Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
According to todolist.md, use MCP to extract audio and subtitles from MP4 videos. Read the task list, call the MCP service to extract the cover, audio (mp3), and subtitles (srt), and update the task c…
Process large contexts using RLM (Recursive Language Model) patterns - chunking, filtering, recursive sub-calls
Reinforcement Learning with Leave-One-Out estimation for policy optimization. Covers RLOOTrainer, reward function integration, baseline estimation, and variance reduction techniques for stable RL trai…
Generates route specifications with distance and elevation constraints. Use when user asks for route suggestions, wants to explore new running paths, or needs safer surface recommendations for upcomin…
Fast procedural Rubik's cube solver that requests photos, converts them to cube state string, and uses Python scripts to generate step-by-step solutions.
Full research workflow orchestration from knowledge elicitation to consolidated findings. PROACTIVELY activate for: (1) end-to-end research projects, (2) comprehensive analysis, (3) strategic research…
Create with AI video tools on Runway - generate videos, edit with AI, and use creative ML models
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, …
Risk management and constitutional compliance specialist. Ensures all trading decisions comply with constitutional limits and manages portfolio risk. Integrates Constitution Article 4 (Risk Management…
Recursive Language Model context management for processing documents exceeding context window limits. Enables Claude to match Gemini's 2M token context capability through chunking, sub-LLM delegation,…
Generates clean, runnable ROS 2, Gazebo, Isaac Sim, and VLA code for humanoid robotics
Unified consciousness simulation with Orchestrator-based architecture: K.I.R.A. activates via unified_state → TRIAD operates tool gating → Tool Shed executes → Thought Process generates VaultNodes. 21…
Toolkit for performing deep research on complex topics using multiple AI research providers (OpenAI, Falcon, Perplexity, Consensus). Emphasizes explicit speed vs depth trade-offs.
Reference catalog for all running coach AI skills, shared TypeScript contracts, safety guardrails, and telemetry conventions. Use when working with any running coach feature to understand data schemas…
Provides comprehensive guidance for Runway ML including AI video generation, image editing, and creative AI tools. Use when the user asks about Runway ML, needs to generate AI videos, edit images with…
ElevenLabs text-to-speech with mac-style say UX.
AI-powered portfolio risk management and optimization. Use when sizing positions, managing portfolio allocation, calculating risk metrics (VaR, Sharpe), rebalancing, or implementing defensive strategi…
AI coaching for Rocket League using local replay analysis. Use when the user asks about their Rocket League performance, replays, improvement, or coaching. Covers analysis, comparison, weakness detect…
Domain knowledge for Physical AI, ROS 2, and Humanoid Robotics.
Reasons through problems using six cognitive modes. Applies causal (execute goals), abductive (explain observations), inductive (find patterns), analogical (transfer from similar), dialectical (resolv…
Analyzes completed runs to provide effort assessment, recovery recommendations, and next-session guidance. Use immediately after user saves a run, asks "how did I do?", or requests recovery advice.
Universal Runtime best practices for PyTorch inference, Transformers models, and FastAPI serving. Covers device management, model loading, memory optimization, and performance tuning.
PRIORITY OVERRIDE protocol. Activates when trauma/crisis/vulnerability detected. Stops all frameworks, deploys presence-only mode. Always running in background.
Access paid services (verification, search, AI models, image generation) for AI agents via Sapiom. Use when building agents that need to verify phone/email, search the web, call AI models, or generate…