{
  "markdown": "# each::labs Agent Skills\n\n**Give your AI coding agent creative superpowers.** Generate videos, images, music, voiceovers, and more — directly from your terminal.\n\n445+ AI models and 130+ pre-built workflows. Works with Claude Code, Cursor, Copilot, and any agent that supports the [Agent Skills Spec](https://agentskills.io/specification).\n\n## Install\n\n```bash\nnpx skills add eachlabs/skills\n```\n\nOr install a single skill:\n\n```bash\nnpx skills add eachlabs/skills@eachlabs-video-generation\nnpx skills add eachlabs/skills@eachlabs-image-generation\nnpx skills add eachlabs/skills@eachlabs-music\n```\n\n## What Can Your Agent Do?\n\nOnce installed, your coding agent can:\n\n- **\"Generate a 10-second product demo video from this screenshot\"** — text-to-video, image-to-video with 54+ models\n- **\"Create a hero image for my landing page\"** — text-to-image with Flux, GPT Image, Gemini, Imagen, and more\n- **\"Add a voiceover to this video in 6 languages\"** — ElevenLabs TTS, lip sync, video translation\n- **\"Compose a 30-second jingle for my app\"** — full songs, instrumentals, lyrics with Mureka AI\n- **\"Swap the model's face in these campaign photos\"** — face swap across images and videos\n- **\"Generate product shots on white background\"** — e-commerce photography, lifestyle scenes, 360-degree views\n- **\"Create a virtual try-on with this outfit\"** — fashion AI for model imagery and runway content\n- **\"Build a pipeline that generates an image, upscales it, and adds a voiceover\"** — multi-step workflows chaining any models together\n\nNo context switching. No browser tabs. Just ask your agent.\n\n## Available Skills\n\n| Skill | What it does | Models |\n|-------|-------------|--------|\n| [eachlabs-video-generation](skills/eachlabs-video-generation/) | Text-to-video, image-to-video, transitions, motion control, talking heads, avatars | 192 |\n| [eachlabs-video-edit](skills/eachlabs-video-edit/) | Lip sync, video translation, subtitles, upscaling, style transfer, extension | 25+ |\n| [eachlabs-image-generation](skills/eachlabs-image-generation/) | Text-to-image with Flux, GPT Image, Gemini, Imagen, Seedream, and more | 62 |\n| [eachlabs-image-edit](skills/eachlabs-image-edit/) | Style transfer, background removal, upscaling, inpainting, 3D generation | 124 |\n| [eachlabs-product-visuals](skills/eachlabs-product-visuals/) | E-commerce product shots, background replacement, lifestyle scenes, 360-degree views | 17 |\n| [eachlabs-fashion-ai](skills/eachlabs-fashion-ai/) | Fashion model imagery, virtual try-on, runway videos, campaign visuals | 12 |\n| [eachlabs-ugc-video](skills/eachlabs-ugc-video/) | Trending social media effects, dance clips, movie scene recreations | 130+ workflows |\n| [eachlabs-music](skills/eachlabs-music/) | Songs, instrumentals, lyrics, podcasts, stem separation, song recognition | 13 |\n| [eachlabs-voice-audio](skills/eachlabs-voice-audio/) | ElevenLabs TTS, Whisper transcription, RVC voice conversion | 35 |\n| [eachlabs-face-swap](skills/eachlabs-face-swap/) | Face swap across images and videos | 3 |\n| [eachlabs-workflows](skills/eachlabs-workflows/) | Chain multiple models into custom multi-step pipelines | -- |\n\n## Quick Start\n\n1. **Get your API key** at [eachlabs.ai](https://eachlabs.ai)\n\n2. **Set your environment variable:**\n   ```bash\n   export EACHLABS_API_KEY=\"your-api-key\"\n   ```\n\n3. **Install skills:**\n   ```bash\n   npx skills add eachlabs/skills\n   ```\n\n4. **Ask your agent to create something.** That's it.\n\n## How It Works\n\nEach skill follows the [Agent Skills Spec](https://agentskills.io/specification) — an open standard for giving AI agents new capabilities. A skill is a directory containing:\n\n- `SKILL.md` — Instructions, API patterns, and examples the agent reads to learn the skill\n- `references/` — Model catalogs and additional context loaded on demand\n\nWhen your agent encounters a request it can handle with an installed skill (e.g. \"generate a video\"), it reads the skill file, understands the available models and API patterns, and executes the right API calls autonomously.\n\n## APIs\n\neach::labs exposes two APIs that skills interact with:\n\n- **Predictions API** (`api.eachlabs.ai`) — Run individual AI models for image, video, audio, and music generation\n- **Workflows API** (`workflows.eachlabs.run`) — Execute pre-built and custom multi-step workflows\n\nAll API calls are authenticated with your `EACHLABS_API_KEY` environment variable.\n\n## License\n\nMIT\n",
  "bytes": 4421,
  "sha": "ef376d7a2ea23fd8499c028dc0d99d75206fc32e54c4997b14fca286454ece9d",
  "repo_slug": "eachlabs/skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_eachlabs_skills_interior_design_visualiz_f97cd46f/readme"
}