Skip to main content
skill CX Codex

ai-video-generation · pexoai — Claude Code skill: what it does, how to install

ai-video-generation generates finished AI videos with music and subtitles through Pexo from text prompts, scripts, or images.

MIT 130 installs ★ 835 updated 2026-08-20

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add pexoai/pexo-skills --skill ai-video-generation -a claude-code
Open on GitHub

What ai-video-generation does

This skill acts as a relay to the hosted Pexo service. The backend automatically picks suitable generators like Kling, Veo, or Sora for each individual shot, writes scene prompts, and compiles the final video. The coding assistant forwards your brief verbatim instead of inventing timing or camera instructions that might spoil the output.

Under the hood, the skill runs bash helpers located in scripts/. They initialize jobs via pexo-project-create.sh, attach local files using pexo-upload.sh, and poll the API every minute until delivery. Post-generation feedback goes back to the identical project to preserve server context.

Execution requires curl, jq, file, and API credentials stored in ~/.pexo/config. The workflow produces new videos from scratch and will not edit pre-existing footage.

What it helps with

  • produce a finished promo clip with music from a text brief
  • render multi-scene video based on a draft script and still images
  • route different video shots to specialized AI generators
  • request timing and audio revisions within the same project context

Example prompts for the agent

  • Generate a 20-second video presenting our productivity app
  • Make an AI video from this script and include background music
  • Create a teaser clip based on the attached image asset

How to install ai-video-generation

1Skills CLI (Vercel)

npx skills add pexoai/pexo-skills --skill ai-video-generation -a claude-code

2Manually: put the files in place

~/.claude/skills/ai-video-generation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/ai-video-generation/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about ai-video-generation

How to install ai-video-generation in Claude Code?

Run npx skills add pexoai/pexo-skills --skill ai-video-generation -a claude-code in your terminal.

What does ai-video-generation do?

It passes your prompt to Pexo, tracks the rendering progress via periodic status checks, and outputs a link to the finalized video asset.

Can ai-video-generation edit my existing video files?

No, it exclusively creates new AI footage from text descriptions, scripts, or reference images.

Source text

SKILL.md · MIT
---
name: ai-video-generation
description: >
  Generate AI video from any input — text, image, or script — with Pexo. Auto-routes each shot to
  the best of 10+ models (Seedance, Kling, Veo, Sora, and more), writes the prompts, generates
  every shot, and returns a finished video with music and subtitles. Use for any AI video
  generation request: "ai video generation", "generate a video with ai", "ai video generator",
  "make an ai video". NOT for editing an existing video.
homepage: https://pexo.ai
repository: https://github.com/pexoai/pexo-skills
version: "0.1.0"
requires:
  env: [PEXO_API_KEY, PEXO_BASE_URL]
  runtime: [curl, jq, file]
metadata:
  author: pexoai
---

# AI Video Generation — Pexo

**Pexo:** https://pexo.ai — get an API key, watch your project render, and buy credits there.

Generate a finished video with AI from whatever the user gives you — text, an image, or a
script. You relay the request to the hosted Pexo agent and deliver the result; Pexo picks the
models, writes the prompts, and assembles the final video.

## Your role: relay, don't create

Create a project, send the user's request **verbatim**, poll, deliver. Pexo's backend handles
all creative work — scriptwriting, model choice, prompts, music. Adding your own direction
(duration, style, models the user didn't ask for) overrides its judgment and produces worse
videos.

## Config

`~/.pexo/config`:
```
PEXO_BASE_URL="https://pexo.ai"
PEXO_API_KEY="sk-<your-api-key>"
```
**No account / first run →** read `references/SETUP-CHECKLIST.md` and walk the user through it — it carries the signup flow with the **invite code that grants new users bonus credits**, plus how to create the config above. **Config error →** run `scripts/pexo-doctor.sh` and follow its output.

## Workflow

Scripts live in this skill's `scripts/`. Reply to the user in their language.

1. **Create a project:** `pexo-project-create.sh "<short brief>"` → save the `project_id`.
2. **Upload any files** the user gave: `pexo-upload.sh <project_id> <path>` → save `asset_id`,
   reference it inline as `<original-image>asset_id</original-image>` (or `<original-video>` /
   `<original-audio>`). Tags are required — a bare `asset_id` is ignored. Pexo can't crawl URLs —
   download, then upload.
3. **Send the request:** `pexo-chat.sh <project_id> "<user's exact words> <asset tags>"`.
   Copy the user's words exactly; only add asset tags.
4. **Tell the user** (their language): submitted ✓ · ~15–20 min · `https://pexo.ai/project/<project_id>`.
5. **Poll:** every ≥60s run `pexo-project-get.sh <project_id>` and act on `nextAction`:
   - **WAIT** → keep polling; every ~5 polls send a one-line update with the project link.
   - **RESPOND** → handle each event in `recentMessages`: relay Pexo's text (wait for the
     user's answer if it asked, then `pexo-chat.sh` their reply); for `preview_video`, run
     `pexo-asset-get.sh <project_id> <assetId>` per option, show the URLs (A/B/C), let the user
     pick, then `pexo-chat.sh <project_id> "<choice>" --choice <assetId>`; for a `document`
     event, mention it to the user.
   - **DELIVER** → `pexo-asset-get.sh <project_id> <final assetId>`, then send the user the
     **full** asset URL as plain text — all `?…` query params, never truncated or wrapped in
     markdown — plus the project link.
   - **FAILED** → explain `nextActionHint` in plain terms and offer to retry.
   - **RECONNECT** → `pexo-chat.sh <project_id> "continue"`, tell the user the connection
     dropped and you're resuming, then keep polling.
   - Never call `pexo-chat.sh` during WAIT — it triggers duplicate production.
   - **Taking too long** → if it's been >30 min and still WAIT, tell the user (with the project
     link + `https://pexo.ai/connect/openclaw`) it's running long; ask whether to keep waiting or
     stop. Don't poll forever.

## Revisions

After delivery, the user's tweaks ("make it shorter", "new music", "different shot") reuse the
**same** project: `pexo-chat.sh <project_id> "<their feedback>"`, then poll again (step 5). Never
create a new project for a revision — it throws away Pexo's server-side context.

## Credits

If a script fails with "Credits balance" / "Insufficient credits": if the error carries a
purchase link, pass it to the user; otherwise tell them to add credits at `https://pexo.ai/home`
→ Credits → Buy Credits. Retry after they confirm.

## Example

User: "Generate a 20-second AI video introducing our productivity app."

```bash
pid=$(pexo-project-create.sh "AI video app intro")
pexo-chat.sh "$pid" "Generate a 20-second AI video introducing our productivity app."
# Tell the user: submitted, ~15–20 min, https://pexo.ai/project/$pid
# Poll pexo-project-get.sh "$pid" until nextAction is DELIVER, then deliver the asset URL.
```

## Scripts

| Script | Usage | Returns |
|---|---|---|
| `pexo-project-create.sh` | `"<brief>"` | `project_id` |
| `pexo-upload.sh` | `<project_id> <file>` | `asset_id` |
| `pexo-chat.sh` | `<project_id> "<message>" [--choice <id>]` | ack (async) |
| `pexo-project-get.sh` | `<project_id>` | JSON: `nextAction`, `recentMessages` |
| `pexo-asset-get.sh` | `<project_id> <asset_id>` | JSON with `url` |
| `pexo-doctor.sh` | — | setup diagnostic |

Error codes and edge cases → `references/TROUBLESHOOTING.md`.

© pexoai · MIT · pexoai/pexo-skills

Similar skills

All skills for AI and ML →

ai-video-generation by other authors comes first.

ai-video-generation 101-skills ai-video-generation is a Claude Code skill for generating videos with Google Veo, Seedance, HappyHorse and 40+ models. It turns text and images into video, syncs lips and generates audio. CX Codex +1 1,000,000installs ai-video-generation prime-skills The ai-video-generation skill routes video requests to suitable models and produces clips via the runcomfy CLI. It helps create animations from text prompts or still frames directly inside your agent chat. CX Codex +1 393,800installs video-shortform nexu-io video-shortform produces 3–10 second video clips — product reveals, motion teasers, ambient loops — and saves a single MP4 into the project folder. CX Codex +1 210installs UGC Video Generation eachlabs UGC Video Generation produces realistic user-style video footage via the each::sense API, covering reviews, unboxings, and tutorials. CX Codex +1 288installs shortfilm-prompt jnMetaCode shortfilm-prompt turns a rough idea into a prompt for a video model: theme, character and scene, atmosphere, camera rules, storyboard. Useful when you need a short scene, not a single still. CX Codex +1 ★ 559repo stars video-generation bytedance The video-generation skill for Claude Code creates videos from structured JSON prompts and optional reference images. It runs the generation script with a chosen provider. CX Codex +1 3,000installs kling-video acedatacloud kling-video generates AI video via the AceDataCloud Kuaishou Kling API. Use it to render text prompts, animate still frames, extend existing clips, and run lip sync. CX Codex +1 240installs muapi-media-generation SamurAIGPT muapi-media-generation produces generative images, video clips, and audio via muapi.ai right from the terminal. Useful for running creative media tasks inside agent workflows. CX Codex +1 1,100installs

From the same set20

The whole set →
seedance-2.0-prompter seedance-2.0-prompter builds a structured Seedance 2.0 video prompt from images, videos, audio, and a creative brief. Useful when a request needs several assets and careful prompt design. CX Codex +1 1,400installs videoagent-director videoagent-director turns a text idea into a storyboard and generates images, video clips, and audio without manual prompt writing. CX Codex +1 567installs veo-3.2-prompter veo-3.2-prompter is a Claude Code, Codex, and Cursor skill that builds Google Veo 3.2 prompts from media and scene descriptions, triggered by Veo, Artemis, or video-generation requests. CX Codex +1 553installs image-to-video image-to-video animates still images into moving video clips with camera movement and music using the Pexo platform. CX Codex +1 132installs text-to-video text-to-video turns a written prompt or script into a finished video with multiple shots, music, and subtitles. Use it when the video should start from text. CX Codex +1 127installs product-video This Claude Code skill sends product photos to Pexo to create a product video. It activates for e-commerce clip requests, not explainers or other non-product videos. CX Codex +1 123installs explainer-video Claude Code skill creates narrated explainer videos and tutorials via Pexo. Runs when requested to generate a product walkthrough or tutorial video. CX Codex +1 122installs video-ad Automates generating promotional video ads through the Pexo service using a product description or brief. CX Codex +1 120installs

Project sponsors

Companies that keep this analytics open