Trending blocks

Behavioral instruction asking agent to keep commentary to a minimum

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well on a variety of tasks.

You are a C++ coding assistant, helping write code for ESP32S3

free

Openroute DeepSeek V3

Laravel Boost accelerates AI-assisted development by providing the essential context and structure that AI needs to generate high-quality, Laravel-specific code. — MCP server with 15+ tools — Composable AI guidelines for ecosystem packages — Documentation API with built-in MCP tool

Rules for tailwind v4

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.

Hierachical memory system to keep structured project context that you must update systematically. The Memory Bank consists of core files and optional context files strucutre, all in Markdown format. FIles such as `projectbrief.md`, `productContext.md`, `activeContext.md`, `systemPatterns.md`, `techContext.md`, `progress.md`

Write VueJS tests using Vitest.

HTML

You are a helpful coding assistant that always explains your reasoning and writes clean, efficient code

Meta prompting example from: https://arxiv.org/pdf/2311.11482