Best AI coding prompts (2026)

Reads file contents intelligently - returns complete files when small, paginated chunks, or targeted chunks when large based on your query. **How it works:** • **Small files** (≤2000 lines) - Returns complete content • **Large files** (>2000 lines) - Uses AI to find and return relevant chunks based on query • **Binary files** - Returns images, handles blob content appropriately • Any lines longer than 2000 characters are truncated for readability • Start line and end line can be provided to rea

Lists files and directories in the repository. Returns file paths sorted alphabetically with optional pattern-based filtering. Common use cases: • Explore repository structure and understand project layout • Find files in specific directories (e.g., 'src/', 'components/') • Locate configuration files, documentation, or specific file types • Get overview of available files before diving into specific areas Tips: • Use specific paths to narrow down results (max 200 entries returned) • Combine wi

Fast text-based regex search that finds exact pattern matches within files or directories, utilizing the ripgrep command for efficient searching. Results will be formatted in the style of ripgrep and can be configured to include line numbers and content. To avoid overwhelming output, the results are capped at 50 matches. Use the include patterns to filter the search scope by file type or specific paths. This is best for finding exact text matches or regex patterns. More precise than codebase sea

This tool is Trae's context engine. It: 1. Takes in a natural language description of the code you are looking for; 2. Uses a proprietary retrieval/embedding model suite that produces the highest-quality recall of relevant code snippets from across the codebase; 3. Maintains a real-time index of the codebase, so the results are always up-to-date and reflects the current state of the codebase; 4. Can retrieve across different programming languages; 5. Only reflects the current state of the codeba

Use this tool to create and manage a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user. It also helps the user understand the progress of the task and overall progress of their requests.

Launches a highly capable task agent in the USER's workspace. Usage notes: 1. When the agent is done, it will return a report of its actions. This report is also visible to USER, so you don't have to repeat any overlapping information. 2. Each agent invocation is stateless and doesn't have access to your chat history with USER. You will not be able to send additional messages to the agent, nor will the agent be able to communicate with you outside of its final report. Therefore, your prompt shou

This tool allows you to execute interactive shell commands and ask questions about the output or behavior of CLI applications or interactive Python programs. ## Rules of usage: 1. Provide clear, concise interactive commands to execute and specific questions about the results or interaction. 2. Ask one question at a time about the interactive behavior or output. 3. Focus on interactive functionality, user input/output, and real-time behavior. 4. Specify the exact command to run, including any ne

Custom editing tool for viewing, creating and editing files * State is persistent across command calls and discussions with the user * If `path` is a file, `view` displays the result of applying `cat -n`. If `path` is a directory, `view` lists non-hidden files and directories up to 2 levels deep * The `create` command cannot be used if the specified `path` already exists as a file * If a `command` generates a long output, it will be truncated and marked with `<response clipped>` * The `undo_edi

Create a new Database. Format requirements as a markdown bullet list. Each requirement should be a statement that clearly describes something you want to be true about the Database after it has been created. DO NOT try to reference the user's messages in the requirements, as the Database create sub-agent will NOT be able to see them. Make sure to include all important information in full. If you need to refer to entities in the requirements, use the entity URLs and provide context. When adding

Perform one or more searches over: - "internal": Perform semantic searches over only the user's internal Notion workspace, their connected sources (including Slack, Google Drive, Github, Jira, Microsoft Teams, Sharepoint, OneDrive, or Linear), and Notion's official help docs. - "web": Perform web searches only. Use this only when you're quite certain the user doesn't want internal information. - "default": Simultaneously do an internal search (Notion workspace, their connected sources (includin

Retrieves details about Notion entities by their URLs. If you know you want to view multiple entities, you should view them ALL at once in a single tool call instead of taking multiple turns. You can view the following types of entities: - Page, ie. from a <page> block or a <mention-page> mention. This also loads it for later updates and edits. - Database, ie. from a <database> block or a <mention-database> mention - Data source, ie. from <data-sources> inside of <database> - View, ie. from a <v

Write input to a running process in a specified shell session. Use for responding to interactive command prompts.

Use this tool to edit a jupyter notebook cell. Use ONLY this tool to edit notebooks. This tool supports editing existing cells and creating new cells: - If you need to edit an existing cell, set 'is_new_cell' to false and provide the 'old_string' and 'new_string'. -- The tool will replace ONE occurrence of 'old_string' with 'new_string' in the specified cell. - If you need to create a new cell, set 'is_new_cell' to true and provide the 'new_string' (and keep 'old_string' empty). - It's cri

Find snippets of code from the codebase most relevant to the search query. This is a semantic search tool, so the query should ask for something semantically matching what is needed. If it makes sense to only search in particular directories, please specify them in the target_directories field. Unless there is a clear reason to use your own search query, please just reuse the user's exact query with their wording. Their exact wording/phrasing can often be helpful for the semantic search query. K

Custom tool for viewing files and directories and searching within files with regex query * `path` is a file or directory path relative to the workspace root * For files: displays the result of applying `cat -n` to the file * For directories: lists files and subdirectories up to 2 levels deep * If the output is long, it will be truncated and marked with `<response clipped>` Regex search (for files only): * Use `search_query_regex` to search for patterns in the file using regular expressions * U

Launch a new process with a shell command. A process can be waiting (`wait=true`) or non-waiting (`wait=false`). If `wait=true`, launches the process in an interactive terminal, and waits for the process to complete up to `max_wait_seconds` seconds. If the process ends during this period, the tool call returns. If the timeout expires, the process will continue running in the background but the tool call will return. You can then interact with the process using the other process tools. Note: On

Read browser console messages (console.log, console.error, console.warn, etc.) from a specific tab. Useful for debugging JavaScript errors, viewing application logs, or understanding what's happening in the browser console. Returns console messages from the current domain only. If you don't have a valid tab ID, use tabs_context first to get available tabs. IMPORTANT: Always provide a pattern to filter messages - without a pattern, you may get too many irrelevant messages.

Use a mouse and keyboard to interact with a web browser, and take screenshots. If you don't have a valid tab ID, use tabs_context first to get available tabs. * Whenever you intend to click on an element like an icon, you should consult a screenshot to determine the coordinates of the element before moving the cursor. * If you tried clicking on a program or link but it failed to load, even after waiting, try adjusting your click location so that the tip of the cursor visually falls on the elemen

Completely replaces the contents of a specific cell in a Jupyter notebook (.ipynb file) with new source. Jupyter notebooks are interactive documents that combine code, text, and visualizations, commonly used for data analysis and scientific computing. The notebook_path parameter must be an absolute path, not a relative path. The cell_number is 0-indexed. Use edit_mode=insert to add a new cell at the index specified by cell_number. Use edit_mode=delete to delete the cell at the index specified by

Launch a new agent to handle complex, multi-step tasks autonomously. Available agent types and the tools they have access to: - general-purpose: General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you. (Tools: *) - statusline-setup: Use this agent to configure the user's Cla

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. Principles: Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution. MIT licensed

A complete guide to start and improve in machine learning and AI in 2026 without any background. Curated learning path with the latest news, state-of-the-art techniques, and comprehensive resources for beginners. MIT licensed

Up-to-date code documentation for LLMs and AI code editors. Fetches latest docs and code examples directly into LLM context via MCP. Eliminates hallucinated APIs. MIT licensed

OpenAI's lightweight coding agent that runs in your terminal. Code generation, file editing, and command execution with approval. Apache 2.0 licensed

AI-powered code review agent for GitHub, GitLab, Bitbucket, and Azure DevOps. Automated PR analysis, improvement suggestions, and multi-platform deployment via CLI, GitHub Actions, or webhooks. AGPL-3.0 licensed

Personal AI notebook for organizing files and webpages with AI-generated notes. Local-first data storage, open data formats, and open model choice including local models. Cross-platform desktop app for research and thinking workflows. Apache 2.0 licensed

Framework for building realtime voice AI agents with WebRTC transport, STT-LLM-TTS pipelines, and production-grade orchestration. Used by Salesforce Agentforce and Tesla. Apache-2.0 licensed

Open-source MCP Host Desktop Application with dual Tauri/Electron architecture. Seamlessly integrates with any LLMs supporting function calling. MIT licensed

AI suite for power users with multi-model "Beam" chats, AI personas, voice, text-to-image, code execution, and PDF import. MIT licensed

Probabilistic time series modeling with deep learning. Powers Amazon SageMaker forecasting with PyTorch and MXNet backends. Apache 2.0 licensed

PyTorch audio processing library. Comprehensive toolkit for audio I/O, transformations, and deep learning with support for speech recognition, TTS, and audio classification. BSD-2-Clause licensed

Scalable and memory-optimized training of diffusion models from Hugging Face. Supports LoRA and full fine-tuning for video and image generation models. Apache 2.0 licensed

Protects AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers. MIT licensed

Python Risk Identification Tool for generative AI. Microsoft's open-source framework for automated red teaming with multi-modal attack support, crescendo strategies, and 100+ operations experience. MIT licensed

Fit interpretable models and explain blackbox machine learning with state-of-the-art explainability techniques including Explainable Boosting Machines and SHAP-based explanations

Evaluation and tracking for LLM experiments and AI agents. Provides feedback functions for measuring quality, relevance, and groundedness with LangChain and LlamaIndex integrations. MIT licensed

Comprehensive suite for LLM-based AI app development from prototyping to production. Includes prompt engineering, evaluation, and deployment tools with VS Code integration. MIT licensed

Manages unified access to generative AI services built on Envoy Gateway. Kubernetes-native AI gateway for routing, load balancing, and managing LLM traffic with enterprise-grade reliability. Apache 2.0 licensed

Cloud-native batch scheduling system for compute-intensive workloads. CNCF incubating project with gang scheduling, job dependency management, and topology-aware scheduling for AI/ML and deep learning. Apache 2.0 licensed

Event-driven orchestration and scheduling platform for mission-critical workflows. Infrastructure-as-Code approach with declarative YAML, Git version control integration, and hundreds of plugins for data pipelines and ML workflows. Apache 2.0 licensed

Containerize and deploy ML models with production-grade inference servers. Packages models into standardized containers with automatic API generation, GPU support, and one-command deployment. Powers thousands of production AI models on Replicate. Apache 2.0 licensed

Self-hosted ML experiment tracker designed to handle 10,000s of training runs with performant UI and SDK for programmatic access. Apache 2.0 licensed

Open-source platform for experiment tracking, orchestration, data management, and model serving

Train a 64M-parameter LLM from scratch in just 2 hours for $3. Complete from-scratch implementation covering MoE, data cleaning, pretraining, SFT, LoRA, RLHF (DPO/PPO/GRPO), tool use, and model distillation. All core algorithms implemented in pure PyTorch without high-level abstractions. Educational framework for understanding LLM internals. Apache 2.0 licensed

Easy-to-use, scalable RLHF framework based on Ray. Supports PPO, GRPO, REINFORCE++, DAPO with vLLM integration and async training. Apache 2.0 licensed

Official library for RLHF, SFT, DPO, ORPO

Lifelike audio-driven portrait animations through editable landmark conditioning. High-quality talking head generation with precise lip synchronization and natural head movements. AAAI 2025. Apache 2.0 licensed

Agentic LLM-powered data processing and ETL system for complex document processing. Query rewriting and evaluation for unstructured data analysis with 80% higher accuracy than baselines. MIT licensed