OpenClaw · Skills: Media & design

Map design guidance on color, hierarchy, type, and general cartographic craft.

Converts documents, images, audio, and web pages into Markdown for LLM processing.

Media layer for HyperFrames: resolves music, effects, images, voice, and grades into local files.

Makes short motion graphics where the movement carries the message, from titles to animated maps.

Turns a music track into a beat-synced lyric video, slideshow, or promo.

Generates and edits images using the Nano Banana Pro model, from text or another image.

Generates three different images from one prompt in parallel with Nano Banana Pro.

NVIDIA skill for searching, ingesting, and querying document collections with the NeMo Retriever CLI.

NVIDIA orchestration skill for adapting Nemotron Speech and NeMo ASR to a domain or language.

NVIDIA skill for routing Nemotron Speech NIM tasks across ASR, TTS, and translation.

NVIDIA skill for creating, refining, or fixing real-time voice agents with Pipecat or LiveKit.

NVIDIA skill for softmax fine-tuning of VISTA3D on CT image and label datasets.

NVIDIA skill for computing federated statistics over tabular and image data across NVFLARE sites.

Generates batches of images with the OpenAI Images API and shows them in a gallery.

Transcribes speech to text locally with the Whisper CLI, with no API key.

Transcribes audio files through the OpenAI Audio Transcriptions API using Whisper.

Bundles a prompt with files and gets a second-model review for code work.

NVIDIA skill for generating event videos and building anomaly datasets.

NVIDIA skill for augmenting image attributes and searching images by attribute.

NVIDIA skill for PAIDF augmentation configs and remote Cosmos inference jobs.