llm — Claude Code skill: LLM training and fine-tuning
A skill that gives your agent ground rules for large language model work: architecture, fine-tuning, training and deployment. Useful when the project is about transformers.
npx skills add Mindrally/skills --skill llm -a claude-codeWhat llm does
The skill turns your agent into an LLM development assistant. It carries a set of principles: understand transformer architectures, use efficient training strategies, apply proper evaluation, optimize inference. The agent leans on those when writing training code or reviewing someone else's.
Specific sections follow. Attention: self-attention, multi-head patterns, positional encodings, context length limits. Tokenization: picking between BPE and SentencePiece, handling special tokens, vocabulary size trade-offs, padding and truncation. Fine-tuning splits two ways — parameter-efficient methods such as LoRA, P-tuning, adapter layers and prefix tuning, versus full fine-tuning with careful learning rates, warmup schedules, gradient checkpointing and regularization.
Infrastructure covers distributed training (DeepSpeed, FSDP, gradient synchronization, checkpoint saving and loading) and memory work (gradient accumulation, mixed precision, activation checkpointing, dynamic batch sizes). Separate sections handle evaluation (perplexity, BLEU, benchmarks, tracking metrics during training) and deployment (quantization, pruning, batched inference, production monitoring). Project structure gets its own part: configs in YAML, data processing kept apart from training, experiment tracking, version control for models and configs. Nothing here is tied to one framework, so it fits a PyTorch or JAX project equally well.
What it helps with
- choose between LoRA and full fine-tuning for a task
- split training of a large model across several GPUs
- work out whether a batch fits in memory and set gradient accumulation
- configure a tokenizer and handle special tokens
- organize configs and experiment tracking in a project
Example prompts for the agent
- help me set up LoRA to fine-tune the model on our dataset
- review my training script — is multi-head attention implemented correctly?
- suggest an FSDP and gradient checkpointing setup that fits in memory
How to install llm
1Skills CLI (Vercel)
npx skills add Mindrally/skills --skill llm -a claude-code2Manually: put the files in place
~/.claude/skills/llm/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/llm/
1Skills CLI (Vercel)
npx skills add Mindrally/skills --skill llm -a codex2Manually: put the files in place
.agents/skills/llm/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Mindrally/skills --skill llm -a cursor2Manually: put the files in place
.cursor/skills/llm/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Mindrally/skills llm2Manually: put the files in place
.github/skills/llm/SKILL.md1Skills CLI (Vercel)
npx skills add Mindrally/skills --skill llm -a gemini-cli2Platform CLI
gemini skills install https://github.com/Mindrally/skills --path llmManually: put the files in place
.devin/skills/llm/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Mindrally/skills --skill llm -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about llm
How do I install llm in Claude?
Run npx skills add Mindrally/skills --skill llm -a claude-code. The skill file then lands at ~/.claude/skills/llm/SKILL.md.
What does the llm skill do?
It gives the agent rules for large language model development: attention architecture, tokenization, fine-tuning, distributed training, evaluation and deployment.
Which platforms support the llm skill?
Claude, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode. Each platform has its own install command.
Source text
SKILL.md · Apache-2.0
--- name: llm description: Large Language Model development, training, fine-tuning, and deployment best practices. metadata: maintainer: Mindrally source: https://github.com/Mindrally/skills --- # LLM Development You are an expert in Large Language Model development, training, and fine-tuning. ## Core Principles - Understand transformer architectures deeply - Implement efficient training strategies - Apply proper evaluation methodologies - Optimize for inference performance ## Model Architecture ### Attention Mechanisms - Implement self-attention correctly - Use multi-head attention patterns - Apply positional encodings appropriately - Understand context length limitations ### Tokenization - Choose appropriate tokenizers (BPE, SentencePiece) - Handle special tokens properly - Manage vocabulary size trade-offs - Implement proper padding and truncation ## Fine-Tuning Techniques ### Parameter-Efficient Methods - Use LoRA for efficient adaptation - Apply P-tuning for prompt optimization - Implement adapter layers - Use prefix tuning when appropriate ### Full Fine-Tuning - Manage learning rates carefully - Implement proper warmup schedules - Use gradient checkpointing for memory - Apply regularization appropriately ## Training Infrastructure ### Distributed Training - Use DeepSpeed for large models - Implement FSDP for memory efficiency - Handle gradient synchronization - Manage checkpoint saving/loading ### Memory Optimization - Apply gradient accumulation - Use mixed precision training - Implement activation checkpointing - Optimize batch sizes dynamically ## Evaluation - Use appropriate metrics (perplexity, BLEU, etc.) - Implement proper benchmark evaluation - Handle evaluation at scale - Track metrics during training ## Deployment - Optimize models for inference (quantization, pruning) - Implement efficient serving solutions - Handle batched inference - Monitor production performance ## Project Structure - Organize configs in YAML files - Separate data processing from training - Implement experiment tracking - Version control models and configs
© Mindrally · Apache-2.0 · Mindrally/skills
