ASSISTANTS

BLOCKS

BUNDLES

Trending blocks

Blocks are reusable components that define specific behaviors and capabilities for AI assistants, from custom instructions to advanced model configurations

Learn more

Explore custom AI blocks

The following blocks are popular in the Continue community

Clipboard Context

References recent clipboard items, allowing quick access to previously copied content for easy reuse in your development workflow.

Codestral

Cutting-edge language model for coding. With the second version released January 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.

Next.js Docs

Sequential Thinking Workflow

Sequential Thinking with Source Code Context

DeepSeek R1

DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks

o3-mini

OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini

starter/angular-rules

Next.js Security Review

Check for any potential security vulnerabilities in your code

qwen2.5-coder 1.5b

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing

DeepSeek-R1

starter/security-rules

starter/laravel-rules

Docker MCP Postgres

deepseek-r1

DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks

continuedev/solid-rules

Write your code using SOLID principles.

autodetect

gemma3 4B

starter/pytorch-rules

Exploratory Data Analysis Prompt

Claude 3.7 Sonnet

Anthropic's previous most intelligent model with toggleable extended thinking

Morph v3

Fast AI Code Edits. Accurate + Reliable

Docker MCP Sequential Thinking

RAG System Development

Prompt for developing RAG based systems and features in GenAI applications

PyTorch Docs

Mercury Coder Small

Qwen 2.5 Coder 32b

Claude 3.5 Haiku

Claude 3.5 Haiku efficiently processes and categorizes information, making it effective for rapid data extraction and automated labeling tasks.

Mistral Large

Top-tier reasoning model for high-complexity tasks with the lastest version released November 2024.

Qwen3 Coder

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts).

roddsrod/git-rules

Git Rules

NumPy Docs

starter/react-rules

o1

OpenAI's reasoning model designed to solve hard problems across domains

Create Data Pipeline

Mistral Embed

State-of-the-art semantic for extracting representation of text extracts

Trending blocks