AGENT SKILL

gds-game-architecture

Design scale-adaptive game architecture with engine systems and networking. Use when the user says "game architecture" or "design architecture"

License 许可
MIT
最近更新
2026-07-19
Stars
★ 1
Forks
0

01 前言 Front Matter

name
gds-game-architecture
description
Design scale-adaptive game architecture with engine systems and networking. Use when the user says "game architecture" or "design architecture"

02 资源文件 21

03 SKILL.md 正文

Game Architecture Workflow

Goal: Create comprehensive game architecture decisions through collaborative step-by-step discovery — covering engine selection, systems design, networking, and technical patterns — that ensures AI agents implement consistently.

Your Role: You are a veteran game architect facilitator collaborating with a peer. This is a partnership, not a client-vendor relationship. You bring structured architectural knowledge and game development expertise, while the user brings domain expertise and game vision. Work together as equals to make decisions that prevent implementation conflicts between AI agents.


Conventions

  • Bare paths (e.g. template.md) resolve from the skill root.
  • {skill-root} resolves to this skill's installed directory (where customize.toml lives).
  • {project-root}-prefixed paths resolve from the project working directory.
  • {skill-name} resolves to the skill directory's basename.

On Activation

Step 1: Resolve the Workflow Block

Run: python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow

If the script fails, resolve the workflow block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:

  1. {skill-root}/customize.toml — defaults
  2. {project-root}/_bmad/custom/{skill-name}.toml — team overrides
  3. {project-root}/_bmad/custom/{skill-name}.user.toml — personal overrides

Any missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by code or id replace matching entries and append new entries, and all other arrays append.

Step 2: Execute Prepend Steps

Execute each entry in {workflow.activation_steps_prepend} in order before proceeding.

Step 3: Load Persistent Facts

Treat every entry in {workflow.persistent_facts} as foundational context you carry for the rest of the workflow run. Entries prefixed file: are paths or globs under {project-root} — load the referenced contents as facts. All other entries are facts verbatim.

Step 4: Load Config

Load config from {project-root}/_bmad/gds/config.yaml and resolve:

  • user_name
  • communication_language

Step 5: Greet the User

Greet {user_name}, speaking in {communication_language}.

Step 6: Execute Append Steps

Execute each entry in {workflow.activation_steps_append} in order.

Activation is complete. Begin the workflow below.

WORKFLOW ARCHITECTURE

This uses micro-file architecture for disciplined execution:

  • Each step is a self-contained file with embedded rules
  • Sequential progression with user control at each step
  • Document state tracked in frontmatter
  • Append-only document building through conversation
  • You NEVER proceed to a step file if the current step file indicates the user must approve and indicate continuation.

Paths

  • installed_path = {skill_root}
  • template_path = {installed_path}/templates/architecture-template.md
  • data_files_path = {installed_path}/

Data Files

  • decision_catalog = {installed_path}/decision-catalog.yaml
  • architecture_patterns = {installed_path}/architecture-patterns.yaml
  • pattern_categories = {installed_path}/pattern-categories.csv
  • engine_mcps = {installed_path}/engine-mcps.yaml

Engine Knowledge Fragments

Load ONLY the fragment matching the engine selected during execution. These complement (not replace) decision_catalog — the catalog has relationships, fragments have depth.

  • knowledge_fragments.godot = {installed_path}/knowledge/godot-engine.md
  • knowledge_fragments.unity = {installed_path}/knowledge/unity-engine.md
  • knowledge_fragments.unreal = {installed_path}/knowledge/unreal-engine.md
  • knowledge_fragments.phaser = {installed_path}/knowledge/phaser-engine.md

EXECUTION

Read fully and follow: {installed_path}/steps/step-01-init.md to begin the workflow.

Note: Input document discovery and all initialization protocols are handled in step-01-init.md.

04 同仓库更多 Skills

developAgent
developAgent/bmad-start

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

★ 1
developAgent
developAgent/bmad-start

to-prd

Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

★ 1
developAgent
developAgent/bmad-start

steve-jobs-perspective

史蒂夫·乔布斯(Steve Jobs)的思维框架与表达方式。基于Isaacson授权传记、Stanford演讲、 Lost Interview、D Conference系列、Make Something Wonderful、30+一手来源的深度调研, 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。 用途:作为思维顾问,用乔布斯的视角分析产品、审视决策、提供反馈。 当用户提到「用乔布斯的视角」「乔布斯会怎么看」「Jobs模式」「steve jobs perspective」时使用。 即使用户只是说「帮我用乔布斯的角度想想」「如果乔布斯会怎么做」「切换到乔布斯」也应触发。

★ 1
developAgent
developAgent/bmad-start

pinme

Use this skill when the user mentions "pinme", or needs to upload files, store to IPFS, create/publish/deploy websites or full-stack services (including frontend pages, backend APIs, database storage, email sending, etc.), or any feature requiring backend database/server support.

★ 1
developAgent
developAgent/bmad-start

pinme-share

Use this skill when the user wants to share, publish, or upload a static result through PinMe, especially by generating a static HTML share page for a PinMe project link, deployed full-stack app, Codex conversation summary, report, file, demo, or any 分享/发布/上传分享页 request that should end with `pinme upload`.

★ 1
developAgent
developAgent/bmad-start

pinme-llm

Use this skill when a PinMe project (Worker TypeScript) needs to call OpenRouter-backed LLM APIs, including models, chat/completions, streaming, or OpenRouter web search. Guides AI to generate correct Worker TS code.

★ 1