Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Deep expertise in ML/CV model selection, training pipelines, and inference architecture. Use when designing machine learning systems, computer vision pipelines, or AI-powered features.
Anthropic Claude API for AI models with tool use and extended context.
Mistral AI API for models like large/medium/small, with function calling and code generation.
Handles vector databases for efficient storage and querying of high-dimensional vectors in AI/ML applications.
Music/song recognition via audio fingerprint: identify playing music, get metadata, Shazam-like
This skill should be used when auditing or comparing Claude Code and Cursor IDE configurations to identify feature gaps, equivalencies, and migration opportunities. Useful when managing AI development…
Cognitive Governance is the God-Mode protocol that implements deep, unblockable
Model optimization is process of improving machine learning models for
Generate web assets including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn. Use when users need icons, favicons, social sharing im…
Google Gemini API for Pro/Flash/Ultra models with 1M token context.
xAI Grok API: OpenAI-compatible at api.x.ai/v1, grok-3/grok-3-mini for fast AI reasoning
Enables real-time detection and tracking of hand gestures using computer vision in AR/VR environments.
Generate polished, self-contained visual explainers, reviews, diagrams, dashboards, comparison pages, and slide-mode HTML from technical or business inputs. Use when the user asks for a diagram, archi…
This skill should be used when the user wants to initialize voice-to-text configuration for the current project. Creates a voice.json config file and generates project-specific vocabulary and context …
Data augmentation is a technique used to artificially increase size and
This skill provides comprehensive guidance on implementing guardrails
Cohere API for embeddings, RAG, reranking, and semantic search.
Perplexity Sonar API for real-time web answers, citations, and search-augmented LLM.
MLflow is an open-source platform for managing the machine learning lifecycle, including tracking, packaging, and deploy
BluOS speaker control: play/pause/volume, multi-room audio, source selection, presets
Model comparison benchmark for generating an SVG image.
De novo protein binder design pipeline -- autonomous backbone generation, sequence design, and multi-metric validation. Use when asked to "design a binder", "create a protein binder", "de novo binder …
This skill covers **when and how** to scale training beyond a single
This is an **alias skill** so requirements/docs can reference `06-ai-ml-production/llm-serving`.