- Root static site with no build step:
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 →- Root static site with no build step:
- Next.js Pages Router lives in `pages/` (e.g., `pages/index.js`, `pages/_app.js`). Dynamic routes under folders like `pages/creator/[id].js`.
**Family Planner** is a comprehensive React-based family planning application designed for Surface tablets. It runs entirely client-side with no backend, integrating with Microsoft services and Azure
<!--
⚠️ MANDATORY COMPLIANCE DIRECTIVE ⚠️
This repository is an Obsidian-based digital garden. Notes are Markdown with YAML frontmatter, organized using Zettelkasten/PARA. Publishing is controlled by the `publish: true` flag and automated by
This is (de)Motivator — a satirical web app that shows short, cheeky one-liners. Built with Svelte 5 + TypeScript, bundled with Vite, and deployed to Firebase hosting. We value pragmatic solutions ove
- This AGENTS.md is the workspace-wide instruction source. Do not add a second global .github/copilot-instructions.md unless intentionally replacing this file.
this document provides a technical overview of the Current codeBase, including its architecture, components, key features, and instuctions for interacting with the code base.
Agent Notes
This file is mandatory reading at the start of every session in this repository.
Andrew Ng (machine learning, co-founder of Coursera and DeepLearning.AI, Stanford University, former Google Brain lead) views AI as a general-purpose technology—the "new electricity." His approach is
人間・コーディングエージェント共通の作業規約。迷ったら **[Design.md](./Design.md)** を先に確認する。
CatastroSwitch is a machine-local workspace switching control plane built inside a VS Code fork. The project uses a two-repo architecture:
This repo is a Vite + React + TypeScript kombucha companion app with Supabase-backed auth, batch tracking, fermentation guidance, F2 planning, guides, and beginner-friendly onboarding.
This file provides guidance to AI coding agents (Claude Code, Cursor, Copilot, etc.) when working with skills in this repository.
This project uses [nexus-agents](https://github.com/williamzujkowski/nexus-agents) v2.3.0 for multi-agent orchestration.
Learn how to create powerful, interconnected Claude sub-agents using advanced patterns.
Subagents are isolated Claude instances spawned within your session via the Agent tool.
Apply this rule when:
Delegate read-only analysis tasks to Gemini CLI agents
A guide to securing Claude Code and Agent SDK deployments with isolation, credential management, and network controls
**Feature Type:** Automatic
The agents documentation contains 6 core markdown files:
Three-criteria evaluation framework for autonomous agent deployment
| Use Case | Use | Why |
Parallel execution requires:
1. 1
As of early 2026, Cursor has shifted heavily toward **Cloud Agents** and **Dynamic Context Discovery**. If you are using Cursor for your MVP build (Step 5 of the vibe-coding workflow), use these patte
Rules for when and how to use subagents.
Subagent definitions for the Feature Builder framework.
| Agent | Role | Model | MCP Servers |
**→ See also: [Agent Best Practices](best-practices.md) for reusable helpers, common patterns, and critical preservation rules**
Phase 2: Liest eine ADR und koordiniert den Aufbau der Agenten- und Workflow-Dateien.
| Agent | Model | Best For | Key Trait |
Quick reference for all available agents and skills. Custom agents live in `~/.claude/agents/`, skills live in `~/.claude/skills/`.
You are a system of 4 agents working in sequence.
from agents import Agent
> **Last Updated**: January 27, 2026
Mix human and AI responses in the same thread for customer support and hybrid workflows.
Synchronizes all project documentation files to ensure consistency and accuracy across:
This file provides guidance to AI coding assistants working in this repository.
AI 코딩 에이전트 거버넌스, Copilot/Claude 통합, 엔터프라이즈 AI 정책
**Subagents for research + build; background Bash for parallel compute.**
Guide for maintaining and extending the commands/skills system in Mechanic.
Use these examples when the user needs raw HTTP requests or is working without an SDK.
- 직접 코드 작성하지 않음
Display all available BMAD agent personas with their descriptions and primary tasks.
Stop. Read this section before doing anything.
This file defines coordinated multi-agent workflows for enterprise accessibility scanning in the Claude Code environment.