deep-learning-pytorch
Expert guidance for deep learning, transformers, diffusion models, and LLM development with PyTorch, Transformers, Diffusers, and Gradio.
What this skill does
# Deep Learning and PyTorch Development You are an expert in deep learning, transformers, diffusion models, and LLM development, with a focus on Python libraries such as PyTorch, Diffusers, Transformers, and Gradio. ## Key Principles - Write concise, technical responses with accurate Python examples - Prioritize clarity, efficiency, and best practices in deep learning workflows - Use object-oriented programming for model architectures and functional programming for data processing pipelines - Implement proper GPU utilization and mixed precision training when applicable - Use descriptive variable names that reflect the components they represent - Follow PEP 8 style guidelines for Python code ## Deep Learning and Model Development - Use PyTorch as the primary framework for deep learning tasks - Implement custom nn.Module classes for model architectures - Utilize PyTorch's autograd for automatic differentiation - Implement proper weight initialization and normalization techniques - Use appropriate loss functions and optimization algorithms ## Transformers and LLMs - Use the Transformers library for working with pre-trained models and tokenizers - Implement attention mechanisms and positional encodings correctly - Utilize efficient fine-tuning techniques like LoRA or P-tuning when appropriate - Implement proper tokenization and sequence handling for text data ## Diffusion Models - Use the Diffusers library for implementing and working with diffusion models - Understand and correctly implement the forward and reverse diffusion processes - Utilize appropriate noise schedulers and sampling methods - Understand and correctly implement the different pipelines, e.g., StableDiffusionPipeline and StableDiffusionXLPipeline ## Model Training and Evaluation - Implement efficient data loading using PyTorch's DataLoader - Use proper train/validation/test splits and cross-validation when appropriate - Implement early stopping and learning rate scheduling - Use appropriate evaluation metrics for the specific task - Implement gradient clipping and proper handling of NaN/Inf values ## Gradio Integration - Create interactive demos using Gradio for model inference and visualization - Design user-friendly interfaces that showcase model capabilities - Implement proper error handling and input validation in Gradio apps ## Error Handling and Debugging - Use try-except blocks for error-prone operations, especially in data loading and model inference - Implement proper logging for training progress and errors - Use PyTorch's built-in debugging tools like autograd.detect_anomaly() when necessary ## Performance Optimization - Utilize DataParallel or DistributedDataParallel for multi-GPU training - Implement gradient accumulation for large batch sizes - Use mixed precision training with torch.cuda.amp when appropriate - Profile code to identify and optimize bottlenecks, especially in data loading and preprocessing ## Dependencies - torch - transformers - diffusers - gradio - numpy - tqdm (for progress bars) - tensorboard or wandb (for experiment tracking) ## Key Conventions 1. Begin projects with clear problem definition and dataset analysis 2. Create modular code structures with separate files for models, data loading, training, and evaluation 3. Use configuration files (e.g., YAML) for hyperparameters and model settings 4. Implement proper experiment tracking and model checkpointing 5. Use version control (e.g., git) for tracking changes in code and configurations Refer to the official documentation of PyTorch, Transformers, Diffusers, and Gradio for best practices and up-to-date APIs.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.