Video Prompting skill
Draft model-specific video prompts and consistent-character reference sheets.
Community · Square Zero Labs| Author | Square Zero Labs |
|---|---|
| Licence | Apache-2.0 |
| Source | Square-Zero-Labs/video-prompting-skill · SKILL.md on GitHub |
| Works in | Claude Code · Codex, Gemini CLI, Cursor, Copilot |
| Read from the source on |
The video-prompting skill drafts prompts for a selected video model and input mode.
It also creates character-sheet prompts before reference-driven image-to-video work.
From the skill's SKILL.md: # Video Prompting
What it does
- Routes the request to a model or character-sheet guide.
What you get
- Final prompt text or self-contained variants.
When to use it
- Plan a shot for an external generator.
When not to use it
- Rendering or purchasing video generation.
What it needs
- An instruction-reading agent; generation requires a separate model or service.
Files in the skill
| File or folder | What it is for |
|---|---|
SKILL.md | Entry-point instructions and workflow routing. |
references/ | Model-specific formats and character-sheet workflow. |
Licence as found in the repository on 2026-11-16: Apache-2.0.
Example prompts
Type one of these after installing; naming the skill makes sure it is used.
- Write a Veo prompt for this shot.
- Create a consistent-character sheet prompt.
- Refine this image-to-video camera move.
How to install video-prompting
Prepare the workflow
Copy the full folder so model and character references remain available. This page offers local agent installation; cloud execution is not independently verified.
A skill is a folder with a SKILL.md file. You install it once; the agent reads its short description at the start of each session and loads the full instructions only when a request matches. Pick the place you use:
Claude Code: copy the folder into your skills folder
Put the skill's folder in ~/.claude/skills/ to use it in every project on this computer, or in .claude/skills/ inside a repository to share it with everyone who works there (commit it).
git clone --depth 1 https://github.com/Square-Zero-Labs/video-prompting-skill.git
mkdir -p ~/.claude/skills
cp -R video-prompting-skill/video-prompting ~/.claude/skills/Claude Code notices new or changed skills in these folders during the session. If the skills folder did not exist when the session started, run /reload-skills once. Then type /video-prompting or just describe the task.
On Windows, run the commands in Git Bash or WSL, or copy the folder into the same place with File Explorer.
Codex, Gemini CLI, Cursor and GitHub Copilot
These agents read the same SKILL.md folders. The one folder all four accept inside a project is .agents/skills/, so this copies the skill there:
git clone --depth 1 https://github.com/Square-Zero-Labs/video-prompting-skill.git
mkdir -p .agents/skills
cp -R video-prompting-skill/video-prompting .agents/skills/| Agent | Project folder | Your user folder | Notes |
|---|---|---|---|
| OpenAI Codex | .agents/skills/ | ~/.agents/skills/ | Type $ or run /skills to pick a skill; Codex also chooses one when your task matches. |
| Gemini CLI | .agents/skills/.gemini/skills/ | ~/.agents/skills/~/.gemini/skills/ | Or install from Git with gemini skills install <git URL> --path <folder> --consent. Google replaced Gemini CLI with Antigravity CLI for free-tier and Google One users on 18 June 2026; Antigravity uses .agents/skills/ in a project and ~/.gemini/config/skills/ for you. |
| Cursor | .agents/skills/.cursor/skills/ | ~/.agents/skills/~/.cursor/skills/ | Type / in Agent chat to pick a skill. Cursor also reads Claude Code's .claude/skills/ folders. |
| GitHub Copilot | .github/skills/.agents/skills/.claude/skills/ | ~/.copilot/skills/~/.agents/skills/ | Works in Copilot CLI, the cloud agent, and agent mode in VS Code, Visual Studio and JetBrains (IDE support depends on the version). Or run gh skill install OWNER/REPOSITORY SKILL (public preview, GitHub CLI 2.90.0 or later). |
Sources for these steps
Checked against each vendor's documentation on 2026-11-14:
Separate shots from settings
Duration, size and model selection normally belong in generator controls, preserving the prompt for scene content.
Use the selected guide
Reference and dialogue workflows have different constraints. Follow the intended model guide rather than blending incompatible syntax.
Questions about video-prompting
Does it generate video?
No. It writes prompts.
Does every model use one format?
No. Each model guide defines its format.
Should settings go inside the prompt?
Usually not; model-specific timing schemas are exceptions.
Can it prepare character consistency?
Yes. It includes character-sheet and follow-on shot prompts.
More AI skills
Related skills
Vox Director skill
Community · Alisa0808Direct narrated editorial collage videos using Atlas Cloud and local assembly.Papercut Explainer skill
Community · 0xS4N4TGPlan and build vertical paper-cut explainers through staged, resumable production.YouTube Transcript skill
Community · michalparkolaRetrieve available captions, then optionally transcribe audio when subtitles are absent.Remotion FFmpeg skill
Community · kajisho5Add measured motion graphics, captions and jump cuts to real footage.Motion Film skill
Community · arhenCoordinate branded motion films with a shared clock, design system and delivery checks.Claude Real Video skill
Community · HUANGCHIHHUNGLeoExtract scene-aware frames and speech for evidence-based video discussion.