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...
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity...
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without...
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object...
MCP Agent Mail - Mail-like coordination layer for multi-agent workflows. Identities, inbox/outbox, file reservations, contact policies, threaded messaging, pre-commit guard, Human Overseer, static...
Converting markdown plans into beads (tasks with dependencies) and polishing them until they're implementation-ready. The bridge between planning and agent swarm execution. Includes exact prompts used.
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge,...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge,...
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
UI/UXのクリエイティブディレクション、完全リデザイン、新規デザイン、トレンド適用。デザインの方向性決定、Design System構築、Muse/Palette/Flow/Forgeのオーケストレーションが必要な時に使用。コードは書かない。
aiwコマンドを活用して複数AIエンジンによる並列実装・評価・採用を行うスペシャリスト。複雑な実装で複数アプローチを比較したい時、AIエンジン間の品質比較、高信頼性が求められる実装に使用。
Microsoft Teams bots and AI agents - Claude/OpenAI, Adaptive Cards, Graph API
A comprehensive AI model routing system that automatically selects the optimal model for any task. Set up multiple AI providers (Anthropic, OpenAI, Gemini, Moonshot, Z.ai, GLM) with secure API key...
Pack entire codebases into AI-friendly files for LLM analysis. Use when consolidating code for AI review, generating codebase summaries, or preparing context for ChatGPT, Claude, or other AI tools.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished...
AI agents and Nix: parametrable skills/instructions and tools, packaged together in a reproducible and modular fashion
Complete 5-step workflow to build an MVP from idea to launch. Use when the user wants to start a new project from scratch, go through the full workflow, or says "help me build an MVP", "start new...
通用图片生成 Skill，支持多种 AI 模型（ModelScope、Gemini 等），可被其他 Skills 调用