Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
SpatialData framework for handling spatial multi-modal and multi-scale data. Use this skill for questions about spatial omics data analysis, visualization, and the SpatialData Python ecosystem.
Generate sport-specific memes from games/moments. Current event reactive content, popular templates, team/player inside jokes.
Generate production-ready SSML scripts for Google Cloud TTS
Start the TTS server in HTTP mode for audio generation
Stop the TTS server
Configure ADK bidi-streaming for real-time multimodal interactions. Use when building live voice/video agents, implementing real-time streaming, configuring LiveRequestQueue, setting up audio/video pr…
This skill should be used when the user asks to rewrite content, transform style, check style consistency, or imitate writing style. It provides multi-channel content rewriting, style consistency chec…
Generate accurate summaries of long documents and text collections
Many turns in one call. Instant communication. No round-trips.
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time ap…
AI-powered intelligence for building Stacks blockchain applications with 40 production code examples
RAG-first ORCHESTRATOR startup. Minimal context (~500 tokens), queries RAG on-demand. Token-efficient alternative to startupO.
Build narrative capture and sharing into the system.
Creates well-organized study notes from any content. Use when the user asks for study notes, learning summaries, revision materials, or wants to understand a topic for studying.
Coordinate all subagents in the Physical AI & Humanoid Robotics textbook project. Assign tasks, validate outputs, and track progress to determine eligibility for extra points and reusable intelligence…
Summarize robotics-related text, research papers, or lecture notes into concise, clear, and structured summaries. Use when user asks to condense or simplify robotics content.
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time ap…
Dynamically create tools and consult peer agents for enhanced capabilities
Run Stanford STORM (knowledge-storm) to generate comprehensive, Wikipedia-style articles with citations. Requires LLM and Search API keys (Bing or You.com).
Generate and manage static audio files for Bob The Skull using ElevenLabs TTS. Use when creating greetings, startup messages, error responses, or test audio. Handles generation, naming, directory stru…
Video streaming expert. Use for questions related to 'CCTV', 'HLS', 'WHEP', 'streaming', 'video'.
Analyze multiple assets and define a unified visual style guide. Use when images don't match, assets come from different sources, or need to regenerate consistent variants. Outputs style guides with l…
Propose the most suitable LLM model based on the content of the next task (coding, research, refactoring, etc.)
Summarize robotics-related text, research papers, or lecture notes into concise, clear, and structured summaries. Use when user asks to condense or simplify robotics content.