Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

AI Video Model Selector

Asks 3-4 targeted questions about your video needs, then recommends the best 1-3 of 16 AI video models with clear reasoning.

Image & VideoBeginner★ 413⑂ 93AI score 9/10Last updated: Oct 7, 2026

What it does

  • Puts 16 AI video models side by side — commercial ones (Seedance 2.0, Kling 3.0, Sora 2, Veo 3.1, Gemini Omni, Runway Gen-4/Aleph, Pika 2.5, Hailuo 02, Wan 2.7, Jimeng AI) and open-source ones (Hunyuan Video 1.5, LTX-Video, Mochi 1, CogVideoX) — in a capability matrix covering Chinese-language handling, native audio, physics, editing, duration and regional availability.
  • Asks only the 3-4 questions that actually change the answer (length, audio, language, new generation vs. editing existing footage, platform/region, local deployment), then walks a decision tree.
  • Returns a fixed output format: best pick + reasoning + fallback option + links to the matching prompter skill, methodology file, and official platform.
  • States explicitly when NOT to use it (model already chosen, prompt writing, prompt debugging).

Who it's for

  • Short-form and ad creators unsure which paid AI video tool deserves their budget.
  • Video production teams that must match client requirements (dialogue, lip-sync, exact duration) to a model fast.
  • Engineers evaluating open-source video models and LoRA training on a local GPU.

Examples

  1. "10-second modern-city drama scene in Chinese with dialogue" → Kling 3.0 as best pick, Wan 2.7 / Jimeng 3.0 as fallbacks.
  2. "I have a clip and want it restyled as watercolor animation" → Runway Aleph, plus a ready-to-use re-style prompt that preserves motion and timing.
  3. "RTX 4090 24GB, want to train my own LoRA" → Hunyuan Video 1.5 with recommended GGUF quant, steps, sampler, CFG and ComfyUI links.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/cclank/lanshu-awesome-ai-video-kit/HEAD/skills/model-selector/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/model-selector folder from the GitHub repo cclank/lanshu-awesome-ai-video-kit into my ~/.claude/skills/model-selector/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/cclank/lanshu-awesome-ai-video-kit.git && mkdir -p ~/.claude/skills && cp -r lanshu-awesome-ai-video-kit/skills/* ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal (Terminal on macOS, Git Bash or WSL on Windows).
  2. Clone the repo: git clone https://github.com/cclank/lanshu-awesome-ai-video-kit.git.
  3. Create the skills folder if needed: mkdir -p ~/.claude/skills.
  4. Copy the skills over: cp -r lanshu-awesome-ai-video-kit/skills/* ~/.claude/skills/. To also use the methodology/ documents the skill links to, keep the cloned repo inside your working project.
  5. Restart Claude Code and ask something like "Which AI video model should I use for this?" to trigger the skill.
  6. Once a model is recommended, continue with the matching *-prompter skill from the same repo to write the actual prompt.
View source on GitHub ↗License: MIT