Total 55,449 skills, AI & Machine Learning has 9217 skills
Showing 12 of 9217 skills
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Vercel AI SDK for building chat interfaces with streaming. Use when implementing useChat hook, handling tool calls, streaming responses, or building chat UI. Triggers on useChat, @ai-sdk/react, UIMessage, ChatStatus, streamText, toUIMessageStreamResponse, addToolOutput, onToolCall, sendMessage.
Generate images and videos using Kling AI API. Use when creating AI-generated images from text prompts, converting images to videos, or generating videos from text descriptions.
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.
Help users evaluate emerging technologies. Use when someone is assessing new tools, making build vs buy decisions, evaluating AI vendors, or deciding on technical architecture.
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and control, using vectorized environments for parallel training, and integrating with deep RL workflows. This skill should be used when users request RL algorithm implementation, agent training, environment design, or RL experimentation.
Perform 12-Factor Agents compliance analysis on any codebase. Use when evaluating agent architecture, reviewing LLM-powered systems, or auditing agentic applications against the 12-Factor methodology.
Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.
Advanced metacognitive dialogue skill with cross-session accumulation. Builds a meta-profile of hypotheses about your thinking patterns, detects when patterns break (more valuable than confirmation), and includes frame-health safeguards against self-negation and direction errors. Hypothesis-first approach — challenges before confirms. 세션 간 축적형 메타인지 대화 스킬. 가설 기반 메타 프로필을 누적하고, 패턴 깨짐을 감지하며, 자기부정/방향오류 안전장치를 포함합니다. 확인보다 도전을 먼저 하는 대화 방식.
Concurrent investigation of independent failures. Use when multiple unrelated issues need parallel resolution.
Modo Elite Coder + UX Pixel-Perfect otimizado especificamente para Gemini 3.1 Pro High. Workflow completo com foco em qualidade máxima e eficiência de tokens.