Loading...
Loading...
Found 554 Skills
Visualizes datasets in 2D using embeddings with UMAP or t-SNE dimensionality reduction. Use when exploring dataset structure, finding clusters, identifying outliers, or understanding data distribution.
Discover cross-domain connections across the wiki. Use when the user wants to find analogies, tensions, or surprising links between concepts from different fields, says "explore", "find connections", "what connects", or wants to discover patterns across their wiki, second brain, or knowledge base.
Pathfinder traversal of the knowledge graph starting from a seed entity
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for motivation.
Automate 7-phase feature development with specialized agents (code-explorer, code-architect, code-reviewer). Use for multi-file features, architectural decisions, or encountering ambiguous requirements, integration patterns, design approach errors.
Host simulated panel discussions and debates among AI-simulated domain experts. Supports roundtable, Oxford-style, and Socratic formats with heterogeneous expert personas, anti-groupthink mechanisms, and structured synthesis. Use when exploring complex topics from multiple expert perspectives, testing argument strength, academic brainstorming, or understanding trade-offs in decisions. NOT for one-on-one conversations, simple Q&A, or real-time debates.
Token optimization best practices for cost-effective Claude Code usage. Automatically applies efficient file reading, command execution, and output handling strategies. Includes model selection guidance (Opus for learning, Sonnet for development/debugging). Prefers bash commands over reading files.
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
Use this at session start to discover what CodeCompass can do. Read .ai/capabilities.json for module map (5 domains, 21+ modules) instead of manual Grep/Glob. Apply when: (1) planning tasks, (2) user asks 'What can CodeCompass do?', (3) before implementing features
Explain how something works in this codebase by exploring code and producing a clear architectural explanation. Optionally critique the architecture for issues.
Project setup. Explore the codebase, ask about strategy and aims, write persistent context to AGENTS.md. Run when starting or when aims shift.
Fine-tune Gemma 4 and 3n models with audio, images, and text on Apple Silicon using PyTorch and Metal Performance Shaders.