Browse Skills

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) with SAELens to decompose neural network activations into interpretable features. Use for discovering features, analyzing superposition, or studying monosemantic representations.

Provides guidance for implementing agentic reinforcement learning (RL) using Meta's torchforge library. Use when you need clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Provides expert guidance for fine-tuning large language models with Unsloth, achieving 2-5x faster training and 50-80% less memory using LoRA/QLoRA optimization. Use when implementing, debugging, or learning best practices for Unsloth.

Verl RL Training provides guidance for training LLMs with reinforcement learning using verl. Use it when implementing RLHF, GRPO, PPO, or other post-training algorithms at scale with flexible backends.

Reproduce an EmDash admin UI bug. Boots a demo with bgproc, drives the admin with agent-browser using the dev-bypass session, and captures the reproduction as screenshots plus a written transcript.

Adversarial code review that assumes bugs exist and hunts for them. Use to audit code for correctness, stress-test pull requests, or when you need a hostile reviewer to find every flaw.

Use agent-browser to interact with web UIs, verify visual changes, fill forms, and capture screenshots directly from the command line.

Building EmDash Site helps you build and customize EmDash CMS sites on Astro. Use it for pages, collections, seed files, Portable Text, menus, taxonomies, widgets, deployment, and other site tasks.

Learn to build and customize EmDash CMS sites on Astro, covering schema design, content querying, Portable Text, caching, menus, taxonomies, widgets, deployment, and more.