Total 50,524 skills, AI & Machine Learning has 8481 skills
Showing 12 of 8481 skills
Orchestrates multi-advisor council debates on high-impact architecture, technology, or product decisions. Dispatches 3-5 domain archetype subagents (pragmatic-engineer, architect-advisor, security-advocate, product-mind, devils-advocate, the-thinker) through opening statements, tensions, position evolution, and synthesis phases. Preserves dissent and delivers actionable recommendations with captured risks. Use when evaluating trade-offs, stress-testing a PRD or tech spec, resolving dilemmas with multiple viable options, or when a decision needs diverse expert perspectives. Don't use for simple yes/no questions, factual lookups, creative brainstorming without tradeoffs, or tasks where a single expert perspective suffices.
Purge the context-mode knowledge base. Permanently deletes all indexed content and resets session stats. This is destructive and cannot be undone. Trigger: /context-mode:ctx-purge
Run a structured multi-perspective council on a hard decision, design choice, debugging question, strategy problem, or tradeoff. Use when the user wants multiple viewpoints, explicit cross-examination, and a compact final verdict.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch for Claude Code or Cursor, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
SSH into host `h100_sglang`, enter Docker container `sglang_bbuf`, work in `/sgl-workspace/sglang`, and use the ready H100 remote environment for SGLang development and validation. Use when a task needs remote CUDA work, GPU-backed smoke tests, diffusion checks, or a safe remote copy instead of local-only execution.
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
CuTe Python DSL API reference and implementation patterns for NVIDIA GPU kernel programming. Provides execution model, core API table, key constraints, common patterns, and documentation index. Use when: (1) writing or modifying CuTe DSL kernel code, (2) looking up CuTe DSL API syntax, (3) implementing attention/GEMM/MLA patterns in CuTe DSL, (4) understanding CuTe DSL execution model and compilation pipeline, (5) checking what CuTe DSL can and cannot do.
Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (Codex GPT-5.4 xhigh), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.
AI-powered web search via Exa with content extraction. Use when user says "exa search", "web search with content", "find similar pages", or needs broad web results beyond academic databases (arXiv, Semantic Scholar).
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports. Uses a fresh cross-model reviewer with web/DBLP/arXiv lookup to catch hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations (cite present but the cited paper does not establish the claim). Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.