12 free skills · Agent Skills Marketplace

Media & Creative Skills

Your agent can create more than just text. These skills cover image generation, text-to-speech with OpenAI and Kokoro, video creation with Remotion, and audio transcription with ElevenLabs. Perfect for content pipelines that need multimedia output.

Peter SteinbergerPeter Steinberger

Sag

ElevenLabs text-to-speech with mac-style say UX.

18.4k·19·Jan 4
IPedraxIPedrax

Antigravity Image Generator

Generate images using the internal Google Antigravity API (Gemini 3 Pro Image). High quality, native generation without browser automation.

10.3k·16·Feb 17
IvánIván

Image

Create, inspect, process, and improve image files and visual assets with reliable format choice, resizing, compression, color-profile, metadata, and platfor...

9.6k·12·Mar 11
CellCogCellCog

image-cog

AI image generation powered by CellCog. Create images, edit photos, consistent characters, product photography, reference-based images, sets of images, style...

8k·6·Mar 19
Robin797860Robin797860

Qwen Image

Generate images using Qwen Image API (Alibaba Cloud DashScope). Use when users request image generation with Chinese prompts or need high-quality AI-generated images from text descriptions.

6.1k·6·Feb 6
porspors

OpenAI TTS

Converts text to natural-sounding speech using OpenAI's TTS models, giving your AI agent a voice.

4.6k·6·Jan 6
edkiefedkief

Kokoro TTS

Generates high-quality, expressive speech from text using the Kokoro voice engine, an alternative to major cloud TTS providers.

4.4k·1·Feb 1
IvánIván

Image Editing

Gives your AI agent the ability to edit images, from basic operations like cropping and resizing to AI-powered edits like background removal and style changes.

4.3k·4·Feb 12
EvolinkAIEvolinkAI

Best Image Generation

Generates images by routing your prompts to the best available AI image models, letting you compare results across providers.

3.6k·6·Feb 21
clawdbotborgesclawdbotborges

ElevenLabs Speech-to-Text

Transcribes audio files to text using ElevenLabs' speech recognition, with support for speaker detection and multiple languages.

3.5k·5·Jan 26
clawdbotborgesclawdbotborges

ElevenLabs Music

Creates original music tracks using ElevenLabs' AI music generation, from background scores to jingles, all from text descriptions.

2.5k·1·Jan 26
CellCogCellCog

music-cog

A music toolkit that handles both analysis and generation, from detecting chords and tempo to creating new musical pieces.

2.2k·4·Feb 11

Frequently asked questions

The top media & creative skills by downloads are Sag, Antigravity Image Generator, Image. These skills are used by thousands of AI agents and ranked by real community usage data.