best-prompts

Syncs Telegram supergroup topics into local task files and GitHub issues, using embedded Python scripts for deterministic JSON state management. Preserves raw bilingual messages verbatim, injects refactored prompts, and correlates codebase context.

100% Jetpack Compose, MVI (UDF), Hilt, and SQLDelight for token-efficient, zero-hallucination Android development.

NestJS, Prisma ORM, Vertical Slice Architecture, and Strict TypeScript for zero-hallucination backend development.

Expo Managed Workflow, Expo Router, NativeWind, and Strict TypeScript for zero-hallucination cross-platform apps.

Automatically generates decentralized task files based on manager instructions.

Idiomatic Go, Clean Architecture, and Gin routing best practices

Hexagonal Architecture (Ports and Adapters), gRPC, Uber Fx, and Redis caching for ultra-low latency Go backends.

SwiftUI, MVVM, and modern iOS app architecture

App Router, Server/Client Components, Server Actions, and Tailwind tokens for Next.js

AI-Optimized FastAPI architecture with strict Pydantic V2 schemas and modular routing.

React 18+ SPA architecture, hooks, and Vite configuration

DDD, hexagonal style, and naming conventions for Spring Boot

Intelligently exports a range of Telegram messages (text, media, voice notes) into a numbered folder, capturing reply hierarchies, and packing them into a ZIP archive.

Vue 3 Composition API, Nuxt 3 routing, and state management

Enforces decentralized task management, UI/UX design strictness, and global state constraints within AGENTS.md.

Refactors basic user prompts into elite, highly constrained, XML-tagged instructions optimized for AI agent reasoning.

Mandatory workflow for diagnosing complex bugs, deadlocks, race conditions, and silent failures via strategic logging and tracing.

Standardizes Semantic Versioning (SemVer), Keep a Changelog formats, Conventional Commits, and Safe Push Protocols across all repositories.

Mandatory workflow for exploring the codebase and gathering context for AI Studio.

Extract a comprehensive design system (DESIGN.md) directly from frontend source code — React, Vue, Svelte, Angular, plain HTML/CSS, or any web framework. Analyzes component files, stylesheets, Tailwind configs, theme definitions, and design tokens to produce a rich, Stitch-compatible design system document. Use this skill whenever the user wants to reverse-engineer a design system from an existing codebase, audit the visual language of a project, extract design tokens from source files, or understand the styling patterns in a frontend repo — even if they just say "what does this app look like?" or "pull out the design from this code."

Rules for modifying the Cognitive Lead AI SOP repository

Application Factory, Blueprints, SQLAlchemy, and config separation for Flask