← 返回 Skills 市场
wangminrui2022

short-video-content-replicator

作者 顶尖王牌程序员 · GitHub ↗ · v1.0.2 · MIT-0
cross-platform ⚠ suspicious
128
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install short-video-content-replicator
功能描述
当用户想要**一键复制抖音或B站短视频内容**、**把短视频转成带标点的高质量文字**、**提取视频干声和转录文本**、**端到端处理短视频内容**时自动触发。 这是一个复合工作流技能:输入抖音/B站视频URL或本地视频目录,按严格6步顺序执行全流程(或从指定步骤断点续跑)。 步骤包括:1. 下载视频(link-...
安全使用建议
This skill is an orchestrator that runs other Python scripts in a sibling skills/ directory. Before installing or running it: 1) Verify that the referenced child skills (link-resolver-engine, mp4-to-mp3-extractor, purevocals-uvr-automator, turbo-whisper-local-stt, llm-text-correct, funasr-punctuation-restore) are present and come from trusted sources. 2) Inspect those child scripts for network calls, credential usage, or unexpected behavior — the orchestrator will execute them with your user privileges. 3) Note several wrapper scripts referenced by replicate.py (audio_to_text.py, correct_text.py, punctuation_restore.py, video_snapper.py) are not bundled here; confirm where they come from to avoid accidental execution of unintended code. 4) Run in a sandbox or on non-sensitive data first, and check for any environment variables or keys the child scripts require. If you cannot verify the provenance of the sibling skills, do not run this skill.
功能分析
Type: OpenClaw Skill Name: short-video-content-replicator Version: 1.0.2 The skill is a legitimate workflow orchestrator designed to automate a 6-step process for downloading videos (from Douyin/Bilibili) and converting them into high-quality text. The main script, `scripts/replicate.py`, safely manages sub-processes using `subprocess.run` with argument lists, preventing shell injection. It coordinates with other atomic skills (like `mp4-to-mp3-extractor` and `purevocals-uvr-automator`) to perform audio extraction, vocal separation, and transcription. No evidence of data exfiltration, malicious persistence, or prompt injection was found.
能力评估
Purpose & Capability
The name/description (download → extract → separate → transcribe → correct → punctuate) aligns with the script's orchestration role. However the orchestrator expects multiple other skills (link-resolver-engine, mp4-to-mp3-extractor, purevocals-uvr-automator, turbo-whisper-local-stt, llm-text-correct, funasr-punctuation-restore) to exist as sibling directories. That dependency is reasonable for an orchestrator, but callers should expect those external skills to be required. Also the replicate.py references a few scripts (audio_to_text.py, correct_text.py, punctuation_restore.py, video_snapper.py) that are not present in this package — a missing/ inconsistent file set.
Instruction Scope
The SKILL.md and replicate.py instruct the agent to spawn subprocesses that run many other scripts. The orchestrator will resolve a top-level skills/ directory and execute scripts from sibling skill folders — this effectively grants it permission to run arbitrary code present in that directory tree. The skill's instructions do not read unrelated system files or environment variables themselves, but the external scripts it calls could. Also several wrapper scripts the orchestrator expects to call are not bundled, so runtime behavior depends on the environment's layout.
Install Mechanism
No install spec; it's instruction-only with one Python script. Nothing is downloaded or installed by the skill itself — low install risk. The only declared runtime dependency is python, which is appropriate.
Credentials
The skill declares no required environment variables or credentials. That is proportionate to an orchestrator. Caveat: the external child scripts it invokes (downloaders, transcribers, etc.) might require API keys or credentials not declared here — the orchestrator does not surface or validate those.
Persistence & Privilege
always is false and user-invocable is true. The skill does not request elevated platform persistence or modify other skills' configs. However, because it executes sibling scripts, an installed instance gains runtime ability to run arbitrary code present in the skills/ tree when 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 short-video-content-replicator
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /short-video-content-replicator 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
- Added scripts/replicate.py as the main workflow entry. - Enhanced trigger phrases and use case descriptions in SKILL.md, with improved clarity on when and how the skill activates. - Updated SKILL.md to detail supported inputs, step descriptions, and real user intentions for better discoverability and usability. - No breaking changes; existing workflow steps and commands remain the same.
v1.0.1
- Documentation simplified for clarity and brevity; redundant explanations and usage details removed. - Descriptions for each workflow step now focus on CLI command usage and parameters. - The introduction now highlights that this Skill orchestrates atomic CLI Skills in strict sequence. - Usage examples streamlined; advanced options presented more concisely. - Functional behavior and workflow remain unchanged.
v1.0.0
- Initial release of an end-to-end short video content replication workflow. - Automatically processes videos from Douyin or Bilibili URLs, or local directories, in up to 6 ordered steps: video download, MP4-to-MP3 extraction, vocal separation, audio transcription, text correction, and punctuation restoration. - Supports breakpoint resume from any workflow step based on input type (URL, video, MP3, WAV, or TXT directory). - Allows custom output directory configuration for each processing step. - Ensures each intermediate and final output is saved for further use or manual review.
元数据
Slug short-video-content-replicator
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

short-video-content-replicator 是什么?

当用户想要**一键复制抖音或B站短视频内容**、**把短视频转成带标点的高质量文字**、**提取视频干声和转录文本**、**端到端处理短视频内容**时自动触发。 这是一个复合工作流技能:输入抖音/B站视频URL或本地视频目录,按严格6步顺序执行全流程(或从指定步骤断点续跑)。 步骤包括:1. 下载视频(link-... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 128 次。

如何安装 short-video-content-replicator?

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

short-video-content-replicator 是免费的吗?

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

short-video-content-replicator 支持哪些平台?

short-video-content-replicator 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 short-video-content-replicator?

由 顶尖王牌程序员(@wangminrui2022)开发并维护,当前版本 v1.0.2。

💬 留言讨论