering the user-provided link, clicking the extract button, and returning the resulting title/body and any media links. The instructions do not ask the agent to read local files, access environment secrets, or transmit data to any endpoint other than the target site and the user.

✓ Install Mechanism

No install spec (instruction-only). Nothing will be downloaded or written to disk by the skill itself.

✓ Credentials

The skill declares no environment variables, credentials, or config paths. This is proportionate for a scraper that uses a third-party web UI. Note: if the agent's browser automation requires credentials or cookies to access certain content, those would be external to this skill.

✓ Persistence & Privilege

always is false and the skill does not request elevated or persistent privileges. Autonomous invocation is allowed by platform default but the skill does not request system-wide configuration changes.

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 anytocopy-extractor
安装完成后，直接呼叫该 Skill 的名称或使用 /anytocopy-extractor 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 anytocopy-extractor. - Enables extraction of video captions from platforms like Douyin and Xiaohongshu via anytocopy.com. - Supports over 50 platforms, offering features such as watermark-free video download, audio extraction, and image watermark removal. - Provides extracted content including title, main text/script, and optional media links. - No login required; fully browser-based workflow.

元数据

Slug anytocopy-extractor

版本 1.0.0

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