Total 56,727 skills, AI & Machine Learning has 9435 skills
Showing 12 of 9435 skills
Ultra-compressed communication mode (lite / full / ultra) that cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Use when the user requests "caveman mode", "less tokens", "be brief", or when output budget is tight.
Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.
Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.
MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.
Day-one data bootstrapping for a new brain. Sequences the highest-leverage data sources to go from empty brain to useful brain in one session. Uses ClawVisor for safe credential handling — the agent never holds raw API keys. Covers Gmail import, calendar sync, contacts seeding, X/Twitter archive, conversation imports, and file archives. Use when a user has just finished gbrain setup and asks "now what?"
ML trading signal classifiers using XGBoost and LightGBM with walk-forward validation, SHAP feature importance, and threshold optimization
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
Compress an agent's routing file (RESOLVER.md or AGENTS.md) by converting granular skill-per-row tables into functional-area dispatchers. Each area lists sub-skills in a "(dispatcher for: ...)" clause. The LLM reads one area entry and routes to the correct sub-skill. Proven via held-out A/B eval: dispatcher pattern outperforms naive pipe-table compression.
AI-powered portfolio risk management and optimization. Use when sizing positions, managing portfolio allocation, calculating risk metrics (VaR, Sharpe), rebalancing, or implementing defensive strategies. Covers: position sizing, correlation analysis, drawdown management, dynamic rebalancing, kill switches.
Automate Cheat Engine memory analysis, reverse engineering, and debugging using AI through MCP protocol
Use OpenAI Codex CLI through MCP to get AI-powered code analysis, generation, review, and web search directly in your editor
在 AntiGravity 連接 NotebookLM MCP。說「連接 NotebookLM」「設定 NotebookLM」時載入。