Learn-skills.dev agent-media

Agent-first media toolkit for image, video, and audio processing. Use when you need to resize, convert, generate images, remove backgrounds, extract audio, transcribe speech, or generate videos. All commands return deterministic JSON output.

install

source · Clone the upstream repo

git clone https://github.com/NeverSight/learn-skills.dev

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/NeverSight/learn-skills.dev "$T" && mkdir -p ~/.claude/skills && cp -r "$T/data/skills-md/agntswrm/agent-media/agent-media" ~/.claude/skills/neversight-learn-skills-dev-agent-media && rm -rf "$T"

manifest: data/skills-md/agntswrm/agent-media/agent-media/SKILL.md

source content

Agent Media

Agent Media is an agent-first media toolkit that provides CLI-accessible commands for image, video, and audio processing. All commands produce deterministic, machine-readable JSON output.

Available Commands

Image Commands

```
agent-media image resize
```
- Resize an image
```
agent-media image convert
```
- Convert image format
```
agent-media image remove-background
```
- Remove image background
```
agent-media image generate
```
- Generate image from text

Audio Commands

```
agent-media audio extract
```
- Extract audio from video
```
agent-media audio transcribe
```
- Transcribe audio to text

Video Commands

```
agent-media video generate
```
- Generate video from text or image

Output Format

All commands return JSON to stdout:

{
  "ok": true,
  "media_type": "image",
  "action": "resize",
  "provider": "local",
  "output_path": "output_123.webp",
  "mime": "image/webp",
  "bytes": 12345
}

On error:

{
  "ok": false,
  "error": {
    "code": "INVALID_INPUT",
    "message": "input file not found"
  }
}

Providers

local - Default provider using Sharp (resize, convert) and Transformers.js (remove-background, transcribe)
fal - fal.ai provider (generate, edit, remove-background, transcribe, video)
replicate - Replicate API (generate, edit, remove-background, transcribe, video)
runpod - Runpod API (generate, edit)
ai-gateway - Vercel AI Gateway (generate, edit)

Provider Selection

Explicit:
```
--provider <name>
```
Auto-detect from environment variables
Fallback to local provider

Environment Variables

```
AGENT_MEDIA_DIR
```
- Custom output directory
```
FAL_API_KEY
```
- Enable fal provider
```
REPLICATE_API_TOKEN
```
- Enable replicate provider
```
RUNPOD_API_KEY
```
- Enable runpod provider
```
AI_GATEWAY_API_KEY
```
- Enable ai-gateway provider