video-prompting
Draft and refine prompts for video generation models (text-to-video and image-to-video). Use when a user asks for a "video prompt" or a model-specific prompt such as Ovi, Sora, Veo 3, Wan 2.2, or LTX-2, including requests like "text-to-video prompt", "image-to-video prompt", or "write a prompt for [model]".
When & Why to Use This Skill
This Claude skill provides expert-level drafting and refinement of prompts for state-of-the-art video generation models like Sora, Veo 3, Wan 2.2, and LTX-2. It bridges the gap between creative intent and technical execution by applying model-specific formatting, tokens, and motion guidance for both text-to-video and image-to-video tasks, ensuring high-quality cinematic results.
Use Cases
- Generating high-fidelity text-to-video prompts tailored for specific AI models such as Sora, Veo, or Wan 2.2 to ensure optimal visual output.
- Transforming static images into dynamic video sequences (i2v) by defining consistent motion, lighting, and camera transitions while maintaining subject identity.
- Optimizing creative workflows by automatically applying model-specific technical constraints, including required tokens, duration parameters, and structural formatting.
- Refining vague creative concepts into structured, multi-beat action descriptions that guide AI models through complex visual progressions.
| name | video-prompting |
|---|---|
| description | Draft and refine prompts for video generation models (text-to-video and image-to-video). Use when a user asks for a "video prompt" or a model-specific prompt such as Ovi, Sora, Veo 3, Wan 2.2, or LTX-2, including requests like "text-to-video prompt", "image-to-video prompt", or "write a prompt for [model]". |
Video Prompting
Overview
Turn a user’s intent into a strong, model-compliant video prompt by routing to the correct model guide and applying its formatting/tokens.
Model-specific guidance lives in references/models/. This file is the entry point: pick the model, ask the minimum clarifying questions, then draft the prompt in that model’s expected format.
Model Index
- Ovi:
references/models/ovi/prompting.md - Sora (Sora 2):
references/models/sora/prompting.md - Veo 3 / 3.1:
references/models/veo3/prompting.md - Wan 2.2:
references/models/wan22/prompting.md - LTX-2:
references/models/ltx2/prompting.md
To add a new model later: create references/models/<model>/prompting.md, then add it to this index.
Workflow
Step 1 — Identify the model and input mode
If the user did not name a model, ask which model they are using (or offer supported options from the Model Index).
Then confirm the input mode:
- Text-to-video (t2v), or
- Image-to-video (i2v)
If i2v: ask the user to share the image (optional, but it will help you generate a better prompt). Use the image as an anchor according to the chosen model’s guidance (e.g., keep identity/wardrobe/composition stable; focus your text on motion/camera/what changes).
If the chosen model has versions, duration constraints, or required parameters, ask the minimum questions needed to select the right format (see the model guide).
Step 2 — Load the model reference and follow its format
Open the model’s prompting.md from the Model Index and follow its rules strictly (tokens, audio formatting, parameter constraints, recommended structure).
Step 3 — Draft the prompt as a coherent clip
Default structure (adapt to the model’s style and required sections):
- Subject(s): who/what, distinctive details
- Setting: where/when, lighting, mood
- Action progression: what changes over time (start → beat → beat → end)
- Camera: framing/movement only if it matters
- Dialogue/audio: only if the model supports it, using the model’s exact format
Avoid keyword soup. Prefer a single, well-described shot unless the user explicitly wants multiple cuts/shots.
Step 4 — Output
Default: output only the final prompt text.
If the user asks for options: provide 2–3 distinct prompt variants, each fully self-contained and compliant with the model’s formatting.
If the model uses required API parameters (e.g., duration/size), include a short “Recommended parameters” line only when the user has specified them or explicitly asks for them.