Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/yehyakin/hermes-skills/yoyo-video-clipping-workflow)<a href="https://agentmods.dev/skills/yehyakin/hermes-skills/yoyo-video-clipping-workflow"><img src="https://agentmods.dev/badge/skills/yehyakin/hermes-skills/yoyo-video-clipping-workflow/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/yehyakin/hermes-skills/yoyo-video-clipping-workflow"><img src="https://agentmods.dev/badge/skills/yehyakin/hermes-skills/yoyo-video-clipping-workflow.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 | $0.00035 | $0.01800 |
| Opus 5 | $0.00017 | $0.00900 |
| Sonnet 5 | $0.00007 | $0.00360 |
| Haiku 4.5 | $0.00003 | $0.00180 |
Grade C, and why
yoyo-video-clipping-workflow scanned grade C with 2 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 12d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "http://localhost:8000/api/projects/{PROJECT_ID}" | python3 -c " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:8000/health How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
悠悠有鸽 - 竞品视频精剪流水线
概述
从悠悠有鸽（香港YoYo）直播竞品视频中，通过 Whisper 转录 → AI分析识别带货节点 → 剪辑精剪切片的完整流水线。
环境准备
Python 环境
- AutoClip 需要 Python 3.11+（系统默认 3.9 不支持
type |语法） - 使用
~/.hermes-guardian/venv/bin/python3.11 - 依赖安装：
pip install fastapi uvicorn python-multipart dashscope==1.23.5 \ openai pydub pysrt pydantic python-dotenv aiofiles \ requests aiohttp cryptography yt-dlp watchfiles whisper
Whisper 模型
- 模型缓存位置：
~/.cache/whisper/ - 已下载：
base.pt,large-v3-turbo.pt - whisper CLI 位置：
~/.hermes-guardian/venv/bin/whisper
流水线步骤
Step 1：提取音频（ffmpeg）
视频文件大（4GB+），需要先提取音频再转录。
# 提取音频（WAV格式，单声道16kHz）
ffmpeg -y -i "INPUT.mp4" \
-ac 1 -ar 16000 -c:a pcm_s16le \
-t 600 \ # 可选：限制时长（秒）
"output.wav"
# 快速测试：只提取前1分钟
ffmpeg -y -i "INPUT.mp4" \
-ac 1 -ar 16000 -c:a pcm_s16le \
-t 60 \
"output_1min.wav"
Step 2：Whisper 转录
# 创建输出目录
mkdir -p /tmp/whisper_output
# 使用 tiny 模型（最快，用于测试）
whisper "audio.wav" \
--model tiny \
--language zh \
--output_format srt \
--output_dir /tmp/whisper_output
# 使用 base 模型（平衡速度与精度）
whisper "audio.wav" \
--model base \
--language zh \
--output_format srt \
--output_dir /tmp/whisper_output
性能参考（Mac M2 CPU）：
- 1分钟音频：约2分钟（tiny模型）
- 10分钟音频：转录超时（约20分钟+）
base模型比tiny慢约3-5倍- 建议分批处理或使用 GPU
Step 3：AutoClip 后端
# 启动后端（需要 Python 3.11）
cd ~/autoclip_mvp
mkdir -p uploads outputs logs # 首次需要创建
PYTHONPATH=~/autoclip_mvp \
~/.hermes-guardian/venv/bin/python3.11 \
backend_server.py
# 健康检查
curl http://localhost:8000/health
Step 4：AutoClip 前端
cd ~/autoclip_mvp/frontend
npm install # 首次需要
npm run dev # 启动后访问 http://localhost:3000
测试视频路径
/Users/yehya/Downloads/竞品视频/香港🇭🇰YoYo20260425201954.mp4
- 时长：100分29秒
- 大小：4.3GB
- 适合测试完整流程
悠悠有鸽转录样本
[00:00.000 → 00:03.720] 这个门店去给来去做这么一个直播
[00:03.720 → 00:04.360] 我们最近的话呢
[00:04.360 → 00:08.600] 也是有很多的一些上心
[00:08.600 → 00:09.960] 大部分的话都是断秀
[00:09.960 → 00:12.600] 那么最近也是一直后台很多老粉
...
→ 主播正在介绍新品上架，引导观众关注
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.
- 12d ago First seen · 177 lines · 35 tokens per session scan C 4b854f588713
yoyo-video-clipping-workflow is a skill published in the GitHub repository yehyakin/hermes-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 1,800 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
chinese-video-transcribe-pdf
A workflow that turns Chinese-language videos, with or without subtitles, into structured text and a Chinese PDF report. It can use videos from sources such as YouTube or local MP4 files.
Генерация команд для Whisper CLI
A command-line guide for running OpenAI Whisper, a tool that converts speech recordings into text. It builds commands using the chosen model, language, and output file settings.
card-xiaohongshu
Xiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.
data-report
Turns CSV, Excel, or JSON data into a polished visual report page.
poster-hero
Vertical poster or Moments-style share image with strong visual impact.
deck-ljg-present
A presentation template that converts an outline or Markdown document into large, poster-like slides while keeping the original wording, order, and content. It uses black, red, or yellow colour themes and assigns document elements to slide layouts.