# awesome-genmedia/skills architecture

> Architecture diagram of the GitHub repository awesome-genmedia/skills, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-17). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/awesome-genmedia/skills
- Repository: https://github.com/awesome-genmedia/skills

## Overview

This repository is a catalog of generative-media skills for AI agents, rather than an application runtime. Users invoke a skill for a media task; the README documents use-case skills with each::sense’s model-selecting API and direct model access through the Prediction API. The catalog also includes domain-specific categories and individual model skills. No source excerpts were provided, so relationships beyond these documented entry points are omitted.

Main entry points: [`image-generation/SKILL.md`](https://github.com/awesome-genmedia/skills/blob/main/image-generation/SKILL.md) (Image Skills), [`image-editing/SKILL.md`](https://github.com/awesome-genmedia/skills/blob/main/image-editing/SKILL.md) (Image Editing), [`video-generation/SKILL.md`](https://github.com/awesome-genmedia/skills/blob/main/video-generation/SKILL.md) (Video Skills), [`song-generation/SKILL.md`](https://github.com/awesome-genmedia/skills/blob/main/song-generation/SKILL.md) (Song Generation)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_skills["Core Skills"]
  node_image["Image Skills<br/>[SKILL.md]"]
  node_image_edit["Image Editing<br/>[SKILL.md]"]
  node_image_up["Image Upscaling<br/>[SKILL.md]"]
  node_bg["Background Removal<br/>[SKILL.md]"]
  node_face["Face Swap<br/>[SKILL.md]"]
  node_video["Video Skills<br/>[SKILL.md]"]
  node_video_edit["Video Editing<br/>[SKILL.md]"]
  node_song["Song Generation<br/>[SKILL.md]"]
  node_music["Music Generation<br/>[SKILL.md]"]
  node_lyrics["Lyrics Generation<br/>[SKILL.md]"]
  node_voice["Voice Generation<br/>[SKILL.md]"]
  node_tts["Text to Speech<br/>[SKILL.md]"]
  node_stt["Speech to Text<br/>[SKILL.md]"]
  node_effects["Sound Effects<br/>[SKILL.md]"]
end

subgraph group_catalog["Skill Catalog"]
  node_categories["Domain Skills"]
  node_models["Model Skills"]
end

subgraph group_access["API Access"]
  node_sense{{"each::sense API"}}
  node_prediction{{"Prediction API"}}
end

node_user(("Agent User"))
node_eachlabs(("each::labs"))
node_media["Generated Media"]

node_user -->|"invokes"| node_image
node_user -->|"invokes"| node_image_edit
node_user -->|"invokes"| node_image_up
node_user -->|"invokes"| node_bg
node_user -->|"invokes"| node_face
node_user -->|"invokes"| node_video
node_user -->|"invokes"| node_video_edit
node_user -->|"invokes"| node_song
node_user -->|"invokes"| node_music
node_user -->|"invokes"| node_lyrics
node_user -->|"invokes"| node_voice
node_user -->|"invokes"| node_tts
node_user -->|"invokes"| node_stt
node_user -->|"invokes"| node_effects
node_user -->|"selects"| node_categories
node_user -->|"selects"| node_models
node_image -->|"uses for requests"| node_sense
node_image_edit -->|"uses for requests"| node_sense
node_video -->|"uses for requests"| node_sense
node_song -->|"uses for requests"| node_sense
node_sense -->|"sends requests"| node_eachlabs
node_models -->|"direct model access"| node_prediction
node_user -->|"submits model request"| node_prediction
node_prediction -->|"sends prediction"| node_eachlabs
node_eachlabs -->|"generates"| node_media

click node_image "https://github.com/awesome-genmedia/skills/blob/main/image-generation/SKILL.md"
click node_image_edit "https://github.com/awesome-genmedia/skills/blob/main/image-editing/SKILL.md"
click node_image_up "https://github.com/awesome-genmedia/skills/blob/main/image-upscaling/SKILL.md"
click node_bg "https://github.com/awesome-genmedia/skills/blob/main/background-removal/SKILL.md"
click node_face "https://github.com/awesome-genmedia/skills/blob/main/face-swap/SKILL.md"
click node_video "https://github.com/awesome-genmedia/skills/blob/main/video-generation/SKILL.md"
click node_video_edit "https://github.com/awesome-genmedia/skills/blob/main/video-editing/SKILL.md"
click node_song "https://github.com/awesome-genmedia/skills/blob/main/song-generation/SKILL.md"
click node_music "https://github.com/awesome-genmedia/skills/blob/main/music-generation/SKILL.md"
click node_lyrics "https://github.com/awesome-genmedia/skills/blob/main/lyrics-generation/SKILL.md"
click node_voice "https://github.com/awesome-genmedia/skills/blob/main/voice-generation/SKILL.md"
click node_tts "https://github.com/awesome-genmedia/skills/blob/main/text-to-speech/SKILL.md"
click node_stt "https://github.com/awesome-genmedia/skills/blob/main/speech-to-text/SKILL.md"
click node_effects "https://github.com/awesome-genmedia/skills/blob/main/sound-effects/SKILL.md"
click node_categories "https://github.com/awesome-genmedia/skills/tree/main/categories"
click node_models "https://github.com/awesome-genmedia/skills/tree/main/models"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_image,node_image_edit,node_image_up,node_bg,node_face,node_video,node_video_edit,node_song,node_music,node_lyrics,node_voice,node_tts,node_stt,node_effects,node_user toneBlue
class node_categories,node_models toneAmber
class node_sense,node_prediction toneMint
class node_eachlabs,node_media toneIndigo
```

## Components

### Core Skills

- [Image Skills](https://github.com/awesome-genmedia/skills/blob/main/image-generation/SKILL.md): `image-generation/SKILL.md`
- [Image Editing](https://github.com/awesome-genmedia/skills/blob/main/image-editing/SKILL.md): `image-editing/SKILL.md`
- [Image Upscaling](https://github.com/awesome-genmedia/skills/blob/main/image-upscaling/SKILL.md): `image-upscaling/SKILL.md`
- [Background Removal](https://github.com/awesome-genmedia/skills/blob/main/background-removal/SKILL.md): `background-removal/SKILL.md`
- [Face Swap](https://github.com/awesome-genmedia/skills/blob/main/face-swap/SKILL.md): `face-swap/SKILL.md`
- [Video Skills](https://github.com/awesome-genmedia/skills/blob/main/video-generation/SKILL.md): `video-generation/SKILL.md`
- [Video Editing](https://github.com/awesome-genmedia/skills/blob/main/video-editing/SKILL.md): `video-editing/SKILL.md`
- [Song Generation](https://github.com/awesome-genmedia/skills/blob/main/song-generation/SKILL.md): `song-generation/SKILL.md`
- [Music Generation](https://github.com/awesome-genmedia/skills/blob/main/music-generation/SKILL.md): `music-generation/SKILL.md`
- [Lyrics Generation](https://github.com/awesome-genmedia/skills/blob/main/lyrics-generation/SKILL.md): `lyrics-generation/SKILL.md`
- [Voice Generation](https://github.com/awesome-genmedia/skills/blob/main/voice-generation/SKILL.md): `voice-generation/SKILL.md`
- [Text to Speech](https://github.com/awesome-genmedia/skills/blob/main/text-to-speech/SKILL.md): `text-to-speech/SKILL.md`
- [Speech to Text](https://github.com/awesome-genmedia/skills/blob/main/speech-to-text/SKILL.md): `speech-to-text/SKILL.md`
- [Sound Effects](https://github.com/awesome-genmedia/skills/blob/main/sound-effects/SKILL.md): `sound-effects/SKILL.md`

### Skill Catalog

- [Domain Skills](https://github.com/awesome-genmedia/skills/tree/main/categories): `categories`
- [Model Skills](https://github.com/awesome-genmedia/skills/tree/main/models): `models`

### API Access

- **each::sense API**
- **Prediction API**

### Other components

- **Agent User**
- **each::labs**
- **Generated Media**

## Connections

- Agent User → Image Skills: invokes (evidence: `README.md`)
- Agent User → Image Editing: invokes (evidence: `README.md`)
- Agent User → Image Upscaling: invokes (evidence: `README.md`)
- Agent User → Background Removal: invokes (evidence: `README.md`)
- Agent User → Face Swap: invokes (evidence: `README.md`)
- Agent User → Video Skills: invokes (evidence: `README.md`)
- Agent User → Video Editing: invokes (evidence: `README.md`)
- Agent User → Song Generation: invokes (evidence: `README.md`)
- Agent User → Music Generation: invokes (evidence: `README.md`)
- Agent User → Lyrics Generation: invokes (evidence: `README.md`)
- Agent User → Voice Generation: invokes (evidence: `README.md`)
- Agent User → Text to Speech: invokes (evidence: `README.md`)
- Agent User → Speech to Text: invokes (evidence: `README.md`)
- Agent User → Sound Effects: invokes (evidence: `README.md`)
- Agent User → Domain Skills: selects (evidence: `README.md`)
- Agent User → Model Skills: selects (evidence: `README.md`)
- Image Skills → each::sense API: uses for requests (evidence: `README.md`)
- Image Editing → each::sense API: uses for requests (evidence: `README.md`)
- Video Skills → each::sense API: uses for requests (evidence: `README.md`)
- Song Generation → each::sense API: uses for requests (evidence: `README.md`)
- each::sense API → each::labs: sends requests (evidence: `README.md`)
- Model Skills → Prediction API: direct model access (evidence: `README.md`)
- Agent User → Prediction API: submits model request (evidence: `README.md`)
- Prediction API → each::labs: sends prediction (evidence: `README.md`)
- each::labs → Generated Media: generates (evidence: `README.md`)
