Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ALBEDO-TABAI/video-copy-analyzer --skill video-copy-analyzergit clone --depth 1 https://github.com/ALBEDO-TABAI/video-copy-analyzerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/albedo-tabai/video-copy-analyzer/video-copy-analyzer)<a href="https://agentmods.dev/skills/albedo-tabai/video-copy-analyzer/video-copy-analyzer"><img src="https://agentmods.dev/badge/skills/albedo-tabai/video-copy-analyzer/video-copy-analyzer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/albedo-tabai/video-copy-analyzer/video-copy-analyzer"><img src="https://agentmods.dev/badge/skills/albedo-tabai/video-copy-analyzer/video-copy-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00114 | $0.03782 |
| Opus 5 | $0.00057 | $0.01891 |
| Sonnet 5 | $0.00023 | $0.00756 |
| Haiku 4.5 | $0.00011 | $0.00378 |
Grade A, and why
video-copy-analyzer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- workshop — 86% identical, 410 lines differ
How it starts
The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
视频文案分析工具
一站式视频内容提取与文案分析,支持 B站、YouTube、抖音 等平台。
安装部署
系统要求
- Python 3.9+
- FFmpeg(用于音视频处理)
- 约 3GB 磁盘空间(FunASR 模型缓存)
一键安装
# 1. 基础工具
brew install ffmpeg # macOS
pip install yt-dlp requests pysrt python-dotenv
# 2. FunASR(核心 ASR 引擎,中文语音转录)
pip install funasr modelscope torch torchaudio
# 3. RapidOCR(烧录字幕识别,可选)
pip install rapidocr-onnxruntime
⚠️ FunASR 首次运行注意事项
FunASR 首次运行时会自动下载约 2-3GB 模型文件到 ~/.cache/modelscope/:
| 模型 | 大小 | 用途 |
|---|---|---|
| paraformer-zh | ~1.05GB | 中文语音识别(ASR) |
| fsmn-vad | ~20MB | 语音活动检测(长音频分段) |
| ct-punc | ~1GB | 标点恢复 |
- 首次下载可能需要 1-5 分钟(取决于网速),期间看起来像是卡住,请耐心等待
- 下载完成后会缓存到本地,后续运行秒级加载
- 如果下载失败,可手动从 ModelScope 下载模型放到
~/.cache/modelscope/hub/models/iic/目录
环境验证
# 验证所有依赖
python scripts/check_environment.py
# 或手动检查关键组件
yt-dlp --version
ffmpeg -version
python -c "from funasr import AutoModel; print('FunASR OK')"
python -c "from rapidocr_onnxruntime import RapidOCR; print('RapidOCR OK')"
首次使用设置
首次使用时,询问用户:
"请设置默认工作目录(用于保存下载的视频和分析报告):
A. 使用默认目录:
~/video-analysis/B. 每次手动指定目录 C. 指定一个固定目录:[请输入路径]"
保存用户选择供后续使用。
工作流程(5 阶段)
重要:你必须严格按照以下 5 个阶段顺序执行,每个阶段完成后再进入下一个阶段。不要跳过任何阶段。
阶段 1: 下载视频
目标:将用户提供的视频 URL 下载为本地 MP4 文件。
执行步骤:
- 获取用户提供的视频 URL 和输出目录
- 如果输出目录不存在,创建它:
mkdir -p <输出目录> - 判断视频平台并选择下载方式:
抖音视频(URL 包含 douyin.com 或 v.douyin.com)
使用专用下载脚本:
python scripts/download_douyin.py "<抖音链接>" "<输出目录>/<文件名>.mp4"
支持的链接格式:v.douyin.com/xxx、www.douyin.com/video/xxx、douyin.com/jingxuan?modal_id=xxx
抖音网页已对纯 HTTP 解析做风控。脚本会先尝试分享页解析,失败后启动本机 Chrome/Edge/Chromium(无头)提取播放地址,再回退 yt-dlp。需要 Node.js 18+ 以及上述浏览器之一;也可设置 DOUYIN_BROWSER 指向浏览器可执行文件。
其他平台(B站、YouTube 等)
使用 yt-dlp:
yt-dlp -f "bestvideo[height<=1080]+bestaudio/best[height<=1080]" \
--merge-output-format mp4 \
-o "<输出目录>/%(id)s.%(ext)s" \
"<视频URL>"
- 确认下载成功:检查 MP4 文件是否存在且大小 > 0
阶段 2: 字幕提取
目标:从视频中提取 SRT 格式字幕文件。
执行步骤:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 369 lines · 114 tokens per session scan A efe03f3bf4d6
video-copy-analyzer is a skill published in the GitHub repository ALBEDO-TABAI/video-copy-analyzer (208 stars, last pushed 23d ago), licensed MIT. It adds 114 tokens to every session and 3,782 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.