What is ecommerce-video-clip-workflow?

A complete process for turning livestream or competitor recordings into short sales clips. It extracts audio, transcribes it, finds sales-related phrases, cuts the matching sections, creates subtitle files, and burns the subtitles into the video.

Studying competitor sales wording, finding livestream highlights, and producing multiple short clips for product-link promotion.

It brings searching, editing, and subtitle creation into one repeatable workflow for long recordings.

ecommerce-video-clip-workflow — Skill by yehyakin/hermes-skills

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/yehyakin/hermes-skills

agentmods

npx agentmods add skills/yehyakin/hermes-skills/ecommerce-video-clip-workflow

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yehyakin/hermes-skills/ecommerce-video-clip-workflow/github.svg)](https://agentmods.dev/skills/yehyakin/hermes-skills/ecommerce-video-clip-workflow)

Your own site

<a href="https://agentmods.dev/skills/yehyakin/hermes-skills/ecommerce-video-clip-workflow"><img src="https://agentmods.dev/badge/skills/yehyakin/hermes-skills/ecommerce-video-clip-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yehyakin/hermes-skills/ecommerce-video-clip-workflow"><img src="https://agentmods.dev/badge/skills/yehyakin/hermes-skills/ecommerce-video-clip-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 996 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00062	$0.00996
Opus 5.5	$0.00025	$0.00398
Sonnet 5.5	$0.00012	$0.00199
Haiku 4.5	$0.00006	$0.00100

Measured 2mo ago against content hash 331cfefbeb6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ecommerce-video-clip-workflow 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (examples/analyze_competitor.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

ecommerce-video-clip-workflow/SKILL.md · 97 lines

What it actually says

电商带货视频切片工作流

从长视频（直播/竞品视频）中自动识别高价值带货片段，精剪为挂车切片。

适用场景

竞品视频话术分析 + 切片提取
直播回放高光时刻挖掘
视频挂车素材批量制作

前置要求

whisper.cpp 已编译 Metal 支持（Mac Apple Silicon）
ffmpeg-full（支持 libass subtitles 滤镜）
模型：ggml-small.bin（中文识别准确 + 速度快）

Pipeline

Step 1: 提取音频

ffmpeg -i INPUT.mp4 -vn -c:a pcm_s16le audio.wav

Step 2: Whisper 转写（Metal GPU，8x 实时）

cd ~/whisper.cpp
./build/bin/whisper-cli \
  -m models/ggml-small.bin \
  -f audio.wav \
  -l zh \
  --output-txt \
  --output-file transcript

速度：small 模型 Metal 加速 ~8x 实时（base 模型仅 0.8x 且中文差）

Step 3: 定位带货节点

# 找"一号链接"、"必买"、"鲜货"、"限量"等关键词
grep -n "一号链接\|必买\|鲜货\|限量\|划算" transcript.txt

# 计算行号 → 视频时间（每行 ≈ 视频秒数 / 总行数）
python3 -c "
video_sec = 13112  # 视频总秒数
lines = 8480       # transcript 总行数
per_line = video_sec / lines  # ≈ 1.54秒/行
"

Step 4: 精剪片段（ffmpeg）

ffmpeg -y -i INPUT.mp4 \
  -ss 1630 -t 25 \
  -c:v libx264 -crf 20 -preset fast \
  -c:a aac -b:a 128k \
  clip.mp4

Step 5: 生成 SRT 字幕文件

# 根据行号范围 + 每行秒数生成 SRT
def lines_to_srt(transcript_path, start_line, end_line, per_line_sec=1.54):
    # 生成带时间戳的 SRT 文件

Step 6: 烧字幕（ffmpeg-full + libass）

/opt/homebrew/opt/ffmpeg-full/bin/ffmpeg -y \
  -ss START -t DURATION \
  -i INPUT.mp4 \
  -vf "subtitles=SRT_PATH:force_style='FontSize=28,Bold=1,OutlineColour=&H00000000,Outline=2'" \
  -c:v libx264 -crf 20 -preset fast \
  -c:a aac -b:a 128k \
  OUTPUT.mp4

关键：必须用 ffmpeg-full（Homebrew），标准 ffmpeg 缺 libass 滤镜。

关键经验

问题	原因	解决方案
Whisper CPU 太慢（3.6小时要跑7小时）	base 模型 + CPU	改 whisper.cpp small 模型 + Metal
base 模型中文识别差	模型太小	换 ggml-small.bin
ffmpeg subtitles 滤镜报错	标准 ffmpeg 不含 libass	brew install ffmpeg-full
SRT 时间戳和片段对不上	transcript 是纯文本无时间戳	用总秒数/总行数估算每行时长
中文路径导致 ffmpeg 报错	路径含中文字符	复制到 ~/tmp/ 简单路径

输出规格

分辨率：1088x1920（竖屏抖音/视频号）
时长：20-30秒（挂车最佳）
编码：H264 + AAC
字幕：内嵌 SRT burn-in

Files

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.

examples/analyze_competitor.py 4.7 KB runs code

Changes

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.

2mo ago First seen · 97 lines · 62 tokens per session scan A 331cfefbeb6e

Subscribe to this mod's changes

ecommerce-video-clip-workflow is a skill published in the GitHub repository yehyakin/hermes-skills (10 stars, last pushed 5mo ago), licensed MIT. It adds 62 tokens to every session and 996 once invoked, about $0.0002 per session on Opus 5.5. 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.

Creative and media E-commerce media

ecommerce-video-clip-workflow next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ecommerce-video-clip-workflowyehyakin/hermes-skills	Skill	10	5mo ago	MIT	A	62	Claude Code, Codex
image-zoom-360finsilabs/awesome-ecommerce-skills	Skill	63	15d ago	MIT	A	32	Claude Code, Codex
ai-image-generation-editing-apirondoflow/rondoflow	Skill	29	2d ago	MIT	A	63	Claude Code, Codex
gemini-image-generatoroyi77/1ai-skills	Skill	17	yesterday	MIT	A	21	Claude Code
amazon-reviews-api-skillbrowser-act/skills	Skill	6.3k	2d ago	MIT	A	124	Claude Code, Codex
amazon-competitor-analyzerbrowser-act/skills	Skill	6.3k	2d ago	MIT	A	48	Claude Code, Codex
run-testsAzure/azure-sdk-for-java	Skill	2.6k	yesterday	MIT	A	21	Claude Code, Codex