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 yehyakin/hermes-skills --skill ecommerce-video-discoverygit clone --depth 1 https://github.com/yehyakin/hermes-skillsWrote 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-discovery)<a href="https://agentmods.dev/skills/yehyakin/hermes-skills/ecommerce-video-discovery"><img src="https://agentmods.dev/badge/skills/yehyakin/hermes-skills/ecommerce-video-discovery/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-discovery"><img src="https://agentmods.dev/badge/skills/yehyakin/hermes-skills/ecommerce-video-discovery.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 | $0.00051 | $0.01070 |
| Opus 5 | $0.00026 | $0.00535 |
| Sonnet 5 | $0.00010 | $0.00214 |
| Haiku 4.5 | $0.00005 | $0.00107 |
Grade A, and why
ecommerce-video-discovery 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.
What it actually says
电商视频高光发现路由器
核心定位
收到"分析视频找高光"类任务时,根据视频特征自动选择最优发现路径,不需要用户指定用哪个工具。
下游调用 skill:
whisper-video-clipping-workflow→ Whisper路径(有字幕、话语丰富)ecommerce-visual-clip-scanning→ 视觉扫描路径(无字幕、画面信息多)ecommerce-video-highlights→ 三阶段AI分析(需要商业价值评估)
路由决策树
用户:分析这个视频找带货高光
│
├── 用户是否指定了方法?
│ ├── 指定 Whisper/转写/话术 → 走 whisper-video-clipping-workflow
│ ├── 指定视觉/画面/镜头 → 走 ecommerce-visual-clip-scanning
│ └── 指定 AI 分析/评估 → 走 ecommerce-video-highlights
│
├── 用户没指定 → 分析视频特征
│ ├── 视频时长 < 5分钟 + 有字幕轨道 → whisper-video-clipping-workflow
│ ├── 视频时长 > 30分钟 + 无字幕 → 视觉扫描路径
│ └── 需要批量切片 → AutoClip → whisper-video-clipping-workflow
│
└── 用户说"随便/都行/你决定" → 默认走 whisper-video-clipping-workflow
路由提示词模板
根据选择的路径,在任务开头注入:
Whisper路径注入:
该视频有字幕/话术丰富,优先使用 whisper-video-clipping-workflow:从 Whisper 转写入手,用关键词定位高光片段,再 FFmpeg 切割。完成后存入 neirong-fuoli 素材库。
视觉扫描路径注入:
该视频无字幕或镜头语言丰富,优先使用 ecommerce-visual-clip-scanning:从画面抽帧 + AI 视觉分析入手,识别有产品展示的时间段,再验证+切割。完成后存入 neirong-fuoli 素材库。
三阶段AI路径注入:
需要评估视频的商业价值,使用 ecommerce-video-highlights:抽帧 + Whisper + AI 视觉三阶段分析,输出带商业价值评分的片段清单。完成后存入 neirong-fuoli 素材库。
统一输出标准
无论走哪个路径,最终交付格式统一:
# {竞品名} 视频高光分析
**视频**:{标题/链接}
**时长**:{X}分钟
**发现方法**:{Whisper/视觉扫描/AI分析}
**分析时间**:{日期}
---
## 推荐片段清单
| # | 时间戳 | 时长 | 场景类型 | 商业价值 | 话术亮点 |
|---|--------|------|----------|----------|----------|
| 1 | 01:41 | 25s | 产品特写 | ⭐⭐⭐⭐⭐ | "..." |
| 2 | 03:22 | 30s | 搭配讲解 | ⭐⭐⭐⭐ | "..." |
---
## 话术亮点摘录
{3-5句核心话术,可直接复用}
---
## 下一步
- [ ] 发布清单已生成 → `/发布视频 {标题}`
- [ ] 存入 content-fuoli 素材库
- [ ] 人工审核后精调导出
关键约束
- 不重复发明轮子:直接调用现有 skill,不复制 skill 内的步骤代码
- 完成后必须存入 neirong-fuoli:切片数 + 话术亮点 + 视频元信息 →
~/content-fuoli/ - 选路径前先问用户:如果视频特征模糊,主动确认用哪种方法
- 碎片化场景用视觉扫描:竖屏直播回放,主播边走动边讲解,Whisper 容易失效
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 · 107 lines · 51 tokens per session scan A 879b900cb6f2
ecommerce-video-discovery is a skill published in the GitHub repository yehyakin/hermes-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 1,070 once invoked, about $0.0003 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
card-twitter
Twitter quote or data card designed to pair with a post.
card-xiaohongshu
Xiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.
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.
info-funnel
A funnel infographic is a visual that shows how a large starting group becomes a smaller result across three to six stages.
deck-presenter-mode
A presentation format for speakers who want written notes and a pop-up teleprompter. A teleprompter shows the current script while the speaker presents.