Skip to main content
skill CX Codex

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

image-to-video animates still images into moving video clips with camera movement and music using the Pexo platform.

MIT 132 installs ★ 835 updated 2026-08-20

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

What image-to-video does

This skill relays image files and user prompts directly to the hosted Pexo service. The Pexo backend handles the generation pipeline, picking models such as Seedance, Kling, or Wan while adding camera paths and audio tracks. The AI assistant acts as a coordinator rather than an editor.

Execution relies on local shell utilities: pexo-project-create.sh, pexo-upload.sh, and pexo-chat.sh. Rendering takes approximately 15–20 minutes, during which the agent polls project status every 60 seconds. Feedback and revisions stay within the same project identifier so the server keeps context intact.

Running the scripts requires curl, jq, file, and active Pexo credits configured in ~/.pexo/config. Missing keys cause API calls to abort immediately.

What it helps with

  • turn a product photograph into an animated promotional clip
  • add camera zoom and transitions to a still illustration
  • delegate video model selection for image animation tasks
  • attach background music and rendering effects to static frames

Example prompts for the agent

  • Animate this product photo with a slow camera zoom and music
  • Make a short video from this still picture: animate the water in the background
  • Turn this image into a video clip with smooth pan movement

How to install image-to-video

1Skills CLI (Vercel)

npx skills add pexoai/pexo-skills --skill image-to-video -a claude-code

2Manually: put the files in place

~/.claude/skills/image-to-video/SKILL.md

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

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

Questions about image-to-video

How to install image-to-video in Claude Code?

Run npx skills add pexoai/pexo-skills --skill image-to-video -a claude-code. The skill definition will be placed in ~/.claude/skills/image-to-video/SKILL.md.

What system requirements does image-to-video have?

The environment must have curl, jq, and file in its path. You also need an API key from pexo.ai placed in ~/.pexo/config as PEXO_API_KEY.

Can image-to-video create clips from text prompts alone?

No, it requires an image asset to operate. Text-only generations should be directed to the dedicated text-to-video skill instead.

Source text

SKILL.md · MIT
---
name: image-to-video
description: >
  Animate a still image into a finished, moving video with Pexo. Upload a photo and Pexo adds
  natural motion, camera moves, and transitions, auto-picks the best image-to-video model
  (Seedance, Kling, Wan, and more), and returns a publish-ready clip with music. Use when the
  user has an IMAGE to bring to life: "image to video", "animate this photo", "make a video from
  this picture", "turn my image into a video". NOT for text-only prompts (use the text-to-video
  skill) or 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
---

# Image to Video — Pexo

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

Bring a still image to life as a finished video. You upload the user's image, hand the request
to the hosted Pexo agent, and deliver the result — Pexo adds the motion, camera movement, music,
and assembles the final clip.

## 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: "Animate this product photo into a 10-second clip with a slow zoom."

```bash
pid=$(pexo-project-create.sh "animate product photo")
pexo-chat.sh "$pid" "Animate this product photo into a 10-second clip with a slow zoom."
# 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 →

image-to-video by other authors comes first.

image-to-video prime-skills image-to-video — a skill for Claude Code, Codex, Cursor and other agents that turns a still image into video via RunComfy. CX Codex +1 448,900installs image-to-video 101-skills image-to-video — a reference skill for turning still images into short videos: model choice, motion prompts and camera moves. CX Codex +1 65,800installs image-to-video eachlabs image-to-video turns still photos into short videos with each::sense: subtle motion, cinemagraphs, camera pushes. Handy when all you have is one image. CX Codex +1 553installs video-prompting-guide 101-skills video-prompting-guide breaks a video prompt into shot, movement, light and style, with phrase tables and per-model notes. For the point where plain descriptions stop working. CX Codex +1 268installs layer-video layerai layer-video — a skill for generating video with Layer: text-to-video, animating a still, extending a clip, camera motion, audio and lip sync. Useful when a prompt returns the wrong motion. CX Codex +1 4,900installs kling-video calesthio kling-video is a Claude Code skill for planning and producing videos with Kling AI. It covers generation, editing, motion control, and output review. CX Codex +1 158installs muapi-character-story-video SamurAIGPT muapi-character-story-video — a skill for Claude Code, Codex, Cursor and other agents that builds a multi-part animated video from a character description and a story premise. CX Codex +1 678installs muapi-one-shot-video SamurAIGPT muapi-one-shot-video is a Claude Code skill that generates a cinematic video as one continuous shot. It responds to requests for a single take or a smooth camera move through a scene. CX Codex +1 673installs

From the same set20

The whole set →
videoagent-audio-studio videoagent-audio-studio routes text-to-speech, music creation, sound effects, and voice cloning to ElevenLabs and fal.ai. Returns ready audio URLs straight inside your coding agent. CX Codex +1 4,000installs 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 ai-video-generation ai-video-generation generates finished AI videos with music and subtitles through Pexo from text prompts, scripts, or images. CX Codex +1 130installs 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

Project sponsors

Companies that keep this analytics open