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 loveld322/viral-video-blueprint --skill replicate-viral-videogit clone --depth 1 https://github.com/loveld322/viral-video-blueprintWrote 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/loveld322/viral-video-blueprint/replicate-viral-video)<a href="https://agentmods.dev/skills/loveld322/viral-video-blueprint/replicate-viral-video"><img src="https://agentmods.dev/badge/skills/loveld322/viral-video-blueprint/replicate-viral-video/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/loveld322/viral-video-blueprint/replicate-viral-video"><img src="https://agentmods.dev/badge/skills/loveld322/viral-video-blueprint/replicate-viral-video.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 | $0.00060 | $0.00794 |
| Opus 5 | $0.00030 | $0.00397 |
| Sonnet 5 | $0.00012 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
replicate-viral-video 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.
What it actually says
爆款视频复刻
核心原则
先用项目产生可核验的证据，再改写为用户自己的内容。不得凭链接或印象编造分析。
输入
必须取得一个受支持的 HTTPS 单条视频链接。可选输入：新主题、业务材料或文件路径、目标客户、CTA、fast|balanced|deep、auto|none|openai|gemini|ollama。
没有真实链接时只索取链接，不运行示例地址。本地 MP4、账号主页、合集、私密/付费内容或绕过访问控制的请求必须拒绝。
执行
- 读取用户明确提供的业务材料；不要搜索无关目录。
- 从本
SKILL.md所在目录解析scripts/analyze_link.py，运行：
python3 <skill目录>/scripts/analyze_link.py "<视频链接>" \
--output-dir "<用户指定目录>" \
--profile balanced --provider auto
不要默认传 --project-dir：runner 会优先读取 VVB_PROJECT_DIR，再从软链解析后的本脚本路径定位仓库，最后尝试默认 Documents 目录。
- 命令失败时原样报告结构化错误和可执行修复建议，不生成虚构结论。
- 成功后必须读取
analysis.md、template.json、transcript.srt，并查看contact-sheet.jpg。缺少任一文件即停止。 - 将证据与用户材料合并为下面的固定中文交付；不要只返回文件路径。
输出契约
按顺序输出：
- 原视频一句话套路与目标受众
- 前 3 秒钩子和爆点证据
- 原视频叙事、镜头、字幕、配音、BGM、背景与元素拆解
- 新主题完整口播/字幕脚本
- 逐镜头复刻表：时间、目的、画面、台词、剪辑、替换素材
- 素材准备清单
- 配音、BGM、音效和剪辑参数
- 获客 CTA 与发布建议
- 置信度、未识别项和版权边界
明确说明第一版产出分析与制作蓝本，不直接渲染最终视频。
复用边界
可复用结构、节奏、镜头功能和公开剪辑预设。必须替换原人物、原文案、Logo、账号标识、水印、截图和受版权保护素材。禁止去水印、截取原旁白、克隆真人声音或分发原音乐。同一 BGM 仅在平台曲库或用户许可证允许时使用。
可复制提示词
使用 $replicate-viral-video 分析这个视频链接：<链接>。
我的新主题：<主题>
我的产品/业务：<说明或材料路径>
目标客户：<人群>
期望行动：<私信、留资、咨询或购买>
请输出业务化新脚本、逐镜头复刻表、素材清单、剪辑参数和 CTA；保留方法与节奏，替换原人物、文案、Logo、水印和受版权保护素材。
What ships with it
2 files 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 · 65 lines · 60 tokens per session scan A d4ab2c742171
replicate-viral-video is a skill published in the GitHub repository loveld322/viral-video-blueprint (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 794 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
douyin-upload
A workflow for using the sau command-line tool to log in to Douyin, the Chinese short-video platform, check account cookies, and publish videos or image-and-text posts.
kuaishou-upload
A workflow for using the sau command-line tool to log in to Kuaishou, a Chinese social media platform, check account cookies, and publish videos or image-and-text posts.
xiaohongshu-upload
A workflow for using the sau command-line tool to log in to Xiaohongshu, a Chinese social media platform, check account cookies, and publish videos or image-and-text posts.
bilibili-upload
A workflow for using the sau command-line tool to log in to Bilibili, a Chinese video-sharing platform, check an account, and upload videos.
laohan-chuangzuo
A writing workflow for spoken-video scripts. It accepts an outline, raw text, a recording, a web-link queue, or a free-form topic, then organizes the material before writing the script.
laohan-skillcreator
A skill-development tool for creating, reviewing, repairing, and improving Agent Skills, which are reusable instructions that guide coding agents through specialized work.