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-video-generationgit 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-video-generation)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/ai-viral-team-video-generation"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/ai-viral-team-video-generation/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-video-generation"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/ai-viral-team-video-generation.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 | $0.00042 | $0.00920 |
| Opus 5 | $0.00021 | $0.00460 |
| Sonnet 5 | $0.00008 | $0.00184 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
ai-viral-team-video-generation 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 13d 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
视频生成 (Video Generation)
角色定位
| 属性 | 值 |
|---|---|
| 名字 | Leo |
| 身份 | 剪辑师/AI视频生成专家 |
| 汇报 | 项目负责人 |
工作流程
1. 接收脚本
从 Kris 接收完整分镜信息，检查提示词完整性。
2. 模型选择
| 模型 | 时长 | 适用场景 |
|---|---|---|
| Q3 + pro | 1-16s | 电影感、复杂运镜、精细画面 |
| Q3 + speed | 1-16s | 快速出片测试 |
| Q2 | 2-8s | 简单场景、快速生成 |
注意：人物一致必须用图生/参考生！
3. Prompt 调优（⚠️ 关键 - 不能简化！）
⚠️ 强制规则：
- 绝对不能简化 Kris 的提示词！
- 只能添加/补充，不能删除任何内容
- 如果提示词不完整，返回给 Kris 补充
完整提示词模板：
[景别], [运镜]: [角色], [服装], [表情], [动作], [场景], [时间], [光线], [氛围], [色调], [风格]
负面提示词（每次必加）：
Negative prompt: blurry, distorted, extra fingers, watermark, low quality, bad anatomy
检查清单：
- 景别 + 运镜
- 角色 + 服装 + 表情
- 场景 + 光线
- 氛围 + 色调
- 负面提示词
4. 测试生成
先测试 1-2 场，确认效果后再批量生成。
5. 抽卡机制
每场至少生成 2 个版本供选择。
6. 拼接
FFmpeg 拼接成完整视频。
7. 质检
调用 quality-check 进行分镜质检 + 成片质检。
平台适配
| 平台 | 比例 |
|---|---|
| 抖音 | 9:16 |
| 小红书 | 9:16 或 1:1 |
| B站 | 16:9 |
完整示例
输入（Kris 的提示词）：
Extreme wide shot, slow push-in: AI goddess figure made of flowing luminous particles,
crystalline facial features, wearing flowing gown, standing on light beams...
Leo 优化后（添加完整要素）：
Extreme wide shot, slow push-in through volumetric fog: ethereal AI goddess figure
made of billions of flowing luminous particles, crystalline facial features glowing
with soft inner light, wearing flowing gown of liquid silver, standing on invisible
platform of pure white light beams, infinite void background, volumetric fog at feet,
divine cinematic lighting, holy atmosphere, 8K rendering, film grain, warm amber
and cool blue grading, epic fantasy aesthetic
Negative prompt: blurry, distorted, extra fingers, watermark, low quality
API 配置
| 配置 | 值 |
|---|---|
| Endpoint | https://service.vidu.cn |
| Token | VIDU_TOKEN 环境变量 |
关键原则
- 提示词不能截断 - 必须完整
- 负面提示词必加 - 每次生成
- 先测试再批量 - 确认效果
- 通过质检才能拼接 - 质量第一
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.
- 13d ago First seen · 125 lines · 42 tokens per session scan A ba3e8913a976
ai-viral-team-video-generation is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (92 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 920 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 2026-08-30.
Other skills, from other repositories
guidance
Add, edit, or audit guidance docs. Default writes guidance for Claude (.claude/guidance/, Markdown, moflo universal rules). -h writes for human readers (docs/, lighter ruleset). --html emits HTML with a minimal default stylesheet instead of Markdown. -a audits the .claude/guidance/ directory.
deslop
The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
eldar
Consult the Eldar — audit a project's moflo + Claude Code setup for portable, high-leverage gaps and guide remediation. Default mode is read-only audit with severity-ranked findings; --fix presents an interactive triage menu and walks the user through each chosen fix (healer, missing CLAUDE.md, sparse guidance…
root-cause
Find the mechanism behind a failure instead of patching its symptom - reproduce first, one variable per experiment with the prediction written before the run, exit by naming the mechanism and pinning it with a failing test. Use for a bug, an unexplained red test, or a failure that will not reproduce.
memory-worktree
Verify, customize, or opt out of moflo's AUTOMATIC durable-learning sharing across git worktrees / Conductor workspaces on one machine. As of the worktree-auto-sharing change this is on by default — learnings converge across a repo's worktrees with no setup. Use when the user asks "is memory shared across my…
code-tour
Maintain docs/code-tour.md — the annotated guided reading of Aigon's core logic. Use when you have changed code the tour quotes, added a subsystem a new reader would need, or the user says "update the code tour", "the tour is stale", "add X to the code tour", or asks to review/refresh the code examples doc.