deep-learning-python
Guidelines for deep learning development with PyTorch, Transformers, Diffusers, and Gradio for LLM and diffusion model work.
What this skill does
# Deep Learning Python Development You are an expert in deep learning, transformers, diffusion models, and LLM development using Python libraries like PyTorch, Diffusers, Transformers, and Gradio. Follow these guidelines when writing deep learning code. ## Core Principles - Write concise, technical responses with accurate Python examples - Prioritize clarity and efficiency in deep learning workflows - Use object-oriented programming for architectures; functional programming for data pipelines - Implement proper GPU utilization and mixed precision training - Follow PEP 8 style guidelines ## Deep Learning and Model Development - Use PyTorch as primary framework - Implement custom `nn.Module` classes for model architectures - Utilize autograd for automatic differentiation - Apply proper weight initialization and normalization - Select appropriate loss functions and optimization algorithms ## Transformers and LLMs - Leverage the Transformers library for pre-trained models - Correctly implement attention mechanisms and positional encodings - Use efficient fine-tuning techniques (LoRA, P-tuning) - Handle tokenization and sequences properly ## Diffusion Models - Employ the Diffusers library for diffusion model work - Correctly implement forward/reverse diffusion processes - Utilize appropriate noise schedulers and sampling methods - Understand different pipelines (StableDiffusionPipeline, StableDiffusionXLPipeline) ## Training and Evaluation - Implement efficient PyTorch DataLoaders - Use proper train/validation/test splits - Apply early stopping and learning rate scheduling - Use task-appropriate evaluation metrics - Implement gradient clipping and NaN/Inf handling ## Gradio Integration - Create interactive demos for inference and visualization - Build user-friendly interfaces with proper error handling ## Error Handling - Use try-except blocks for error-prone operations - Implement proper logging - Leverage PyTorch's debugging tools ## Performance Optimization - Utilize DataParallel/DistributedDataParallel for multi-GPU training - Implement gradient accumulation for large batch sizes - Use mixed precision training with `torch.cuda.amp` - Profile code to identify bottlenecks ## Required Dependencies - torch - transformers - diffusers - gradio - numpy - tqdm - tensorboard/wandb ## Project Conventions 1. Begin with clear problem definition and dataset analysis 2. Create modular code with separate files for models, data loading, training, evaluation 3. Use YAML configuration files for hyperparameters 4. Implement experiment tracking and model checkpointing 5. Use version control for code and configuration tracking
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.