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.
git clone --depth 1 https://github.com/cclank/lanshu-awesome-ai-video-kitnpx agentmods add skills/cclank/lanshu-awesome-ai-video-kit/model-selectorWrote 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/cclank/lanshu-awesome-ai-video-kit/model-selector)<a href="https://agentmods.dev/skills/cclank/lanshu-awesome-ai-video-kit/model-selector"><img src="https://agentmods.dev/badge/skills/cclank/lanshu-awesome-ai-video-kit/model-selector/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/cclank/lanshu-awesome-ai-video-kit/model-selector"><img src="https://agentmods.dev/badge/skills/cclank/lanshu-awesome-ai-video-kit/model-selector.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 | $0.00257 | $0.02529 |
| Opus 5 | $0.00129 | $0.01264 |
| Sonnet 5 | $0.00051 | $0.00506 |
| Haiku 4.5 | $0.00026 | $0.00253 |
Grade A, and why
model-selector 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.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
model-selector
15 个主流 AI 视频模型(11 商业 + 4 开源)的"购物顾问"。问用户 3-4 个关键问题,给出推荐 + 理由。
何时不用此 skill
- 用户已经确定要用某个模型 → 用对应的
<model>-prompterskill - 用户问"提示词怎么写" → 用
seedance-prompter/kling-prompter/happyhorse-prompter - 用户的提示词不工作 → 用
seedance-debugger
11 模型能力速查矩阵
| 模型 | 中文 | 音频 | 物理 | 编辑 | 时长 | 开源 | 国内可用 | 主战场 |
|---|---|---|---|---|---|---|---|---|
| Seedance 2.0 | ★★★ | — | ★★★ | — | 15s | — | ✓ | 电影叙事 |
| HappyHorse 1.0 | ★★★ | ★★ | ★★ | — | 15s（默认 5s） | — | ✓ | ASMR / 短片 |
| Kling 3.0 | ★★★★★ | ★★★★ | ★★★★ | ✓ | 2m | — | ✓ | 中文剧情 / 图生视频 |
| Sora 2 | ★★ | ★★★★ | ★★★★★ | — | 25s (Pro) | — | △ | 电影艺术片 |
| Veo 3.1 | ★★ | ★★★★★ | ★★★ | — | 148s chained | — | △ | 多人对话 |
| Gemini Omni ⭐NEW | ★★ | ★★★ | ★★★ | ★★★★★ | 待定 | — | △ | 迭代编辑 / 文字渲染 / 跨模态 |
| Runway Gen-4 | ★★★ | — | ★★★ | ★★★★★ | 30s | — | ✓ | 视频编辑 |
| Pika 2.5 | ★★ | ★ | ★★ | — | 25s | — | ✓ | 创意特效 |
| Hailuo 02 | ★★★ | — | ★★★★★ | — | 10s | — | ✓ | 物理动作 |
| Hunyuan 1.5 | ★★★★ | — | ★★★ | ✓ | 10s | ★★★★★ | ✓ | 开源 / LoRA |
| Wan 2.7 | ★★★ | ★★★★★ | ★★★ | ✓ | 15s | — | ✓ | 数字人 lip-sync |
| 即梦 3.0 | ★★★★★ | ★★ | ★★★ | — | 15s | — | ✓ | 中文 + 剪映集成 |
工作流程
步骤 1：问 3-4 个关键问题
不要全部问，挑最影响结果的 3-4 个：
| 维度 | 问题 |
|---|---|
| 时长 | "需要多长？5 秒 / 10 秒 / 15 秒以上？" |
| 音频 | "要原生音频吗？只要环境音 / 要对白 / 要 BGM / 不要" |
| 语言 | "是中文场景还是英文场景？" |
| 编辑性质 | "全新生成还是编辑已有视频？" |
| 平台限制 | "国内可用 / 国际可用 / 本地部署？" |
| 用途 | "短视频爆款 / 影视级 / 商业广告 / 个人创作？" |
步骤 2：按决策树推荐
是编辑已有视频？
├── Yes → Runway Aleph（独家）
└── No → 继续
├── 要数字人/真人对口型？
│ └── Yes → Wan 2.7（业界最准）
├── 要多人对话+精确配乐？
│ └── Yes → Veo 3.1
├── 中文剧情/中式美学？
│ └── Yes → 即梦 3.0（创作者） / Kling 3.0（开发者 API）
├── 极致物理感（水/火/动作）？
│ └── Yes → Hailuo 02 > Sora 2
├── 创意爆款特效（变身/融化）？
│ └── Yes → Pika 2.5（Pikaffects）
├── 本地部署/开源/LoRA 训练？
│ └── Yes → Hunyuan 1.5
├── 极致电影质感/艺术片？
│ └── Yes → Sora 2 > Runway Gen-4
├── 5/10/15 秒紧凑短片 + 环境音？
│ └── Yes → HappyHorse 1.0
└── 复杂多镜头叙事？
└── Yes → Seedance 2.0 / Kling 智能分镜
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 · 167 lines · 257 tokens per session scan A fc6cbc5fd033
model-selector is a skill published in the GitHub repository cclank/lanshu-awesome-ai-video-kit (391 stars, last pushed 3mo ago), licensed MIT. It adds 257 tokens to every session and 2,529 once invoked, about $0.0013 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
video-shotcraft
Create cinematic product videos from shot recipe cards, a validated template, and code/audio assets (Remotion + real page screenshots + 2.5D camera moves + beat-synced cuts + sound design). Use when the user asks to turn a frontend project or webpage into a product video, says "use video-shotcraft to make a…
cassette-video-edit
Edit, trim, cut, caption, subtitle, reframe, combine, add background music to, or export video, audio, and image files through Cassette. Use this skill whenever the user asks to change, preview, or render a media file in the project — even if they never say "Cassette" or name a tool — for example "trim the intro off…
seo-image-gen
AI image generation for SEO assets: OG/social preview images, blog hero images, schema images, product photography, infographics. Powered by Gemini via nanobanana-mcp. Requires banana extension installed. Use when user says "generate image", "OG image", "social preview", "hero image", "blog image", "product photo"…
vidseeds-setup
Use when connecting to VidSeeds.ai, getting AUTHREQUIRED or SUBSCRIPTIONREQUIRED from the vidseeds MCP server, or setting up VIDSEEDSPAT / OAuth for the connector. Not for workflow recipes - use vidseeds-efficiency and domain skills after connect.
vidseeds-local-video
Use when the user's video is on disk - VidSeeds MCP probe, frame/clip extraction, ffmpeg recipes, precision trim, and midroll analysis. Hosted tools return commands/recipes to run locally; media stays on the user's machine.
vidseeds-projects
Use for VidSeeds MCP project workflows - create a project from YouTube, list/get/snapshot, regenerate metadata (sync or async), translate metadata, apply thumbnails, and update per-platform config before publish.