← 返回 Skills 市场
103
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install oc-youtube-summarizer
功能描述
YouTube and Bilibili video transcript extraction and AI-powered summarization. Use when you need to summarize a YouTube or Bilibili (B站) video, extract trans...
安全使用建议
This skill generally does what it says, but review these before installing:
- Be aware yt-dlp is invoked with '--cookies-from-browser chrome' — that will access Chrome cookies (possible session tokens). Only allow this if you understand and accept the privacy risk; prefer public videos or export cookies to a limited cookie file instead.
- Inspect the rest of summarize.py (the parts not shown) to confirm where transcripts/summaries are sent. If the script calls external LLM/image services, check which endpoints are used and whether any tokens you provide could be exfiltrated.
- Avoid supplying broad secrets (GITHUB_TOKEN, OPENCLAW_GATEWAY_TOKEN, etc.) unless you trust the skill and have inspected the code paths that use them. If unsure, run the skill in an isolated environment (container or VM) and monitor outbound network traffic.
- The setup script expects Homebrew for yt-dlp install; on Linux manually install yt-dlp/ffmpeg before running setup.
If you want, I can scan the remainder of summarize.py for where LLM/API calls are made (endpoints, headers, and any hardcoded URLs) and highlight exact lines that access cookies or environment tokens.
功能分析
Type: OpenClaw Skill
Name: oc-youtube-summarizer
Version: 2.2.0
The skill is classified as suspicious due to high-risk data access and an extensive external communication chain. Specifically, `scripts/summarize.py` invokes `yt-dlp` with the `--cookies-from-browser chrome` flag when processing Bilibili videos, which allows the script to access sensitive browser data. Furthermore, the script implements a complex LLM fallback chain that utilizes sensitive environment variables (e.g., `GITHUB_TOKEN`, `OPENCLAW_GATEWAY_TOKEN`) to send video transcripts to multiple external endpoints, including an unofficial GitHub Copilot API and Pollinations.ai. While these features are technically aligned with the stated purpose of bypassing rate limits and generating summaries, the combination of browser cookie access and multi-provider data transmission represents a significant security and privacy risk.
能力评估
Purpose & Capability
Name/description match the files: the script uses yt-dlp, youtube-transcript-api, faster-whisper, and ffmpeg to fetch transcripts, transcribe Bilibili audio, extract frames and produce JSON summaries — this is coherent with the stated purpose.
Instruction Scope
The SKILL.md and script instruct using yt-dlp with '--cookies-from-browser chrome' (reads Chrome cookies) and describe an 'innertube ANDROID client + Cloudflare proxy' approach to bypass rate limits. Those steps can access sensitive browser session cookies and involve proxying/more network hops; SKILL.md does not explicitly document where network requests for summaries/images are sent (LLM fallback chain is described but not audited). The skill also suggests agents will post JSON to third-party services (Discord/Notion) in examples — those are examples, not built-in, but increase the potential attack surface when combined with the skill's outputs.
Install Mechanism
Installation is via the provided setup.sh which creates a local venv and pip-installs known PyPI packages (youtube-transcript-api, requests, innertube, faster-whisper). yt-dlp and ffmpeg are installed/required via system package managers (brew or manual). No arbitrary binary downloads or shortener URLs were found; overall install method is reasonable but setup.sh exits if brew is missing (Linux users must install yt-dlp manually).
Credentials
The skill requires no secrets to run, but SKILL.md/README list many optional environment variables (LLM_API_URL/KEY, OPENCLAW_GATEWAY_TOKEN, GITHUB_TOKEN, POLLINATIONS_API_KEY). Those are plausible for LLM/image fallbacks, but the README's fallback chain (including GitHub token as a potential LLM source) is unusual and broad. More importantly, use of '--cookies-from-browser chrome' implicitly grants access to browser cookies (not declared as a required config path), which is disproportionate to a simple transcript fetch unless you need authenticated access to gated content.
Persistence & Privilege
Skill does not request always:true and does not modify other skills. It writes its own config/settings.json and creates a local venv under the skill directory (expected). No evidence of requesting permanent elevated system presence.
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 oc-youtube-summarizer - 安装完成后，直接呼叫该 Skill 的名称或使用
/oc-youtube-summarizer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
v2.2.0
v2.2.0: 安装后模式引导(text-only/auto-insert/ai-review), --mode参数, config/settings.json, --setup重配
v2.1.0
v2.1: 自动帧选择（select_key_frames），输出 selected_frames + frame_time_map，新增 --max-frames 参数
v2.0.0
v2.0: 新增B站视频支持（yt-dlp下载+faster-whisper本地转录+ffmpeg关键帧提取），自动检测平台，新增 --whisper-model/--no-frames/--frame-interval 参数
v1.0.0
Initial release: YouTube transcript + AI summary with 4-level LLM fallback (custom endpoint → OpenClaw Gateway → GitHub Copilot → Pollinations). Env-var driven, zero hardcoded secrets. Forked from happynocode/openclaw-skill-youtube with bug fixes and enhanced LLM support.
元数据
常见问题
Youtube Summarizer 是什么？
YouTube and Bilibili video transcript extraction and AI-powered summarization. Use when you need to summarize a YouTube or Bilibili (B站) video, extract trans... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 103 次。
如何安装 Youtube Summarizer？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install oc-youtube-summarizer」即可一键安装，无需额外配置。
Youtube Summarizer 是免费的吗？
是的，Youtube Summarizer 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Youtube Summarizer 支持哪些平台？
Youtube Summarizer 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 Youtube Summarizer？
由 mcdowelll（@mcdowell8023）开发并维护，当前版本 v2.2.0。
推荐 Skills