← 返回 Skills 市场
228
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-knowledge-ingest
功能描述
Ingest and summarize cross-platform videos into a local knowledge base. Use when working with YouTube, Bilibili, Xiaohongshu, or local media/subtitle files a...
安全使用建议
This skill appears to implement the described video→transcript→summary pipeline, but exercise caution before installing: 1) The package metadata claims no required binaries, yet the code needs yt-dlp, ffmpeg/ffprobe, a Whisper venv, and the `summarize --cli codex` tool — ensure you install and trust those tools first. 2) The code uses hard-coded, user-specific paths (e.g. /home/jason/.openclaw/..., /home/jason/.local/bin) and temporarily prepends them to PATH for subprocesses; update these defaults to match your environment to avoid accidentally using unexpected binaries. 3) Summarization uses an external backend (codex) and will send transcript text to that service if you run it — confirm privacy and authentication expectations. 4) The skill writes persistent transcripts/summaries/index entries to a local KB (default path above); if that data is sensitive, change the KB root before use. 5) Because the skill has executable scripts, review and (if needed) run it in a sandbox or test workspace first. If you want to proceed, update the default paths in the scripts, install the declared tools, and verify codex/summarize authentication separately.
功能分析
Type: OpenClaw Skill
Name: video-knowledge-ingest
Version: 1.0.0
The skill bundle implements a legitimate workflow for downloading, transcribing, and summarizing videos from platforms like YouTube and Bilibili. It utilizes standard tools such as yt-dlp, ffmpeg, and Whisper, and follows safe coding practices by using list-based subprocess calls to prevent shell injection. While the scripts contain hardcoded paths specific to a local environment (/home/jason/), these appear to be configuration artifacts rather than indicators of malicious intent or data exfiltration.
能力评估
Purpose & Capability
The SKILL.md and code clearly require external tools (yt-dlp, ffmpeg/ffprobe, summarize/codex, a Whisper venv) and write to a local knowledge root, but the registry metadata lists no required binaries or env vars. The script also embeds user-specific defaults (/home/jason/.openclaw/workspace and /home/jason/.local/bin) which may not be appropriate for other installations. The requested/used capabilities are coherent with the stated purpose, but the metadata omission and hard-coded paths are unexpected and may cause incorrect behavior.
Instruction Scope
SKILL.md stays on task: normalize URL, attempt subtitles, fall back to media download + Whisper, summarize, and persist results. However, it expects the summarization step to run via `summarize --cli codex` (an external service) and instructs persisting transcripts and summaries to a local knowledge base. The instructions do not request secrets but implicitly require codex authentication (not declared) and will send transcript text to that backend when used.
Install Mechanism
There is no install spec (instruction-only), so nothing is downloaded or installed by the platform. All executable behavior is in bundled scripts and Python files included with the skill. No external download/install URLs are used by the skill itself.
Credentials
The skill declares no required env vars, but the code assumes specific local resources: a workspace venv at a hard-coded path (e.g. /home/jason/.openclaw/workspace/.venv-whisper-gpu), and resolves fallback binary paths like /home/jason/.local/bin/yt-dlp and /home/jason/.local/bin/summarize. The run() helper also prepends /home/jason/.local/bin and /home/jason/.npm-global/bin to PATH for subprocesses. These assumptions are disproportionate (user-specific paths and PATH tweaks) and may cause unexpected use of local binaries or failure on other systems. The summarize/codex step will transmit transcript data to an external summarization backend if used; that external dependency is not represented in metadata.
Persistence & Privilege
The skill writes persistent artifacts (transcripts, summaries, metadata, downloads, and an append-only index) to a local knowledge-root (default under /home/jason/.openclaw/workspace/knowledge/video-notes). It does not request elevated platform privileges and is not always-enabled. Persisting user content locally is expected for its purpose but the hard-coded default path and the instruction 'do not move them unless asked' are noteworthy for users who expect skill data elsewhere.
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 video-knowledge-ingest - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-knowledge-ingest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 video-knowledge-ingest skill.
- Ingests and summarizes videos from YouTube, Bilibili, Xiaohongshu, or local files into a local knowledge base.
- Fetches subtitles if available; otherwise downloads media and transcribes using Whisper.
- Generates a text summary and saves transcript, summary, and metadata locally.
- Handles edge cases including subtitle errors, platform-specific issues, and dependency problems.
- Intended as the default video-to-summary workflow and for debugging ingestion failures.
元数据
常见问题
video-knowledge-ingest 是什么？
Ingest and summarize cross-platform videos into a local knowledge base. Use when working with YouTube, Bilibili, Xiaohongshu, or local media/subtitle files a... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 228 次。
如何安装 video-knowledge-ingest？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-knowledge-ingest」即可一键安装，无需额外配置。
video-knowledge-ingest 是免费的吗？
是的，video-knowledge-ingest 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
video-knowledge-ingest 支持哪些平台？
video-knowledge-ingest 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 video-knowledge-ingest？
由 Exsusiai（@exsusiai）开发并维护，当前版本 v1.0.0。
推荐 Skills