families / media
media
3d-scene-creation
A set of skills for generating, viewing, and refining 3D environments and assets.
These skills differ by their specific function in the 3D pipeline, ranging from asset generation and texturing to spatial layout and camera visualization.
- Generate a 3D model of a rusty sword and apply a patina texture to it.
- Create a walkable 3D room and generate orbit views from different angles.
ai-media-generation
A collection of skills for creating and editing visual media, including images and videos, using various AI models and platforms.
These skills differ by the specific AI model or platform they utilize (e.g., Gemini, GPT, Luma, Kling) and the type of output they produce (static images vs. video clips).
- Generate a photorealistic image of a cyberpunk city using the GPT-Image model.
- Create a short video clip of a dancing robot using the Luma video generator.
audio-processing-and-analysis
A collection of tools for manipulating, analyzing, and extracting data from audio files, including processing, subtitle generation, and speaker identification.
These skills focus on the technical manipulation and analysis of audio data (processing, extraction, and metadata) rather than the creative generation of audio content or the management of playback devices.
- Extract the audio track from a video file and convert it to MP3 format.
- Generate SRT subtitles from a podcast recording and identify distinct speakers in the conversation.
digital-avatar-video-generation
A set of skills for creating various types of video content featuring digital avatars, including keyframe animations, shopping demonstrations, and talking head presentations.
The skills differ by the specific narrative or functional context of the avatar, such as general keyframe animation, e-commerce shopping scenarios, or direct speech delivery.
- Generate a 10-second video of a digital avatar walking through a virtual store to showcase new products.
- Create a talking avatar video where a character explains the features of a software update.
blender-3d-workflow
A collection of specialized skills for creating, animating, and rendering 3D content within the Blender software environment.
The skills differ by their specific focus within the Blender pipeline, ranging from procedural modeling with geometry nodes and hard-surface techniques to character-specific tasks like hair and animation, as well as pre-production and final rendering stages.
- Create a procedural hair system for a character using particle systems and modifiers.
- Set up a cinematic lighting rig and render settings for a final product shot.
camera-capture-and-processing
A set of skills for capturing images via camera APIs and applying post-capture processing or re-photography effects.
camera-api handles low-level hardware access, camsnap focuses on quick snapshot capture, and recamera specializes in post-capture image manipulation.
- Take a photo using the device's default camera and save it to the gallery.
- Apply a vintage filter to a recently captured image using the recamera tool.
character-development
A set of skills for creating, referencing, and analyzing fictional characters and their interpersonal dynamics.
These skills differ by focusing on specific aspects of character work, such as general reference data, novel-specific creation, conflict analysis, or identity scenario libraries.
- Generate a detailed backstory and personality profile for a new protagonist in a sci-fi novel.
- Analyze the primary sources of conflict between the two main characters in the provided script.
chinese-opera-music-analysis
Analyzing the structural and melodic frameworks of Chinese opera, specifically focusing on Banqiang and Qu-pai systems.
The skills differ by focusing on specific musical structures (Banqiang vs. Qu-pai) and whether they provide theoretical definitions or concrete case studies.
- Explain the difference between the rhythmic patterns in Banqiang and the melodic modes in Qu-pai.
- Provide case studies illustrating how specific Qu-pai are applied in traditional Peking Opera scenes.
media-content-creation
A suite of tools for generating, formatting, transcribing, and publishing various forms of digital media content.
These skills differ by their specific function in the media pipeline, ranging from raw content generation and transcription to formatting and final distribution.
- Generate a short video clip from a script and publish it to social media.
- Transcribe a Bilibili video and format the text for a blog post.
vss-deploy
A suite of skills for deploying various computer vision and video analysis models within the VSS infrastructure.
These skills differ by the specific type of computer vision or video analysis model being deployed, such as dense captioning, 2D/3D tracking, or video embeddings.
- Deploy the 2D detection and tracking model to the production cluster.
- Set up the video embedding service for the new media processing pipeline.
video-subtitle-generation
A set of skills for automatically generating, formatting, and managing subtitles and captions for video content.
These skills focus specifically on the creation, formatting, and technical handling of text overlays (subtitles/captions) for video, distinct from general video production, visual analysis, or unrelated gaming/medical content.
- Generate SRT subtitles for this MP4 file using the online auto-subtitle generator.
- Convert the existing caption file to a different format and adjust the timing for better readability.
image-generation-and-editing
A collection of tools for creating, modifying, enhancing, and analyzing visual content using various AI models and APIs.
These skills differ by their specific underlying models (e.g., OpenAI vs. Stable Diffusion), primary function (generation vs. compression vs. captioning), and integration method (API vs. local processing).
- Generate a photorealistic image of a cyberpunk city using Stable Diffusion.
- Remove the background from this product photo and replace it with a white studio setting.
azure-ai-voicelive
A set of language-specific SDKs for integrating Azure AI Voice Live real-time speech and audio streaming capabilities.
The skills differ by the programming language SDK (C#, Java, Python, or TypeScript) used to interact with the Azure AI Voice Live service.
- Implement a real-time voice assistant in a Python application using the Azure AI Voice Live SDK.
- Configure a Java service to stream live audio to Azure AI Voice Live for transcription.
media-pipeline-orchestration
A family of skills for managing, processing, and generating media assets through various cloud services and local tools.
These skills differ by their specific role in the media lifecycle, ranging from low-level processing and metadata extraction to high-level library management, cloud transcoding, and AI-driven content generation.
- Process a video file using ffmpeg to extract metadata and convert it to a specific format.
- Manage a media library by indexing new files with seerr-manager and streaming them via media-proxy.
meme-generation
A set of skills for creating, generating, and producing internet memes using various tools and methods.
The skills differ in their specific implementation and output format, with four-meme-ai focusing on AI-generated content, meme-creator on manual or semi-automated creation, and meme-factory on bulk or automated production.
- Create a funny meme using the four-meme-ai tool with a specific caption.
- Generate a batch of memes for a social media campaign using meme-factory.
motion-graphics-production
A suite of skills for designing, directing, and extracting motion graphics and human movement for media production.
These skills differ by their specific role in the motion pipeline, ranging from initial creation and direction to technical extraction and final placement or showreel assembly.
- Create a 10-second animated logo reveal for a tech startup.
- Extract the walking cycle from a video clip to use in a 3D animation.
movie-catalog-management
A set of skills for managing movie entries and their specific versions within a media catalog.
The skills differ by their specific target, with boka-movie and bona-movie handling general movie entries while bona-version focuses on version-specific data.
- Add a new movie entry to the catalog with its basic metadata.
- Update the specific version details for an existing movie record.
music-creation-and-curation
A suite of tools for generating, analyzing, and managing musical content from lyrics to final release.
These skills differ by their specific function in the music pipeline, ranging from AI generation and lyric processing to metadata synchronization and visual media creation.
- Generate a full song from these lyrics using Suno and then sync the metadata to my Discogs account.
- Analyze the structure of this track and create a kinetic music video scenario for it.
news-aggregation-and-synthesis
A set of skills for gathering, filtering, and synthesizing news content from various sources into coherent summaries or articles.
These skills differ in their specific focus on either raw data processing, specific platform digests, alternative news sources, or multi-source editorial writing.
- Create a daily digest of top stories from Hacker News and other tech sources.
- Write a comprehensive news article by combining information from multiple independent news outlets.
product-media-creation
A set of skills for generating visual and written marketing assets specifically for products.
These skills differ by the specific type of media output they produce, ranging from video scripts and photography to general product assistance.
- Write a 30-second script for a commercial featuring our new smartwatch.
- Generate a set of studio-quality product photos for a ceramic mug on a white background.
remotion-video-production
A comprehensive workflow for creating, structuring, and exporting professional videos using the Remotion framework in React.
These skills cover the entire lifecycle of Remotion development, from initial project setup and coding standards to specific features like captions and interactivity, culminating in the final rendering process.
- Create a new Remotion project with animated captions and export it as an MP4.
- Structure a Remotion component to support interactive playback controls and follow best practices for performance.
media-scenario-workflows
A collection of specialized workflows for generating, analyzing, and managing diverse media assets including 3D worlds, audio, and interactive characters.
These skills differ by their specific media modality (3D, audio, text, image) and operational focus (creation, analysis, or updating) within a scenario-based context.
- Generate a consistent 3D world environment and create a matching audio track for a game level.
- Analyze existing game assets for consistency and update a ChatGPT pet character's dialogue.
screenwriting-craft
A collection of skills for developing narrative structure, character arcs, and production workflows in film and television writing.
These skills differ by focusing on specific structural frameworks, genre-specific techniques like sitcom comedy, or collaborative production processes like writers' rooms.
- Outline the three-act structure for a feature film using John Truby's anatomy method.
- Create a season arc for a sitcom that balances episodic comedy with serialized character development.
short-form-video-production
A comprehensive workflow for creating, scripting, and producing short-form video content including Douyin scripts and short dramas.
These skills differ by their specific stage in the short-form video lifecycle, ranging from initial scriptwriting and platform-specific formatting to asset generation, storyboarding, and final production or review.
- Generate a viral Douyin script and corresponding storyboard for a 30-second product teaser.
- Analyze a novel chapter to develop a short drama episode, including character assets and editing instructions.
speech-processing
A collection of skills for converting audio to text and text to audio using various models and APIs.
The skills differ by the specific model or provider used (e.g., Doubao, Qwen, Azure, Whisper) and the direction of conversion (ASR vs TTS).
- Transcribe this meeting recording into a text file using Whisper.
- Generate an audio narration from this script using the text-to-speech skill.
text-to-speech
A collection of skills for converting written text into spoken audio using various local and cloud-based TTS engines.
The skills differ by the specific TTS provider or engine used, such as OpenAI, Doubao, Edge, or local models like Qwen3.
- Generate a voiceover for this marketing script using the OpenAI Audio API.
- Convert this chapter of a novel into an MP3 file using the local Qwen3 TTS model.
unreal-engine-development
A collection of skills for designing, optimizing, and implementing various aspects of game development within the Unreal Engine ecosystem.
The skills differ by their specific focus area within the engine, ranging from core gameplay logic and world construction to technical aspects like lighting, materials, performance, and visual effects.
- Optimize the frame rate of a complex scene by adjusting lighting and material settings.
- Create a realistic water effect using Niagara VFX and integrate it into the level geometry.
chengfeng-video-workflow
A suite of skills for managing the end-to-end video production pipeline using the Chengfeng platform, covering editing, subtitling, visual analysis, and export.
These skills are distinguished by their specific role within the Chengfeng video processing pipeline, ranging from raw editing and subtitle generation to visual analysis and final output management.
- Use chengfeng-cut to trim the intro from my video and then apply chengfeng-subtitle to add Chinese captions.
- Run chengfeng-visual to analyze the scene changes and use chengfeng-export to save the final file in MP4 format.
voice-synthesis-and-persona
A collection of skills for generating, cloning, and configuring synthetic voice outputs and personas.
These skills focus on the creation and manipulation of audio voice assets, distinguishing them from transcription or general media handling.
- Clone a specific voice sample to create a custom persona for an audiobook.
- Generate a daily motivational quote using a selected voice persona.
youtube-content-creation
A comprehensive suite of skills for planning, scripting, optimizing, and managing YouTube video content from ideation to publication.
These skills focus on the creative and strategic production of YouTube content, distinguishing them from utility tools like video-downloader or bottube which handle file retrieval or general bot management.
- Write a script and generate an SEO-optimized title and description for a new tech review video.
- Analyze the retention data of my last three videos and suggest chapter markers to improve viewer engagement.