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/ecommerce-video-clip-to-shortform)<a href="https://agentmods.dev/skills/yehyakin/hermes-skills/ecommerce-video-clip-to-shortform"><img src="https://agentmods.dev/badge/skills/yehyakin/hermes-skills/ecommerce-video-clip-to-shortform/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/ecommerce-video-clip-to-shortform"><img src="https://agentmods.dev/badge/skills/yehyakin/hermes-skills/ecommerce-video-clip-to-shortform.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 | $0.00047 | $0.01343 |
| Opus 5 | $0.00023 | $0.00672 |
| Sonnet 5 | $0.00009 | $0.00269 |
| Haiku 4.5 | $0.00005 | $0.00134 |
Grade A, and why
ecommerce-video-clip-to-shortform 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
电商直播视频 → 带货切片工作流
背景
从电商直播长视频(60-120分钟)中提取 15-30秒 带货短切片,用于短视频平台发布。
完整工作流
第一步:Whisper 转写
whisper /path/to/video.mp4 \
--model base \
--language zh \
--output_format srt \
--output_dir /tmp/whisper_output
第二步:从 SRT 提取爆点时间
keywords = ['138', '上车', '限量', '350克', '埃及', '万针', '不变形', '扣一']
# 找含有关键词的字幕行,输出:时间戳、关键词、上下文各2句
第三步:切精剪片段(FFmpeg)
ffmpeg -y -ss 00:08:09 -i 原始视频.mp4 -t 20 \
-c:v libx264 -crf 23 -preset fast \
-c:a aac -b:a 128k \
-movflags +faststart 输出.mp4
第四步:加字幕包装(FFmpeg 无 drawtext 时)
MacOS 打包环境通常没有 drawtext,用 PIL 生成叠加图:
from PIL import Image, ImageDraw, ImageFont
W, H = 1080, 1920 # 竖屏 9:16
def make_overlay(filename, line1, color1, size1, line2, color2, size2):
img = Image.new('RGBA', (W, H), (0, 0, 0, 0))
draw = ImageDraw.Draw(img)
font_paths = [
'/Users/yehya/Library/Fonts/27-华康饰艺体W7-GB.ttc',
'/System/Library/Fonts/Supplemental/Arial Unicode.ttf',
]
font1, font2 = None, None
for fp in font_paths:
try:
font1 = ImageFont.truetype(fp, size1)
font2 = ImageFont.truetype(fp, size2)
break
except: continue
# 大字 + 黑色描边
bbox1 = draw.textbbox((0, 0), line1, font=font1)
tw1, th1 = bbox1[2]-bbox1[0], bbox1[3]-bbox1[1]
x1, y1 = (W-tw1)//2, int(H*0.10)
for dx,dy in [(-2,-2),(-2,2),(2,-2),(2,2),(-2,0),(2,0),(0,-2),(0,2)]:
draw.text((x1+dx,y1+dy), line1, fill=(0,0,0,255), font=font1)
draw.text((x1,y1), line1, fill=color1, font=font1)
# 副标题
bbox2 = draw.textbbox((0, 0), line2, font=font2)
tw2, th2 = bbox2[2]-bbox2[0], bbox2[3]-bbox2[1]
x2, y2 = (W-tw2)//2, y1+th1+20
draw.text((x2,y2), line2, fill=color2, font=font2)
img.save(filename, 'PNG')
第五步:FFmpeg 叠加字幕图
ffmpeg -y -ss 00:08:08 -i 原始视频.mp4 \
-i /tmp/overlay_A.png -t 5 \
-filter_complex "[0:v][1:v]overlay=0:0:format=yuv420[out]" \
-map "[out]" -c:v libx264 -crf 23 -preset fast \
-c:a aac -b:a 128k -movflags +faststart 输出.mp4
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 111 lines · 47 tokens per session scan A 3755e4991895
ecommerce-video-clip-to-shortform is a skill published in the GitHub repository yehyakin/hermes-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 47 tokens to every session and 1,343 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
media-fetch
Download video/audio from 1000+ sites (YouTube, Twitter/X, Spotify, TikTok, etc.), extract audio, download subtitles, transcribe speech to text, and search for videos. Use when asked to download, summarize, or transcribe any video/audio URL, or when asked to search YouTube.
ckjia-shopping
A shopping search and price-comparison tool for Taobao, JD.com, Tmall, and Pinduoduo, with image-based product recognition. It requires the ckjia-shopping service and its access key to be enabled.
remotion-video
Use when you need to render an actual video file with Remotion — React compositions, the Composition/Sequence/TransitionSeries graph, transitions, burned-in word-by-word captions from a transcript, automatic silence removal, b-roll overlays, headless CI renders, and a final MP4 or MOV. NOT writing the script, hook…
ai-image-generation-editing-api
AI image generation, editing, and background removal API via Bria.ai — authenticates via OAuth device flow and caches credentials in /.bria/credentials, then calls 20+ endpoints to remove backgrounds for transparent PNGs and cutouts, generate images from text prompts, and edit…
clipforge-video
A tool for making short vertical videos for TikTok, Instagram Reels, YouTube Shorts, and similar platforms from a topic, product link or image, or existing script.
gemini-image-generator
Use when generating professional posed product images for e-commerce using Gemini AI with optimized prompts.