Refactor high-complexity React components in Dify frontend. Use when `pnpm analyze-component...
npx skills add elestirelbilinc-sketch/vapagent-vap-media-skill
Or install specific skill: npx add-skill https://github.com/elestirelbilinc-sketch/vapagent-vap-media-skill
# Description
AI image, video, and music generation. Flux, Veo 3.1, Suno V5.
# SKILL.md
name: vap-media
description: AI image, video, and music generation. Flux, Veo 3.1, Suno V5.
homepage: https://vapagent.com
VAP Media - AI Media Generation
Generate images, videos, and music via the VAP API.
Mode Selection
Check if VAP_API_KEY is set:
- VAP_API_KEY not set → Use Free Mode (images only, 3/day)
- VAP_API_KEY set → Use Full Mode (image, video, music, unlimited)
Free Mode (No API Key)
Generate images for free. No signup required. 3 per day.
Generate Image
curl -s -X POST https://api.vapagent.com/v3/trial/generate \
-H "Content-Type: application/json" \
-d '{"description":"a serene mountain lake at sunset"}'
Returns {"task_id":"UUID","status":"pending","remaining":2}.
Poll Result
curl -s https://api.vapagent.com/v3/trial/status/TASK_ID
Returns {"status":"completed","image_url":"https://..."} when done.
Free Mode Errors
- 429 → Daily limit reached. Suggest upgrading:
export VAP_API_KEY=vape_xxx - 503 → Trial service temporarily unavailable.
Full Mode (With API Key)
Unlimited images, video, and music generation.
Create Task
curl -s -X POST https://api.vapagent.com/v3/tasks \
-H "Authorization: Bearer $VAP_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"type": "image",
"description": "a futuristic cityscape at night",
"aspect_ratio": "16:9"
}'
Returns {"task_id":"UUID","status":"pending","estimated_cost":"0.1800"}.
Poll Result
curl -s https://api.vapagent.com/v3/tasks/TASK_ID \
-H "Authorization: Bearer $VAP_API_KEY"
Returns {"status":"completed","result":{"output_url":"https://..."}} when done.
Task Types
| Type | Model | Params |
|---|---|---|
| image | Flux | description, aspect_ratio (1:1, 16:9, 9:16) |
| video | Veo 3.1 | description, duration (4/6/8), aspect_ratio, generate_audio (bool) |
| music | Suno V5 | description, duration (30-480), instrumental (bool) |
Full Mode Errors
- 401 → Invalid API key.
- 402 → Insufficient balance. Top up at https://vapagent.com/dashboard/signup.html
Instructions
When a user asks to create/generate/make an image, video, or music:
- Improve the prompt - Add style, lighting, composition, mood details
- Check mode - Is VAP_API_KEY set?
- Call the appropriate endpoint - Free or Full mode
- Poll for result - Check task status until completed
- Return the media URL to the user
If free mode limit is hit, tell the user: "You've used your 3 free generations today. For unlimited access, get an API key at https://vapagent.com/dashboard/signup.html"
Free Mode Example
# Create (no auth needed)
curl -s -X POST https://api.vapagent.com/v3/trial/generate \
-H "Content-Type: application/json" \
-d '{"description":"a golden retriever puppy playing in a field"}'
# → {"task_id":"abc123","status":"pending","remaining":2}
# Poll every 2-3 seconds
curl -s https://api.vapagent.com/v3/trial/status/abc123
# → {"status":"completed","image_url":"https://cdn.vapagent.com/abc123.png"}
Full Mode Examples
# Image
curl -s -X POST https://api.vapagent.com/v3/tasks \
-H "Authorization: Bearer $VAP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"type":"image","description":"cyberpunk street at night, neon lights","aspect_ratio":"16:9"}'
# Video
curl -s -X POST https://api.vapagent.com/v3/tasks \
-H "Authorization: Bearer $VAP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"type":"video","description":"ocean waves crashing on beach","duration":6,"generate_audio":true}'
# Music
curl -s -X POST https://api.vapagent.com/v3/tasks \
-H "Authorization: Bearer $VAP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"type":"music","description":"upbeat electronic dance music","duration":120,"instrumental":false}'
Prompt Tips
- Style: "oil painting", "3D render", "watercolor", "photograph", "flat illustration"
- Lighting: "golden hour", "neon lights", "soft diffused light", "dramatic shadows"
- Composition: "close-up", "aerial view", "wide angle", "rule of thirds"
- Mood: "serene", "energetic", "mysterious", "whimsical"
Setup (Optional - for Full Mode)
- Sign up: https://vapagent.com/dashboard/signup.html
- Get API key from dashboard
- Set:
export VAP_API_KEY=vape_xxxxxxxxxxxxxxxxxxxx
Links
# README.md
VAP Media Skill for Claude Code
🎨 AI-powered image, video, and music generation skill for Claude Code, Codex CLI, and other AI coding assistants.
Features
- 🖼 Image Generation - Flux model
- 🎬 Video Generation - Veo 3.1 model
- 🎵 Music Generation - Suno V5 model
- 🆓 Free Mode - 3 free image generations per day
- ⚡️ Full Mode - Unlimited access with API key
Installation
For Claude Code
# Copy to your skills directory
cp SKILL.md ~/.claude/skills/vap-media.md
For Codex CLI
# Copy to your skills directory
cp SKILL.md ~/.codex/skills/vap-media.md
For Gemini CLI
# Copy to your skills directory
cp SKILL.md ~/.gemini/skills/vap-media.md
Quick Start
- Install the skill in your AI assistant
- Ask: "Generate an image of a sunset over mountains"
- The assistant will use VAP API to create your media
Free vs Full Mode
| Feature | Free Mode | Full Mode |
|---|---|---|
| Images | ✅ 3/day | ✅ Unlimited |
| Videos | ❌ | ✅ |
| Music | ❌ | ✅ |
| API Key | Not required | Required |
Get your API key at: https://vapagent.com/dashboard/signup.html
Documentation
Full documentation is in SKILL.md
Links
License
MIT License - See LICENSE file
Author
Created by @elestirelbilinc
# Supported AI Coding Agents
This skill is compatible with the SKILL.md standard and works with all major AI coding agents:
Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.