AYastrebov

End-to-end deployment of the docker-amneziawg AmneziaWG VPN container to a VPS or any compatible Linux host. Use this skill whenever the user wants to deploy, install, set up, provision, launch, or "go live" with this container — including on fresh Ubuntu/Debian/Fedora/Rocky/Alma/Arch hosts, cloud VPS (Hetzner, DigitalOcean, Linode, OVH, AWS EC2, etc.), or their own server. Trigger even if the user only says things like "set this up on my server", "I have a VPS, what now?", "help me install this", "run this on my Hetzner box", "spin up the VPN", or just "deploy". The skill checks OS/Docker/Compose/kernel requirements, installs missing pieces, opens firewall ports, configures sysctls, gathers user settings (server URL, port, peers, DNS, AllowedIPs), generates AmneziaWG obfuscation parameters, writes a docker-compose.yml, pulls the image, brings the stack up, and prints peer configs/QR codes.

Development skill for the docker-amneziawg project - an AmneziaWG VPN container with LinuxServer.io architecture. Use when working in the docker-amneziawg repository for: (1) Adding features or fixing bugs, (2) Modifying s6-overlay services, (3) Updating config generation, (4) Working with AmneziaWG obfuscation parameters, (5) Testing or building the Docker image. Triggers when working in a directory containing this project's structure (root/etc/s6-overlay, awg-related files).

Guide for integrating the Volvo Kotlin API library into a project. Use this skill when the user wants to add Volvo vehicle API support to their app, set up the Gradle dependency, configure authentication (OAuth2 or test tokens), make API calls to Volvo Connected Vehicle/Energy/Location endpoints, handle errors, or query vehicle data like location, fuel, battery, door locks, or remote commands. Also trigger when the user asks about Volvo API setup, VCC API key, Volvo ID tokens, or how to call any Volvo vehicle endpoint from Kotlin.

Development guide for the Volvo Kotlin API library — a Kotlin Multiplatform client for Volvo Vehicle APIs (Connected Vehicle, Energy, Location). Use this skill when adding new API endpoints, fixing bugs, writing tests, updating models, modifying the HTTP transport layer, working with OAuth2 authentication, or making any changes to the volvo-api-core or volvo-api-client modules. Also trigger when the user mentions Volvo API, vehicle commands, VIN, energy state, or any Ktor client configuration in this project.

Bridge astronomy-engine and Three.js for solar-system visualizations — positions, orbits, rotations, phases, and coordinate transforms.

Three.js 3D graphics framework — scene setup, geometry, materials, textures, lighting, animation, shaders, post-processing, interaction, and asset loading. Use as the entry point for any Three.js-related task; delegate specifics to the related skills below.

Build llama.cpp from source, run local LLM inference with GPU acceleration, and configure coding agents to use local models. Use this skill whenever the user wants to: compile llama.cpp, set up local AI inference, run GGUF models locally, configure llama-server or llama-cli, create model launcher scripts, work with Unsloth quantized models, or connect coding tools (Claude Code, opencode, pi.dev, Continue, Cursor) to a local llama.cpp server. Triggers on mentions of llama.cpp, GGUF, local LLM serving, Metal/ROCm/HIP/CUDA GPU backends, model quantization (Q4, Q3, IQ3, Q8, etc), MTP/Multi-Token Prediction, or running models from Hugging Face locally. Also triggers when the user asks about using local models with Claude Code, opencode, pi.dev, or any OpenAI-compatible API client.

Configure OpenCode with NeuralWatt as a cloud AI provider. Use this skill when the user wants to set up NeuralWatt, add Kimi/GLM/Qwen/Devstral cloud models to OpenCode, configure the NeuralWatt provider block, install the nw-usage energy script, or connect OpenCode to NeuralWatt's API. Invoke whenever the user mentions NeuralWatt, wants to add cloud models to OpenCode, or asks about configuring Kimi K2.6, GLM 5.1, Qwen, or Devstral via NeuralWatt — even if they don't use the word "NeuralWatt" explicitly.

Guide for integrating and using the KTelegram library in Kotlin projects. Use this skill whenever someone asks how to add KTelegram as a dependency, set up a Telegram bot, handle updates, process commands, use inline keyboards, send messages/photos/polls, configure webhooks, or write bot logic. Trigger on: "create a telegram bot", "set up ktelegram", "add telegram dependency", "how to use ktelegram", "telegram bot example", "handle telegram updates", "send telegram message", "telegram webhook setup", "telegram inline keyboard", "telegram command handler", "poll for updates", "callback query", or any question about building a bot with this library.

Expert skill for developing the KTelegram library — a Kotlin Multiplatform Telegram Bot API client. Use this skill whenever working on /Users/Andrey.Yastrebov/IdeaProjects/KTelegram or when the user mentions KTelegram, Telegram Bot API types, Telegram bot methods, or wants to add/update Telegram API coverage. Also trigger when the user says "add sendX method", "new Telegram type", "update Bot API", "telegram model", or references the Telegram Bot API changelog. Covers: adding new API types and methods, fixing bugs, writing tests, maintaining serialization consistency, updating documentation, and releasing new versions.