Creates Infrahub transforms that convert data into JSON, text, CSV, or device configs using Python or Jinja2 templates. TRIGGER when: building config generation, data export, format conversion, Jinja2 templates, artifact pipelines. DO NOT TRIGGER when: designing schemas, writing validation checks, creating generators, querying live data.
Guide for migrating components from experimental to stable locations (components/, sds/, ui/). Trigger when the user wants to migrate, promote, or move an experimental component, or asks about deprecating experimental exports.
Добавление файловых вложений (компонент СписокФайлов) к существующему объекту конфигурации 1С:Элемент. Поддерживает 4 паттерна: P1 — стандартные вложения через встроенный реквизит Файлы (новых реквизитов нет); P2 — одиночный файл (ДвоичныйОбъект.Ссылка?, макс. 1); P3 — категория файлов (Массив<ДвоичныйОбъект.Ссылка> с лимитами и фильтрами); P4 — несколько категорий (несколько P3). Вызывай когда пользователь хочет добавить вложения, загрузку файлов, скан договора, логотип, прикреплённые документы к справочнику или документу. НЕ для работы с изображениями (используй xbsl-image-add).
Optimizes text, prompts, and documentation for LLM token efficiency. Applies 41 research-backed rules across 6 categories: Claude behavior, token efficiency, structure, reference integrity, perception, and LLM comprehension. Use when optimizing prompts, reducing tokens, compressing verbose docs, or improving LLM instruction quality.
Optimizes text and docs for LLM token efficiency. Use when - optimizing prompts, reducing tokens, compressing text, condensing verbose content, encoding for CLAUDE.md, compressing for context/prompt/LLM. Trigger keywords - optimize, reduce tokens, compress, condense, slim, tighten, too verbose, shrink, encode, deep compress, deep encode, super compress, maximum compress.
Maintain a repo-local learning scratchpad that compounds improvements across sessions by recording mistakes, user corrections, preferences, what worked, and what failed. Use when a user asks for persistent self-improvement, memory across sessions, agent notes, a scratchpad, or a workflow where Codex should adapt based on prior errors and feedback.
Expert embedded systems engineer specializing in microcontroller programming, RTOS development, and hardware optimization. Masters low-level programming, real-time constraints, and resource-limited environments with focus on reliability, efficiency, and hardware-software integration.
Electron 33+ desktop app development specialist covering Main/Renderer process architecture, IPC communication, auto-update, packaging with Electron Forge and electron-builder, and security best practices. Use when building cross-platform desktop applications, implementing native OS integrations, or packaging Electron apps for distribution. [KO: Electron 데스크톱 앱, 크로스플랫폼 개발, IPC 통신] [JA: Electronデスクトップアプリ、 クロスプラットフォーム開発] [ZH: Electron桌面应用、跨平台开发]
Master .NET async/await patterns including Task-based Asynchronous Pattern (TAP), ValueTask optimization, ConfigureAwait usage, cancellation tokens, parallel processing, and avoiding deadlocks in ASP.NET Core applications for maximum performance and responsiveness.
Master advanced C# patterns including records, pattern matching, async/await, LINQ, and performance optimization for .NET 10. Use when: (1) implementing complex C# patterns, (2) optimizing performance, (3) refactoring legacy code, (4) writing modern idiomatic C#.
Comprehensive evaluation metrics and testing framework for DSPy programs
Integrate DSPy optimization with existing Haystack pipelines
use when adding API to this project that exists in numpy, especially if the user mentions a stream in the numpy-api-parity plan.
Small Spec (Smolspec) - Lightweight Specification for Minor Changes
Game memory optimization, object pooling, garbage collection tuning, and efficient resource management for target platforms.
Game optimization, performance profiling, multi-platform support, and frame rate optimization for smooth gameplay experiences.
YOLO 目标检测 ROS2 部署技能 - YOLOv5/v8/v11 TensorRT/OpenVINO/RKNN 部署
OpenVINO 部署技能 - 模型优化、IR 转换、GPU/CPU/VPU 推理、ROS2 部署
TensorRT 部署技能 - ONNX 转换、Engine 构建、INT8 量化、ROS2 加速推理
Spring Boot framework patterns, best practices, and implementation guides
