<h2>What is the Turing Pyramid Skill?</h2>
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →<h2>What is the Turing Pyramid Skill?</h2>
本仓库的 AI 协作规范以 `CLAUDE.md` 为唯一配置源（Single Source of Truth）。
**Responsibility**: High-level planning, breaking down user requests into atomic tasks, maintaining `task.md`, and ensuring the "Definition of Done".
Agent-readable onboarding instructions. When an agent reads this file, it should walk the developer through each step interactively.
<!-- Parent: ../../AGENTS.md -->
本文檔說明如何安裝與使用 Codex CLI 與 VS Code 擴充套件，並包含核心操作技巧、進階應用與注意事項。
Two tools for collaborating with teammates:
AGENTS.md is the consistency constitution. It is the short rule book that keeps work steady across sessions and agents. Keep it tight, clear, and easy to fix. If you find a rule gap, tighten the rule.
<!--
本文件旨在讓不同的 AI 代理能快速理解專案狀態、目標、開發環境與接手步驟。
<table>
Integrations connect Assistant to external systems (email, GitHub, Gemini, etc.). The project follows a Home Assistant-inspired model: core integrations for universally useful services, with the inten
You are an expert at working with Rust CLI tools and have been onboarded to the `pullhook` codebase.
> 本檔同時供人類與開發代理（Codex、Cursor、Zed、Aider…）閱讀。請嚴格遵守。
This file helps AI agents understand the available agents and how to use them.
This repository contains open source [RabbitMQ](https://www.rabbitmq.com/), a multi-protocol
发布时间：2024年10月22日
Deep agents are autonomous AI agents that combine multiple architectural patterns to handle complex, multi-step tasks with minimal human intervention. They feature:
[`Runner`][agents.run.Runner] 클래스를 통해 에이전트를 실행할 수 있습니다. 3가지 옵션이 있습니다:
<!-- Global AI settings for Claude Code, Codex, Cursor, Gemini CLI -->
- Workspace member: **`rust_scorer`** (CLI + `float_scan_bench`). **`neat-core`** is a **path** dependency on **`../../NEAT-AI-core/neat-core`** (sibling clone of **[NEAT-AI-core](https://github.com/s
本仓库采用 **基于分支的开发方式**，并要求对每个有意义的分支进行记录。
| Constant | Value | Purpose |
dotcube is a dotfiles management system that provisions ZSH shell configurations and system environments using Ansible. It supports macOS, Ubuntu/Debian, Raspbian, and WSL.
Workspace instructions for coding agents working on this repository.
Validiert Agenten-Dateien, YAML-Frontmatter (inkl. color-Attribut) und Best Practices
An agent in Microsoft Agent Framework is a stateful conversational entity that combines:
Initialize agent team for an existing project
> **Scope:** AI coding agents (Claude, Cursor, Copilot, and any other AI assistant operating in this codebase).
This file documents all 5 Agno-powered agents in the WAIGenie framework.
The vocabulary you didn't know you needed. 1 skill, 17 commands, and curated anti-patterns for impeccable style. Works with Cursor, Claude Code, Gemini CLI, and Codex CLI.
This file defines the lead-agent operating model for Aegis feature work in Claude-driven sessions.
How to use different LLM models for different agents in Present-Agent2.
| Agent ID | Owns | Entry dirs | Model | Can parallel with |
We investigate the challenge of task planning for multi-task embodied agents in open-world environments.[^2] Two main difficulties are identified: 1) executing plans in an open-world environment (e.g.
| Agent | subagent_type | isolation | run_in_background |
> This file defines the agent team structure, sub-agent roles, and orchestration patterns for the MTA Website project.
This repository uses **layered documentation** for AI agent context management.
| Aufgabe | Agent | Wann |
<!--
Thaler and Sunstein's choice architecture maps directly to hook enforcement design -- blocking hooks are mandates, context-injecting hooks are nudges, and the graduation between them prevents alert
> Operating instructions for OpenClaw agents working with Claude Code Autopilot projects.
Markdown + YAML Frontmatter形式で記述します。
> 来源：CLAUDE.md v2.0
GSD는 특수화된 에이전트들을 사용하여 복잡한 작업을 자율적으로 처리합니다.
<!-- FOR AI AGENTS - Human readability is a side effect, not a goal -->
Přiřazení agentů k úkolům, hotové instrukce pro spuštění
Automatically spawn the right agents at the right time without manual intervention.
This reference is shared across all agents. Every agent knows the others, their responsibilities, and when to suggest them to the dispatcher.
Sub-agents let you run background tasks without blocking the main conversation. When you spawn a sub-agent, it runs in its own isolated session, does its work, and announces the result back to the cha