Scripting skills

This skill helps you master Bash/Linux patterns and commands for efficient scripting, file handling, and process control on macOS and Linux.

This skill helps you write robust PowerShell scripts for Windows by enforcing ASCII-only code, proper parentheses, null checks, and safe error handling.

This skill renders the Jekyll site locally, captures screenshots, and visually verifies CSS and layout changes.

This skill analyzes a codebase and suggests Claude Code automations across hooks, subagents, skills, plugins, and MCP servers to optimize setup.

This skill creates interactive single-file HTML playgrounds with live preview and prompt output to explore topics visually.

This skill helps you learn to create Claude Code plugin skills with a clear structure, activation rules, and examples.

This skill audits and improves CLAUDE.md files across a repo, delivering a quality report and targeted updates upon approval.

This skill helps you manage Lambda Labs GPU Cloud resources for scalable ML training and inference with persistent storage and easy SSH access.

This skill simplifies distributed training with HuggingFace Accelerate, enabling seamless multi-GPU/TPU setups via a four-line integration.

This skill helps you integrate PyTorch FSDP2 into training scripts with correct initialization, sharding, mixed precision, and DTensor-based checkpointing.

This skill guides fine-tuning LLMs with TRL for instruction tuning, preference alignment, and reward-based optimization, aligning models to human feedback.

This skill helps you fine-tune and deploy OpenPI pi0, pi0-fast, or pi0.5 models for robot policy inference across ALOHA, DROID, LIBERO.

This skill helps you implement and train LLMs with LitGPT across 20+ pretrained architectures for clean, production-ready workflows.

This skill provides expert guidance for fine-tuning LLaMA models with Llama-Factory, covering APIs, setup, and best practices for multimodal, 8-bit QLoRA

This skill helps you optimize large-scale LLM training with Megatron-Core, enabling efficient 2B-462B parameter models using advanced parallelism.

This skill helps you train large-scale Mixture of Experts models with DeepSpeed or HuggingFace efficiently, reducing compute while expanding capacity.

This skill speeds high-performance RLHF training for large models with Ray and vLLM acceleration, simplifying distributed PPO GRPO DPO workflows

This skill helps you collect user input via a modal UI to clarify preferences, confirmations, or constraints before acting.

This skill ensures explicit user permission before any file deletion, preventing accidental loss by requiring approval for all delete operations.

This skill provides a structured workflow to debug and verify changes to the forge CLI, speeding fixes without committing.

This skill guides you in creating effective AI skills, outlining workflows, tools, and domain knowledge for reliable, reusable capabilities.