Use AI product video generation from a coding assistant to turn a creative brief or approved image into video clips. This Skill explains inference.sh workflows through the belt command-line tool, helping the assistant choose an input method, prepare a model-specific request and run generation through your authenticated service account.
The Skill supplies instructions for using external video models, including text, image, reference and editing workflows. It helps bridge the gap between a video brief and a runnable service request, rather than providing a video editor inside this page.
Before starting, install the belt CLI, authenticate the inference.sh account and prepare media you have permission to use. The assistant can then follow the relevant example to generate a clip. Available models, usage limits and charges are controlled by the service and should be checked before submitting a job.
Model-specific examples make the input differences visible: some workflows begin with a written scene, while others need an image or reference media. Pick the workflow around the asset you already have and the change you want to make.
The assistant can prepare and execute command-line generation requests once the external account and CLI are ready. Keep generated clips in the normal creative review process, especially when product appearance or demonstrated use must match the merchandise.
A compatible agent, installed belt CLI, authenticated inference.sh account, prompts, and rights-cleared media.
Use a compatible agent that can discover the installed Skill and read its supporting files. Any external service or creative runtime must be configured separately.
Installing the Skill does not install or authenticate the CLI. Models, availability, limits, and usage charges belong to the external service and need checking before a run.
Copy this request into Codex or Claude Code. The assistant downloads the original repository at the specified commit, installs the complete files and checks required dependencies.
Install ai-video-generation in the app I am using and carry out the file installation, not just explain it.
Original repository: https://github.com/inference-sh/skills.git
Commit: 0cbf91c26ada28702c79962406286f0c14292150
Skill folder: tools/video/ai-video-generation
1. Download this exact source into a new directory. Read SKILL.md and its setup references before running any bundled scripts. Do not substitute another author’s package.
2. For Codex, use ~/.agents/skills/ai-video-generation; for Claude Code, use ~/.claude/skills/ai-video-generation. Install only for my current app. Install the complete Skill folder, including scripts, references, assets and bundled notices. Keep any root license with the installed folder. Check all destination folders first; if any already exist, report differences before replacing them.
3. Compare the source and installed file lists and hashes. Inspect documented runtimes, dependencies and required connections. Configure only the local dependencies needed for this Skill; use an isolated environment when appropriate. Ask me to complete any account login locally, without putting credentials in chat.
4. Report the source commit, actual installation path, file-check results and any remaining runtime setup. Explain how to invoke ai-video-generation in this app. Check discovery separately from file copying; start a new session if needed. Do not run production tasks or claim a successful business outcome from installation alone.Starter prompts for the main use cases—copy and use them directly.
Draft and run a short text-to-video product concept Use for: Draft and run a short text-to-video product concept. Prepare: A compatible agent, installed belt CLI, authenticated inference.sh account, prompts, and rights-cleared media.
Use the installed ai-video-generation Skill. Task: Draft and run a short text-to-video product concept. Inputs: [INPUT]. Constraints: [CONSTRAINTS]. Check missing information first. Produce a reviewable result with evidence, assumptions, and next steps. Installing the Skill does not install or authenticate the CLI. Models, availability, limits, and usage charges belong to the external service and need checking before a run.[INPUT][CONSTRAINTS]Animate an approved product reference image Use for: Animate an approved product reference image. Prepare: A compatible agent, installed belt CLI, authenticated inference.sh account, prompts, and rights-cleared media.
Use the installed ai-video-generation Skill. Task: Animate an approved product reference image. Inputs: [INPUT]. Constraints: [CONSTRAINTS]. Check missing information first. Produce a reviewable result with evidence, assumptions, and next steps. Installing the Skill does not install or authenticate the CLI. Models, availability, limits, and usage charges belong to the external service and need checking before a run.[INPUT][CONSTRAINTS]Compare model input requirements before a video-editing task Use for: Compare model input requirements before a video-editing task. Prepare: A compatible agent, installed belt CLI, authenticated inference.sh account, prompts, and rights-cleared media.
Use the installed ai-video-generation Skill. Task: Compare model input requirements before a video-editing task. Inputs: [INPUT]. Constraints: [CONSTRAINTS]. Check missing information first. Produce a reviewable result with evidence, assumptions, and next steps. Installing the Skill does not install or authenticate the CLI. Models, availability, limits, and usage charges belong to the external service and need checking before a run.[INPUT][CONSTRAINTS]Installing the Skill does not install or authenticate the CLI. Models, availability, limits, and usage charges belong to the external service and need checking before a run.
Source and package files reviewed: GitHub 0cbf91c26ada. This is a static review, not an installation or business-outcome test.
Use authorized inputs and keep secrets out of prompts. Review customer-facing claims, calculations, code changes, and any proposed external action before applying them.
Guide an agent to generate videos through inference.sh using the belt CLI. The instructions give model-specific examples for text, image, reference, and editing workflows.
Choose the method for your agent and install the complete package, not just the displayed SKILL.md. A compatible agent, installed belt CLI, authenticated inference.sh account, prompts, and rights-cleared media. Start a new agent session and explicitly ask to use ai-video-generation. Try one use case below with a small sample and review the output.
Draft and run a short text-to-video product concept; Animate an approved product reference image; Compare model input requirements before a video-editing task
Installing the Skill does not install or authenticate the CLI. Models, availability, limits, and usage charges belong to the external service and need checking before a run.
Source and package files reviewed: GitHub 0cbf91c26ada. This is a static review, not an installation or business-outcome test.
Source and package files reviewed: GitHub 0cbf91c26ada. This is a static review, not an installation or business-outcome test.
Source and package files reviewed: GitHub 0cbf91c26ada. This is a static review, not an installation or business-outcome test.
No reviews yet.