Guide for using SLIME (LLM post-training framework for RL Scaling). Use when working with SLIME for reinforcement learning training of language models, including setup, configuration, training execution, multi-turn interactions, custom reward models, tool calling scenarios, or troubleshooting SLIME workflows. Covers GRPO, GSPO, PPO, Reinforce++, multi-agent RL, VLM training, FSDP/Megatron backends, SGLang integration, dynamic sampling, and custom generation functions.

When the user wants to create or update a README.md file for a project. Also use when the user says "write readme," "create readme," "document this project," "project documentation," or asks for help with README.md. This skill creates absurdly thorough documentation covering local setup, architecture, and deployment.

This skill helps you configure and use the Torii indexer for GraphQL queries, real-time subscriptions, and SQL access to your world state.

Generate marketing screenshots of your app using Playwright. Use when the user wants to create screenshots for Product Hunt, social media, landing pages, or documentation.

Configure a Rails project to work with Conductor (parallel coding agents)

This skill helps you implement ERC20 and ERC721 token standards in Dojo using Origami, enabling game currencies, items, and token-based mechanics.

This skill helps you generate Cairo Dojo system contracts that implement game logic, modify models, and emit events.

This skill helps you configure world permissions, manage namespaces and resource ownership to enforce access control in your Dojo world.

This skill writes ezorm YAML schemas for MySQL or MySQLr projects, emitting YAML only and preferring mysqlr by default.

This skill generates Go code from ezorm YAML schemas for mysql and mysqlr using the ezorm CLI, guiding you with exact commands.

This skill writes ezorm YAML schemas for MongoDB, converting domain models into validated YAML with tables, dbnames, and indexes.

This skill creates and refactors AGENTS.md files using progressive disclosure to keep root docs minimal and focused.

This skill quickly generates 2-3 video outline options with titles, cover ideas, and structure design to accelerate your video planning.

This skill automatically announces project milestones using tailored voices to improve awareness and hands-free collaboration across teams.

This skill guides building a type-safe, high-performance backend with ElysiaJS, covering routing, validation, authentication, plugins, and deployment.

This skill performs manual accessibility reviews against WCAG AA, identifying issues and suggesting practical fixes to improve inclusivity.

This skill helps you generate high-quality Xiaohongshu post images by proposing 2-3 design directions before rendering, ensuring alignment.

This skill runs the Ralph autonomous loop to execute prds using git worktrees, coordinating progress and dependencies.

This skill helps you polish video scripts for natural speech by removing formal tone and adding conversational cues, improving on-screen delivery.

This skill helps you generate OpenGraph and Twitter share images for Next.js by applying best-practice layout, fonts, and metadata.

This skill enables a git-swarm workflow where multiple autonomous agents collaboratively develop by pulling tasks, coding, and pushing in parallel.