← 返回 Skills 市场
mackjosn

视频去除水印

作者 mackjosn · GitHub ↗ · v1.0.2 · MIT-0
cross-platform ⚠ suspicious
106
总下载
1
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install midea-nomark
功能描述
视频去水印解析 Skill。支持 20+ 平台短视频去水印解析,包括抖音、快手、小红书、微博、西瓜视频、豆包、云雀、B站等。使用本技能时触发:解析视频、去水印、视频解析、解析链接、下载视频、去除水印、parse video、video parser、抖音解析、快手解析、小红书解析、bilibili 解析、douy...
安全使用建议
This skill appears to do what it says at the script level, but its core functionality is inside closed-source binaries that are not included or auditable in the package — that is the primary risk. Before installing or running: 1) obtain the actual binaries and verify they come from a trusted source and have published checksums or signatures; 2) prefer source or audited builds; 3) if you must run them, do so in a sandbox/VM or isolated container and monitor network traffic; 4) avoid running on machines with sensitive credentials or data available; 5) ask the publisher for source code or reproducible build instructions and a Linux binary if you need Linux support. If the author cannot supply verifiable binaries or source, treat this package with caution.
功能分析
Type: OpenClaw Skill Name: midea-nomark Version: 1.0.2 The skill relies entirely on the execution of opaque, pre-compiled binaries located in the 'assets/' directory (e.g., parse-video-darwin-arm64). While the provided shell scripts (scripts/parse.sh and scripts/serve.sh) are simple wrappers for these binaries, the core logic is hidden and not open-source, which poses a risk of unauthorized network activity or data exfiltration. The inclusion of a 'serve' command that opens a local HTTP port further increases the attack surface without visibility into the binary's internal behavior.
能力评估
Purpose & Capability
Name/description, scripts, and README all describe a local video parsing/no-watermark tool and the scripts only invoke a local 'parse-video-<os>-<arch>' binary, which is coherent with the stated purpose. However, the package claims local binaries exist but the listed assets are missing from the provided files and README/platform listing mismatches (Linux binary referenced in scripts but not in README assets). The README explicitly states the binary is closed-source ('不开源可执行文件'), which is expected for a binary-only parser but reduces auditability.
Instruction Scope
SKILL.md and the two shell scripts remain narrowly scoped: they detect OS/arch, make a shipped binary executable, then run it with 'parse <url>' or 'serve -p <port>'. The instructions do not tell the agent to read unrelated files or env vars. Concern: the actual network activity and data handling are delegated to an opaque binary (not present for review), so the runtime behavior (what is sent/received, whether other local files are read) cannot be verified from these instructions alone.
Install Mechanism
There is no install spec (instruction-only), which limits supply-chain risk from installers — but the skill relies on prebuilt binaries under assets/. Those binaries are not included in the provided file list; README enumerates some assets but they don't match scripts' expectations (scripts expect Linux binary too). Running unknown, closed-source binaries is high-risk because they could perform hidden network I/O or local data access; no checksums, no source, and no authoritative release URLs are provided.
Credentials
The skill declares no required env vars or credentials and the scripts do not read environment variables or config files. That is proportionate. Nonetheless, because the core logic runs in an opaque binary, that binary could request or transmit secrets at runtime; the lack of declared env requirements makes such behavior non-obvious and harder to detect.
Persistence & Privilege
The skill is not marked 'always:true' and doesn't request persistent system configuration. The serve mode runs a local HTTP server (expected for a local UI) but that is limited scope and user-invoked.
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 midea-nomark
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /midea-nomark 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
v1.0.2
**parse-video 1.0.2** 重命名与扩展:Skill 从 "midea-nomark" 升级为全平台视频无水印解析,支持 20+ 视频/图片平台。 - Skill 名称从“midea-nomark”改为“parse-video”,功能覆盖抖音、快手、小红书、微博、西瓜、B站、豆包、云雀等主流视频平台。 - 增加二进制与脚本:加入多系统 parse-video 程序(darwin/amd64、darwin/arm64、win64)、一键解析脚本 (parse.sh)、服务启动脚本 (serve.sh)。 - 移除过时文档和脚本,精简 references/api_docs.md、parse_doubao.py、start_server.sh 等。 - 更新并简化文档,更强的平台描述与用法示例。 - 支持一键命令行解析、CLI 和 Web UI 服务三种使用方式。
v1.0.1
- Skill name changed from "doubao-nomark" to "midea-nomark". - Added _skillhub_meta.json file for SkillHub integration. - Expanded and clarified the security section in documentation, explicitly noting that no executable binaries are included and describing how binaries are downloaded and verified. - All other functionalities and usage instructions remain unchanged.
v1.0.0
- Initial release of the skill, now renamed to doubao-nomark. - Supports extracting images (without watermark) from Doubao conversation threads. - Supports parsing and downloading Doubao and Yunque (jianying.com) video links without watermarks. - Fully automated: downloads required binaries, starts the service, and processes links with one command. - Local API provided for programmatic access and batch downloads.
元数据
Slug midea-nomark
版本 1.0.2
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 3
常见问题

视频去除水印 是什么?

视频去水印解析 Skill。支持 20+ 平台短视频去水印解析,包括抖音、快手、小红书、微博、西瓜视频、豆包、云雀、B站等。使用本技能时触发:解析视频、去水印、视频解析、解析链接、下载视频、去除水印、parse video、video parser、抖音解析、快手解析、小红书解析、bilibili 解析、douy... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 106 次。

如何安装 视频去除水印?

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

视频去除水印 是免费的吗?

是的,视频去除水印 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

视频去除水印 支持哪些平台?

视频去除水印 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 视频去除水印?

由 mackjosn(@mackjosn)开发并维护,当前版本 v1.0.2。

💬 留言讨论