composing-videos
Combines multiple videos/images into a single video with optional background audio.
Skill by Yusufkotavom
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/yusufkotavom-composing-videos
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/composing-videos
What's inside
- Skill name
composing-videos- Description
- Combines multiple videos/images into a single video with optional background audio. Use when user wants to merge clips, concatenate videos, create slideshow from images, stitch videos together, combine media files, add background music to video, mix video with audio, create video montage, or join multiple video segments. 合并视频、拼接视频、图片合成视频、添加背景音乐、视频拼接、多图生成视频、视频混剪、素材合成。
- License
- MIT
- Instructions
- 97 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Video Composition Combines multiple videos/images into a single video with optional background audio using AI-powered processing. ## When to Use Use this skill when: - Merging multiple video clips into one - Creating a slideshow from multiple images - Adding background music to a video - Combining videos with audio tracks - Stitching together video segments ## Workflow ### Step 1: Collect Media Gather all media URLs from user: - Video files (MP4, MOV, etc.) - Image files (JPG, PNG, etc.) - Audio files (MP3, WAV, etc.) for background music ### Step 2: Submit Task Call `submitAideoTask` with: - **prompt**: Natural language description of desired composition - **multiInputs**: Array of all media URLs ### Step 3: Poll for Results 1. First check: Wait **210 seconds** after submission 2. Subsequent checks: Wait **30 seconds** between polls 3. Call `getAideoTaskStatus` to check progress ### Step 4: Timeout Handling **Maximum wait time: 20 minutes** If task exceeds 20 minutes: - Report as timeout failure - Suggest user try with shorter/smaller media ### Step 5: Return Results On completion, return the output video URL to user. ## Examples ### Example 1: Merge Images into Video **User request**: "Create a video from these 5 photos" ``` submitAideoTask: prompt: "Combine these images into a video, each image displays for 3 seconds with fade transition effects" multiInputs: ["photo1.jpg", "photo2.jpg", "photo3.jpg", "photo4.jpg", "photo5.jpg"] ``` ### Example 2: Merge Videos with Background Music **User request**: "Combine these clips and add background music" ``` submitAideoTask: prompt: "Merge these video clips into one video and add the background music" multiInputs: ["clip1.mp4", "clip2.mp4", "clip3.mp4", "background_music.mp3"] ``` ### Example 3: Create Video Montage **User request**: "Create a montage from my vacation videos" ``` submitAideoTask: prompt: "Create a dynamic video montage with smooth transitions between clips" multiInputs: ["vacation1.mp4", "vacation2.mp4", "vacation3.mp4"] ``` ## Priority for Multi-Media Tasks When using aideo for multi-media composition: - **Always use aideo first** for: Images to video / Video concatenation / Audio-video merge - Priority order: Translation > Erase > Highlight > Vision > Other ## Important Notes - Processing time: approximately 10 minutes per 1-minute of output video - Supports multiple input formats (MP4, MOV, JPG, PNG, MP3, etc.) - For style transfer (comic/anime), use the `transferring-video-styles` skill instead - Maximum wait time is 20 minutes
From Yusufkotavom/AiToEarn, MIT.
More from Yusufkotavom/AiToEarn
- 0.409score
extracting-thumbnails
Yusufkotavom
Extracts thumbnails from video URLs.
SkillDFreshness: DClaude Code +9 - 0.409score
analyzing-videos
Yusufkotavom
Analyzes video content and extracts highlights.
SkillDFreshness: DClaude Code +9 - 0.409score
crawling-social-media
Yusufkotavom
Downloads and extracts content from social media platforms.
SkillDFreshness: DClaude Code +9 - 0.409score
generating-drama-recaps
Yusufkotavom
Generates narrated recap videos from short drama clips using AI-powered narration and voice synthesis.
SkillDFreshness: DClaude Code +9 - 0.409score
managing-content
Yusufkotavom
Manages media files, drafts, and content organization.
SkillDFreshness: DClaude Code +9 - 0.409score
removing-subtitles
Yusufkotavom
Removes hardcoded subtitles from videos using AI inpainting.
SkillDFreshness: DClaude Code +9 - 0.409score
transferring-video-styles
Yusufkotavom
Converts live-action videos into artistic styles like comic, anime, manga, 3D cartoon.
SkillDFreshness: DClaude Code +9 - 0.409score
translating-videos
Yusufkotavom
Translates videos including subtitles, voice cloning, and lip sync.
SkillDFreshness: DClaude Code +9 - 0.406score
api-inventory-maintenance
Yusufkotavom
Gunakan skill ini untuk memelihara dokumentasi endpoint API lintas layanan (aitoearn-ai, aitoearn-server, worker) agar selalu sinkron dengan source code…
SkillDFreshness: DClaude Code +9 - 0.406score
api-sse-integration
Yusufkotavom
Gunakan skill ini ketika mengubah kontrak API atau alur SSE antara backend dan frontend, termasuk endpoint agent/chat stream, format event, polling fallback…
SkillDFreshness: DClaude Code +9 - 0.406score
backend-ai-development
Yusufkotavom
Gunakan skill ini untuk perubahan pada project/aitoearn-backend, termasuk endpoint NestJS, service AI (chat/image/video/agent), queue consumer, serta…
SkillDFreshness: DClaude Code +9 - 0.406score
docker-operations
Yusufkotavom
Gunakan skill ini untuk pekerjaan deployment/container pada project AiToEarn, termasuk docker-compose, Dockerfile web/backend, variabel environment, startup…
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 17, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Yusufkotavom/AiToEarn
- Website
- ai-to-earn.vercel.app
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Yusufkotavom
- 0.409score
managing-content
Yusufkotavom
Manages media files, drafts, and content organization.
SkillDFreshness: DClaude Code +9 - 0.409score
generating-drama-recaps
Yusufkotavom
Generates narrated recap videos from short drama clips using AI-powered narration and voice synthesis.
SkillDFreshness: DClaude Code +9 - 0.409score
crawling-social-media
Yusufkotavom
Downloads and extracts content from social media platforms.
SkillDFreshness: DClaude Code +9 - 0.409score
extracting-thumbnails
Yusufkotavom
Extracts thumbnails from video URLs.
SkillDFreshness: DClaude Code +9 - 0.409score
analyzing-videos
Yusufkotavom
Analyzes video content and extracts highlights.
SkillDFreshness: DClaude Code +9 - 0.409score
removing-subtitles
Yusufkotavom
Removes hardcoded subtitles from videos using AI inpainting.
SkillDFreshness: DClaude Code +9
Cite this page
composing-videos skill. Agent Mart. https://agentmart.dev/skills/yusufkotavom-composing-videos (last updated 2026-10-24)