Total 57,023 skills, AI & Machine Learning has 9481 skills
Showing 12 of 9481 skills
Autonomous LLM training optimization with GPU support. Runs 5-minute training experiments, measures val_bpb, keeps improvements or reverts — repeat forever. Use this skill when the user asks to "train a model autonomously", "optimize LLM training", "run ML experiments", "autoresearch with GPU", "optimize val_bpb", "autonomous ML training", "LLM pretraining loop", "setup ML autoresearch", "GPU training experiments", "pretrain from scratch", "speed up training", "lower my loss", "GPU optimization", "CUDA training", or mentions "train.py", "prepare.py", "bits per byte", "val_bpb", "NVIDIA GPU training", "RTX training", "H100 training", "autonomous model training", "consumer GPU training", "low VRAM training". Always use this skill when the user wants to autonomously optimize any ML training metric.
Retrieve a GitHub issue using the `gh` CLI, analyze it, and spawn a PM + developer team to address it. Accepts an issue URL, issue number, or `owner/repo#number`.
[QwenCloud] Check for qwencloud-ai updates and notify the user when a new version is available. TRIGGER when: user asks to check for updates, check version, asks 'is there a new version', 'latest version', 'update skills', 'check update', or any other qwen skill delegates to this skill, or user explicitly invokes this skill by name (e.g. use qwencloud-update-check). DO NOT TRIGGER when: non-update-related tasks, general version questions about other software.
Generate AI music or create covers from reference audio. Triggers on: "音乐", "music", "生成音乐", "generate music", "翻唱", "cover", "作曲", "compose", "create a song", "做一首歌".
Use when another skill or agent needs a review panel assembled, retained, or converged — invoked by /review-loop, /plan-review, and code-reviewer, not directly by users.
Design a Zoom MCP workflow for Claude. Use when deciding whether Zoom MCP fits a task, when planning tool-based AI workflows, or when separating MCP responsibilities from REST API responsibilities.
Use when starting a new project with Maestro or when no .maestro.md context file exists yet. Run once per project.
Use chat rooms through the Paseo CLI. Use when the user says "chat room", "room", "coordinate through chat", "shared mailbox", or wants agents to communicate asynchronously.
Systematic debugging with persistent state across context resets
HCCL (Huawei Collective Communication Library) performance testing for Ascend NPU clusters. Use for testing distributed communication bandwidth, verifying HCCL functionality, and benchmarking collective operations like AllReduce, AllGather. Covers MPI installation, multi-node pre-flight checks (SSH/CANN version/NPU health), and production testing workflows.
Use when writing, refining, or structuring prompts for AI-powered app features — system prompts, user prompt templates, few-shot examples, chain-of-thought, prompt versioning, and defensive prompting
Expert image creation and editing using Nano Banana 2 (Gemini 3.1 Flash Image). Use when creating visual content from scratch, editing existing images with delta editing, or needing professional-quality images for any visual purpose. Supports photorealistic photography, artistic styles, logos with advanced text rendering, stickers, product mockups, precise delta editing, and character consistency across generations. Features --image-size control (512/1K/2K/4K) and structured production-grade prompting.