native-trigger
native-trigger is a powerful open-source platform designed to simplify workflow automation and provide a seamless experience for developers
Browse AI and ML workflow skills for model integration, prompt engineering, evaluations, and LLM automation across major IDEs.
This directory brings installable AI Agent skills into one place so you can filter by search, category, topic, and official source, then install them directly into Claude Code, Cursor, Windsurf, and other supported environments.
native-trigger is a powerful open-source platform designed to simplify workflow automation and provide a seamless experience for developers
[DEPRECATED] Use /ce:compound instead — renamed for clarity.
Reviews Python code with an extremely high quality bar for Pythonic patterns, type safety, and maintainability. Use after implementing features, modifying code, or creating new Python modules.
Creates or updates README files following Ankane-style template for Ruby gems. Use when writing gem documentation with imperative voice, concise prose, and standard section ordering.
Full autonomous engineering workflow
simple-pr is a Git workflow automation skill that creates a simple PR from staged changes using Git commands
ABP project layer dependency rules - which projects can reference which, domain/application/infrastructure separation, cross-layer violations to avoid. Use when reviewing project structure, adding new
Create a simple PR from staged changes with an auto-generated commit message
Open Source framework for voice and multimodal conversational AI
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in Node.js and browsers (with WebGPU/WASM) using pre-trained models from Hugging Face Hub.
huggingface-jobs is a skill for running general-purpose compute workloads on Hugging Face infrastructure, covering UV scripts, Docker-based jobs, and hardware selection.
huggingface-llm-trainer is a skill for training language models using Transformer Reinforcement Learning on Hugging Face Jobs infrastructure.