Vivideo APITools & SDKs
Agent Skills
Skills are short instruction files that teach an AI agent how to use Vivideo correctly — which tool to call, in what order, how to wait, and how to handle errors. They ride on top of the MCP tools, the CLI, or the API.
i
A skill doesn't do anything by itself. It's a playbook the agent loads when the task matches, so it uses the real tools reliably — no invented parameters, proper retries and idempotency, and it never claims a video is done before the API confirms it.
Install
Skills are plain folders (each a SKILL.md). Copy the ones you want into your agent's skills directory — for Claude, ~/.claude/skills/ or a project .claude/skills/:
# from the toolchain repo
git clone https://github.com/egocen-vivideo/vivideo-toolchain
cp -r vivideo-toolchain/skills/* ~/.claude/skills/They assume the Vivideo MCP server is connected (or the CLI is installed) and a VIVIDEO_API_KEY is configured.
The skills
| Skill | Use it when |
|---|---|
generate-video-from-prompt | Make a video from a text prompt (the canonical workflow). |
create-branded-video | The video must match a company/brand (brand kit). |
create-avatar-voice-video | A specific presenter/avatar and voice are requested. |
create-manual-video | A specific model, image-to-video, or precise controls. |
check-credits-before-generating | Before any creation — confirm premium + credits. |
wait-for-video-safely | Track a render to completion without over-polling. |
handle-limits-and-errors | Any error: rate limits, credits, premium, duplicates. |
avoiding-duplicate-generations | Retryable/automated creates — avoid double charges. |
troubleshoot-failed-generations | A generation failed or seems stuck. |
✓
Best paired together. Connect the MCP server and add these skills, and an assistant can go from “make me a 20-second product video” to a finished MP4 — checking credits, avoiding duplicates, and waiting properly along the way.
Machine-readable: interactive reference · openapi.yaml · llms-api.txt. Base URL
https://api.vivideo.ai.