miles990

Enterprise-grade repository analysis with arc42/C4 architecture documentation, technical debt quantification, security assessment, and multi-stakeholder reporting

Claude Code Plugin 開發、發布、安裝、更新與 Marketplace 管理完整指南

Flame Engine core fundamentals - components, input, collision, camera, animation, scenes

Flame Engine 2D 遊戲開發完整指南 - 核心、系統、模板、部署

Game development patterns, architectures, and best practices

Mobile development with React Native, Flutter, and native patterns

Flame Engine 14 game systems - quest, dialogue, inventory, combat, save/load, shop, crafting, and more

Game type templates for Flame Engine - RPG, Platformer, Roguelike starter code

非技術領域專業知識集合，包含商業、金融、創意、專業服務、生活、方法論等 18 個領域

數位行銷策略、內容行銷與成效分析

產品管理：PRD撰寫、用戶故事、OKR設定、路線圖規劃

專案管理：敏捷開發、Scrum、甘特圖、風險管理、團隊協作

銷售技巧：B2B/B2C 銷售、客戶開發、電商營運、成交策略

商業策略：藍海策略、差異化、競爭優勢、價值創新、商業模式設計

創意發想：頭腦風暴、靈感激發、創意思維框架、發散與收斂思考

類 Slay the Spire 的卡牌構築 Roguelike 遊戲設計框架

跨子系統架構一致性審查 - 利用多視角並行分析架構健康度

多 Agent 監督式實作框架 - TDD 驅動、即時審查、品質守護

智能 commit .claude/memory/ 目錄的變更（含任務追蹤）

端到端工作流編排器 - File-Based Handoff + 智能並行決策

多 Agent 並行規劃框架 - 多視角同時設計，共識驅動實作計劃

多 Agent 並行研究框架 - 多視角同時研究，智能匯總成完整報告

多 Agent 並行審查框架 - 多視角程式碼審查，問題分類與優先排序

一鍵配置 multi-agent-workflow 規範執行機制

Agent Skills Package Manager - Install once, use everywhere. Manage, share, and sync AI agent skills across platforms.

Help users configure MCP (Model Context Protocol) servers for Claude Code and other AI platforms.

程式碼審查，包裝 PAL MCP 的 codereview 功能

除錯輔助，包裝 PAL MCP 的 debug 功能，提供系統化問題診斷

Git 操作輔助，提供 commit message 規範、分支策略與 PR 指引

在檢查點驗證目標和方向，避免偏離軌道

將任務拆解為可執行的 Milestones，支援 PDCA 循環規劃

任務開始前的需求分析與資料收集，整合文件查詢與經驗檢索

Personal AI Agent with Memory + Proactivity - Multi-instance support

Pre-edit coordination ritual for the shared mini-agent tree — checks Kuro's cycle state, current branch, and whether worktree isolation is needed before touching src/ or memory/. Use before editing src/ or memory/ in the mini-agent repo.

Verify that code/config changes are actually persisted (committed + pushed + PR), not left uncommitted on the volatile runtime/main checkout. Use before claiming any "套用/執行/完成" of a change, or when a task asked to apply changes.

Run all mini-agent health-check and janitor scripts in one pass and summarize the results. Use when the user wants a project health check or types /health-sweep.

Check Kuro's current status, health, and recent activity in one shot

Deploy Kuro changes through CI/CD pipeline with pre-flight checks and post-deploy verification

Generic quality checking engine for creative works (novel, screenplay, game narrative)

创意专案初始化 — 支持小说、剧本、游戏等领域

Creative project memory management system — Three-tier memory architecture / Knowledge base maintenance / Summary generation

創意專案規劃系統 — 支援多層級規劃工作流（宏觀結構 / 分段大綱 / 細節列表）

創意專案狀態總覽與健康度檢查 — 通用框架

通用創意內容生成引擎 — 支援多領域結構化創作工作流

自我進化 Agent - 已遷移至原子化架構

自我進化 Agent：給定目標，自主學習並迭代改進直到完成。整合 superpowers 工作流紀律。

Anthropic 風格的專業計畫管理 Skill - 自然語言驅動、預設並行、全自動 GitHub 整合

引導式建立新 Skill 的完整工作流

Unified Planning Layer - 智能整合 spec-workflow 與 evolve PDCA

Use when facing complex problems that need multi-perspective analysis, when stuck in one way of thinking, or when you want to approach a problem like an expert from a different field would

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Flame Engine 2D game development master index - core, systems, templates

Flame Engine core fundamentals - components, input, collision, camera, animation, scenes

Use when an AI needs to discover available receptors, actuators, and tool operations; observe human, environmental, device, or software state; plan one or more adaptive interactions; execute them through the local CLI or HTTP API; verify delivery and effects;…

自我進化 Agent：給定目標，自主學習並迭代改進直到完成。

修行 — 辨認內心升起的非理性衝動（懼怠慢亂邪虛），與之共存，轉化為力量。