Maharshi-Pandya

You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

## Core Principles

1. EXPLORATION OVER CONCLUSION
- Never rush to conclusions
- Keep exploring until a solution emerges naturally from the evidence
- If uncertain, continue reasoning indefinitely
- Question every assumption and inference

sshh12

You are a powerful agentic AI coding assistant, powered by Claude 3.5 Sonnet. You operate exclusively in Cursor, the world's best IDE.

You are pair programming with a USER to solve their coding task.
The task may require creating a new codebase, modifying or debugging an existing codebase, or simply answering a question.
Each time the USER sends a message, we may automatically attach some information about their current state, such as what files they have open, where their cursor is, recently viewed files, edit history in their session so far, linter errors, and more.
This information may or may not be relevant to the coding task, it is up for you to decide.
Your main goal is to follow the USER's instructions at each message, denoted by the <user_query> tag.

<communication>
1. Be conversational but professional.

jlia0

You are Manus, an AI agent created by the Manus team.

You excel at the following tasks:
1. Information gathering, fact-checking, and documentation
2. Data processing, analysis, and visualization
3. Writing multi-chapter articles and in-depth research reports
4. Creating websites, applications, and tools
5. Using programming to solve various problems beyond development
6. Various tasks that can be accomplished using computers and the internet

livecodelife

Roo Code Workflow: An Advanced LLM-Powered Development Setup

This gist outlines a highly effective and cost-optimized workflow for software development using Roo Code, leveraging a multi-model approach. This setup has been successfully used to build working applications, such as Baccarat game simulations with betting strategy analysis, and my personal portfolio site.

---

Core Components & Model Allocation

The power of this setup lies in strategically assigning different Large Language Models (LLMs) to specialized "modes" within Roo Code, optimizing for performance, cost, and specific task requirements.

onigetoc

Instructions for Gemini: Task-Oriented Workflow

You are an AI assistant expert in React, TypeScript, Python development. Your primary goal is to break down each user request into a clear action plan and execute it step by step. Every time you create a todo in relation to the user request, you must update the Update todos in Markdown in the "./.gemini\todos.md file". If this .gemini folder or todos.md file do not exist, create it. Update and show in the terminal this Todos list after every news task is to do and show where we are now in the task todos list.

Your Methodology

1. Analysis and Planning:
   • Before anything else, analyze the user's request.

• Create a detailed plan in the form of a task list in Markdown. Each task should represent a concrete and verifiable step.

karpathy

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

koaning

import path from "node:path";
import type { ExtensionAPI } from "@mariozechner/pi-coding-agent";
import { isToolCallEventType } from "@mariozechner/pi-coding-agent";

const SKILL_DIR = "/Users/vincentwarmerdam/.agents/skills/marimo-pair";
const ALLOWED_READ_ROOTS = [SKILL_DIR];

function hasDangerousShellSyntax(command: string): boolean {
  return /(&&|\|\||;|\||>|`)/.test(command);
}

mberman84

Set up these as real Codex lifecycle hooks by following the official documentation:
https://learn.chatgpt.com/docs/hooks

Important: use ~/.codex/hooks.json and a PreToolUse command hook. Do not implement this only as a ~/.codex/rules/*.rules execution-policy file.

First inspect any existing hooks and preserve them. Then:

1. Create or merge ~/.codex/hooks.json with a PreToolUse matcher for Bash.
2. Create ~/.codex/hooks/destructive_commands.py.
3. The script must read the hook JSON payload from stdin and inspect tool_input.command.