用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/duclm1x1/Dive-Ai --skill vap-media命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
正在显示 SKILL.md
| name | vap-media |
| description | AI image, video, and music generation + editing. Flux, Veo 3.1, Suno V5. |
| metadata | {"clawdbot":{"emoji":"🎬","requires":{"bins":["curl"]}}} |
Generate images, videos, and music. Edit with inpaint, ai_edit, upscale, background removal, video trim/merge.
Check if VAP_API_KEY is set:
Generate images for free. No signup required. 3 per day.
curl -s -X POST https://api.vapagent.com/v3/trial/generate \
-H "Content-Type: application/json" \
-d '{"prompt":"PROMPT"}'
Returns {"task_id":"UUID","status":"pending","remaining":2}.
curl -s https://api.vapagent.com/v3/trial/status/TASK_ID
Returns {"status":"completed","image_url":"https://..."} when done.
429 → Daily limit reached. Suggest upgrading: export VAP_API_KEY=vap_xxx503 → Trial service temporarily unavailable.Unlimited images, video, music, and editing operations.
curl -s -X POST https://api.vapagent.com/v3/tasks \
-H "Authorization: Bearer $VAP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"type":"TYPE","params":{"description":"PROMPT"}}'
Returns {"task_id":"UUID","status":"pending"}.
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.
image or image_generation)| Param | Type | Default | Description |
|---|---|---|---|
description | string | required | Image description |
aspect_ratio | enum | 1:1 | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9, 9:21 |
quality | enum | standard | standard or high |
Tip: Aspect ratio is auto-detected from prompt text. "a wide landscape photo" → 16:9 automatically.
video or video_generation) — Tier 2+| Param | Type | Default | Description |
|---|---|---|---|
description | string | required | Video description |
duration | int | 8 | 4, 6, or 8 seconds |
aspect_ratio | enum | 16:9 | 16:9 (landscape) or 9:16 (portrait) |
generate_audio | bool | true | Include audio track |
resolution | enum | 720p | 720p or 1080p |
negative_prompt | string | "" | What to avoid |
music or music_generation) — Tier 2+| Param | Type | Default | Description |
|---|---|---|---|
description | string | required | Music description (genre, mood, instruments) |
duration | int | 120 | 30-480 seconds |
instrumental | bool | false | No vocals |
audio_format | enum | mp3 | mp3 or wav (lossless) |
loudness_preset | enum | streaming | streaming (-14 LUFS), apple (-16 LUFS), broadcast (-23 LUFS) |
style | string | none | Genre/style (max 1000 chars) |
title | string | none | Song title |
custom_mode | bool | false | Enable custom lyrics + style mode |
401 → Invalid API key.402 → Insufficient balance. Top up at https://vapagent.com/dashboard/signup.html403 → Tier too low for this task type.Post-production editing operations. Tier 1+ required.
curl -s -X POST https://api.vapagent.com/v3/operations \
-H "Authorization: Bearer $VAP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"operation":"OPERATION","media_url":"URL","prompt":"INSTRUCTION"}'
curl -s https://api.vapagent.com/v3/operations/OPERATION_ID \
-H "Authorization: Bearer $VAP_API_KEY"
| Operation | Required Params | Description |
|---|---|---|
inpaint | media_url, prompt | AI editing (optional: mask_url) |
ai_edit | media_url, prompt | AI-powered image editing with text instructions (optional: additional_images) |
background_remove | media_url | Remove background |
upscale | media_url | Enhance resolution (scale: 2 or 4) |
video_trim | media_url, start_time, end_time | Trim video |
video_merge | media_urls (array, min 2) | Merge video clips |
When a user asks to create/generate/make an image, video, or music:
VAP_API_KEY set?/v3/tasks (or /v3/trial/generate for free)/v3/operations/v3/execute with presetWhen a user asks to edit/enhance/modify an existing image or video:
/v3/operations# Create (no auth needed)
curl -s -X POST https://api.vapagent.com/v3/trial/generate \
-H "Content-Type: application/json" \
-d '{"prompt":"A fluffy orange tabby cat on a sunlit windowsill, soft bokeh, golden hour light, photorealistic"}'
# Poll
curl -s https://api.vapagent.com/v3/trial/status/TASK_ID
# Image (widescreen)
curl -s -X POST https://api.vapagent.com/v3/tasks \
-H "Authorization: Bearer $VAP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"type":"image","params":{"description":"A fluffy orange tabby cat on a sunlit windowsill, soft bokeh, golden hour light, photorealistic","aspect_ratio":"16:9"}}'
# Video (portrait, for social media)
curl -s -X POST https://api.vapagent.com/v3/tasks \
-H "Authorization: Bearer $VAP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"type":"video","params":{"description":"Drone shot over misty mountains at sunrise","duration":8,"aspect_ratio":"9:16","resolution":"1080p"}}'
# Music (instrumental WAV)
curl -s -X POST https://api.vapagent.com/v3/tasks \
-H "Authorization: Bearer $VAP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"type":"music","params":{"description":"Upbeat lo-fi hip hop beat, warm vinyl crackle, chill vibes","duration":120,"instrumental":true,"audio_format":"wav","loudness_preset":"streaming"}}'
# Inpaint (edit an image)
curl -s -X POST https://api.vapagent.com/v3/operations \
-H "Authorization: Bearer $VAP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"operation":"inpaint","media_url":"https://example.com/photo.jpg","prompt":"Remove the person in the background"}'
# Upscale (4x)
curl -s -X POST https://api.vapagent.com/v3/operations \
-H "Authorization: Bearer $VAP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"operation":"upscale","media_url":"https://example.com/photo.jpg","options":{"scale":4}}'
# Background Remove
curl -s -X POST https://api.vapagent.com/v3/operations \
-H "Authorization: Bearer $VAP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"operation":"background_remove","media_url":"https://example.com/photo.jpg"}'
curl -s https://api.vapagent.com/v3/tasks/TASK_ID \
-H
For content campaigns, use /v3/execute to generate multiple assets from one prompt:
curl -s -X POST https://api.vapagent.com/v3/execute \
-H "Authorization: Bearer $VAP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"preset":"streaming_campaign","prompt":"PROMPT"}'
Returns all assets when complete:
{"status":"completed","outputs":{"video":"https://...","music":"https://...","thumbnail":"https://..."}}
| Preset | Includes |
|---|---|
streaming_campaign | video + music + thumbnail + metadata |
full_production | video + music + thumbnail + metadata + SEO |
video.basic | video only |
music.basic | music only |
image.basic | image only |
export VAP_API_KEY=vap_xxxxxxxxxxxxxxxxxxxx