Vercel Agent guidance — AI-powered code review, incident investigation, and SDK installation. Automates PR analysis and anomaly debugging. Use when configuring or understanding Vercel's AI development tools.

Deploy projects to Netlify with the Netlify CLI. Use when the user wants to link a repo, validate deploy settings, run a deploy, or choose between preview and production flows.

Triage Outlook mail, extract tasks, clean up subscriptions, draft responses, and route shared mailbox work. Use when the user asks to inspect an Outlook inbox or thread, summarize open actions and deadlines, clean up newsletters, draft replies or forwards, organize mailbox follow-up work, or act on a delegated/shared Outlook mailbox.

Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.

Audit and improve SwiftUI runtime performance from code review and architecture. Use for requests to diagnose slow rendering, janky scrolling, high CPU/memory usage, excessive view updates, or layout thrash in SwiftUI apps, and to provide guidance for user-run Instruments profiling when code review alone is insufficient.

Build a concise prior authorization packet from local case files and payer policy docs.

Inspect Microsoft SharePoint context, discover the right site or library, and prepare safe changes. Use when the user wants site, page, or file review, ownership and status extraction, or change planning before editing content, navigation, or information architecture.

Create and review Cloudflare Durable Objects. Use when building stateful coordination (chat rooms, multiplayer games, booking systems), implementing RPC methods, SQLite storage, alarms, WebSockets, or reviewing DO code for best practices. Covers Workers integration, wrangler config, and testing with Vitest. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Guides Stripe integration decisions — API selection (Checkout Sessions vs PaymentIntents), Connect platform setup (Accounts v2, controller properties), billing/subscriptions, Treasury financial accounts, integration surfaces (Checkout, Payment Element), and migrating from deprecated Stripe APIs. Use when building, modifying, or reviewing any Stripe integration — including accepting payments, building marketplaces, integrating Stripe, processing payments, setting up subscriptions, or creating connected accounts.

Implement, review, or improve SwiftUI features using the iOS 26+ Liquid Glass API. Use when asked to adopt Liquid Glass in new SwiftUI UI, refactor an existing feature to Liquid Glass, or review Liquid Glass usage for correctness, performance, and design alignment.

Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

React best-practices reviewer for TSX files. Triggers after editing multiple TSX components to run a condensed quality checklist covering component structure, hooks usage, accessibility, performance, and TypeScript patterns.

Headless CMS integration guidance — Sanity (native Vercel Marketplace), Contentful, DatoCMS, Storyblok, and Builder.io. Covers studio setup, content modeling, preview mode, revalidation webhooks, and Visual Editing. Use when building content-driven sites with a headless CMS on Vercel.

Summarize Microsoft Teams conversations, triage unread or recent activity, draft follow-ups, and manage Planner tasks through connected Teams data. Use when the user wants to review chats or channels, identify owners and next steps, prepare a safe reply or post, or turn Teams follow-ups into Microsoft Planner tasks.

Write, reply to, and resolve Google Drive comments on Docs, Sheets, Slides, and Drive files with evidence-backed location context. Use when the user asks to leave comments, review a file with comments, respond to comment threads, or resolve Drive comments.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

**Welcome!** If you are an AI Coding Agent tasked to modify, review, or debug this project, read this document first. It contains essential architectural constraints, coding conventions, and project-s

- **NEVER** use git to discard or revert any changes not made by you - they are proposely changed by user and you should live with that.

- Security Architect

Multi-agent orchestration for software development. You coordinate teams of AI agents that build, review, and test code.

Web utility to import Statement of Work (SOW) documents into ScopeStack. Users upload Word/PDF files, AI extracts services/subservices, users review/edit mappings, then export JSON for ScopeStack API.

You are the Coding Agent for this repository.

This file provides guidance for agents working within this repository, which is structured as a "Self-Correcting Coding Agent Team." This team of specialized AI agents collaborates to develop, review,

> **Context:** This is a monorepo built with Bun, Astro, Hono, and Effect TS.

**Date**: 2026-04-03

- Read SOUL.md to align identity.

Universal guidelines for AI agents and developers. This file is used verbatim across multiple projects.

- Follow your assigned role strictly — it defines scope and boundaries for your actions.

本文件為本庫的協作與工程化規範（適用於整個專案目錄）。目標：免費優先（Free-first）的 CI / Security / Review / 文件骨架，並避免動到既有業務邏輯。

- `app.py`: Flask web UI for tagging, manual video review, and NFO metadata plan/write/history workflows.

Guidelines for AI agents working on this Astro-based static site.

This document shows how to build up a complete code review system using the simple tools specification and markdown-based agents.

- **Code Quality**: Write clean, readable, and maintainable code. Use meaningful variable and function names.

- Review the root `README.md` first for product context and local run instructions.

这个仓库是中文主导、双语术语的 AI 开发运行协议。

<!-- Parent: ../AGENTS.md -->

- **dev** – Start dev server

**ACR-QA** — Automated Code Review & Quality Assurance

This directory covers building autonomous agents, not using agent products.

I have been going deep on Claude Code customization lately. After building a plugin, writing custom commands, and setting up hooks, I hit a wall. I was doing everything through the main conversation —

LLM-based agents can accelerate development only if they respect our house rules. This file tells you:

Leyline is an opinionated developer-session workflow plugin that ships a behavior-shaping skill library, two specialized reviewer subagents, and a session-start hook that injects the entry skill on ev

Comprehensive PR review using specialized agents - comments, tests, errors, types, code quality, docs, and simplification

Search through your subagents and skills and make a detailed plan to execute the user's query. Use the subagents to save context and use shared documents in agent_tasks as a form of memory and passive

**Version 3.0.0**

位於 `~/.claude/agents/`：

This skill provides Apple Human Interface Guidelines for macOS. Apply these rules when building, reviewing, or designing Mac apps using SwiftUI or AppKit.

Prompts for parallel documentation review agents.

Problem definition → small, safe change → change review → refactor — repeat the loop.

Comprehensive code review knowledge base for React applications (framework-agnostic). Contains rules across security, performance, architecture, and quality categories. Each rule includes detailed exp