Video editing, thumbnails, comics, and audio (3.2K skills)
Generate photos, illustrations, concept art, and presentation assets from text, or edit existing images with specific instructions. Choose among supported OpenRouter models and save the result as a PNG file at a specified location.
Control NVIDIA Broadcast effects for cameras, microphones, and speakers through MCP, an agent connection interface. Apply effects to local media files, switch devices, adjust camera resolution, and check the current effect settings.
Generate videos from DEFT media samples using PAIDF Cosmos Predict. Prepare configuration, run generation in Docker, avoid repeated processing of duplicate media paths, and produce JSONL records linking each original sample ID to successful or missing video outputs.
Plan, run, and verify Jetson video encoding, decoding, transcoding, and segment workflows using NVIDIA samples or PyNvVideoCodec. It checks file hashes, byte sizes, frame counts, and logs to confirm that each stage consumes the preceding stage’s output.
Calibrate multiple cameras from recorded MP4 files through the AutoMagicCalib REST API. The skill handles project creation, uploads, input verification, progress checks, and evaluation when reference data is supplied, with optional VGGT refinement.
Create images and videos with Wan27 through MCP tools or its CLI. Check available models and credits, estimate generation costs for approval, then track tasks and retrieve completed files or download links.
Make phone calls with Bland AI, turn text into speech with ElevenLabs, and transcribe audio with Groq Whisper. Commands return call status and transcripts, save generated audio files, or print text from an existing recording.
Analyze local video and image files through the Qwen API to get written descriptions of motion, scene changes, or visible elements. The bridge also supports batch video classification, follow-up questions, and structured JSON output.
Extract titles, authors, likes, and tags from Douyin share links, or transcribe Chinese speech from local video files. Local transcription produces a saved text file and timestamped segments for reviewing the spoken content.
Clean up raw YouTube recordings through the Tubeify API by removing silent gaps and filler words such as “um” and “uh.” Submit a video URL, track processing, and download the trimmed video when it is ready.
Create animated GIFs and emoji for Slack by combining movements such as bouncing, shaking, and rotating. Included tools assemble frames, reduce file size, and check dimensions and size limits for message and emoji use.
Transcribe voice files, including WeChat .silk messages, and create spoken replies using six Chinese voice personas. Generate MP3 audio, produce persona-styled text, or convert replies into the voice format used by WeChat.
Save individual YouTube videos with a chosen quality and file format, or download just the audio as MP3. Set a destination folder and choose from MP4, WebM, and MKV video formats.
Find an image model in MuAPI’s current catalog, then submit one image generation request after explicit cost confirmation. Check progress within a fixed polling limit and optionally download the completed image.
Find a Kavel tool for transforming a photo while preserving the face or subject. Get a tailored prompt and generation link for hairstyle changes, figurine images, pet portraits, photo restoration, or dance videos.
Improve screenshots and digital images by increasing resolution, sharpening details, and reducing compression noise. Prepare clearer visuals for documents, presentations, blogs, or social posts, with support for processing entire folders.
Create e-commerce images from product photos, including main listings, detail images, and products placed in scenes. Add brand text and logos, check image quality, adapt sizes for sales platforms, and package files for delivery.
Search and organize a self-hosted Immich photo library through conversation. Find images by description or visible text, curate location albums, detect duplicates, manage faces, repair metadata, and export PDF photobooks while originals stay on your server.
Find Atlas Cloud image and video models, check their current input requirements and prices, and submit one confirmed generation request. The skill checks progress at fixed intervals with a maximum number of checks and returns generated media URLs.
Use local Qwen-Image 2.1 workflows to generate adult images or change character poses. Combine LoRAs, specialized model add-ons, with 3D mannequin references or a pose library, and save images with their generation settings.
Create a rough cut of a spoken video using timestamped speech recognition. It removes redundant content, checks that the remaining speech flows and sentences are complete, and renders the edit while preserving the original audio.
Connect video clips with AI-generated transition footage. The workflow can select and arrange clips, add background music, and render a finished video through a dedicated timeline, with user confirmation before generating all transitions together.
Turn video editing preferences into a reusable skill document. It identifies patterns in pacing, sound, and visual choices, confirms the summary with the user, and saves editing instructions for an agent to follow in future work.
Run an installed OpenStoryline setup to edit local footage through conversation. Start services, submit editing requests, continue revisions in the same session, and check the generated MP4 files and their paths.