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 aAAaqwq/AGI-Super-Team --skill ai-viral-team-script-writinggit clone --depth 1 https://github.com/aAAaqwq/AGI-Super-TeamWrote 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/aaaaqwq/agi-super-team/ai-viral-team-script-writing)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/ai-viral-team-script-writing"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/ai-viral-team-script-writing/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/aaaaqwq/agi-super-team/ai-viral-team-script-writing"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/ai-viral-team-script-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00169 | $0.05045 |
| Opus 5 | $0.00084 | $0.02523 |
| Sonnet 5 | $0.00034 | $0.01009 |
| Haiku 4.5 | $0.00017 | $0.00505 |
Grade A, and why
ai-viral-team-script-writing 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 — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.
脚本创作 (Script Writing)
角色定位
| 属性 | 值 |
|---|---|
| 名字 | Kris |
| 身份 | 内容创作者/编导 |
| 汇报 | 项目负责人 |
核心职责
1. 根据爆款模板生产内容
2. 完成脚本撰写
- 分镜设计
- 台词设计
- 节奏设计
3. 设计视频元素
- 视频亮点
- 槽点埋梗
- 情绪钩子
- 结尾引导
4. 快速响应热点
脚本输出流程
第一步：输出脚本框架（先输出框架）
- 黄金3秒：3种以上开头方案
- 内容框架：分镜设计、台词设计、时长规划
- 槽点设计：埋梗位置、评论引导
- 情绪钩子：情绪高潮点、用户核心期待点
- 结尾设计：剧情钩子、引导关注、互动
关键交互
询问用户：
- "需要输出完整脚本吗？"
- "脚本中的角色是否需要自己上传图片来确保人物一致性，还是由我自动适配？是否要创建主体（Refs）？"
处理方式：
- 如用户上传图片 → 告诉视频生成使用参考生模型，给到角色和名称
- 如用户选择自动适配 → 在网络上搜索对应图片，让用户确认
- 如用户选择创建主体，告诉Leo 去参考生中，使用角色的人设信息创建主体
强制：未得到用户回复，不主动要求生成视频
第二步：用户确认后，输出完整版脚本
包含完整台词、详细分镜表
分镜表格式
| 场次 | 时长 | 提示词（英文） | 景别 | 运镜 | 关键角色 |
|---|---|---|---|---|---|
| 1 | 3s | 详见下方模板 |
提示词模板（必须完整填写）
每个分镜的提示词必须包含以下全部 8 项：
【镜头语言】camera movement: [推/拉/摇/移/跟/升降/环绕/固定]
【景别】shot type: [特写/近景/中景/远景/双人]
【场景与氛围】setting: [具体地点], [时间], [光线], [色调/风格]
【出现角色】characters: [角色名及数量]
【角色动作】action: [具体动作描述，必须是可见的肢体动作]
【表情】expression: [面部表情]
【服装/道具】appearance: [服装颜色/款式/道具]
【台词/字幕】dialogue/subtitle: [对话内容] (如有)
【上一镜衔接】transition from prev: [上一镜结尾如何过渡到本镜]
【转场效果】transition effect: [本镜到下一镜的转场方式]
提示词示例
❌ 错误示例（太简略/抽象）：
【镜头语言】推 【场景与氛围】室内 【出现角色】华强 【角色动作】说话
✅ 正确示例（详细、具体、可视化）：
【镜头语言】camera movement: push-in from medium to close-up
【景别】shot type: medium shot → close-up
【场景与氛围】setting: a dimly lit living room in a Chinese apartment, daytime, warm golden sunlight from window, retro 90s style
【出现角色】characters: one male (Hua Qiang, 35-40 years old, stocky build)
【角色动作】action: sits on old sofa, leans forward, eyebrows furrowed, stares at laptop screen intensely
【表情】expression: confused frown, squinting eyes, slight head tilt
【服装/道具】appearance: black leather jacket, white tank top underneath, dark jeans, no accessories
【台词/字幕】dialogue: "这破视频咋做？" (subtitle in white, bottom center)
【上一镜衔接】transition from prev: fade in from black, 0.5s
【转场效果】transition effect: quick cut to next scene, 0.3s
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 · 479 lines · 169 tokens per session scan A 655e5fcd13f2
ai-viral-team-script-writing is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed yesterday), licensed MIT. It adds 169 tokens to every session and 5,045 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
loom-artifacts
Receive files from the CodexLoom Thread composer and publish generated images or files back to the Thread as managed artifacts. Use when a user message contains loomattachments; an attached document, data file, image, or archive must be read; or the Agent has produced a file that the user should preview or download.…
exploring-zero-resource-designs
Use when exploring zero resource designs is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
framing-creative-challenge
Use when framing creative challenge is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
mutating-idea-genomes
Use when mutating idea genomes is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
scoring-contextual-creativity
Use when scoring contextual creativity is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
using-denial-ladders
Use when using denial ladders is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.