Multica Technical Design

Community

it235

multica-technical-design

基于 PRD 与现有代码产出最小技术方案。用于 @Architect 架构分析、影响评估、实现方案设计；含文档元数据与复审修订规范；草稿就绪后交 multica-artifact-architect 落地。

Overview

Publisher	it235
Repository	`multica-best-practices`
Skill name	`multica-technical-design`
Stars	199
Forks	29
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by it235 on GitHub. Read the source before you install it.

Installation

Install the Multica Technical Design AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/it235/multica-best-practices/tree/main/templates/zh_CN/skills/architect/multica-technical-design
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/it235/multica-best-practices/tree/main/templates/zh_CN/skills/architect/multica-technical-design

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/it235/multica-best-practices.git /tmp/multica-best-practices
mkdir -p .claude/skills
cp -r /tmp/multica-best-practices/templates/zh_CN/skills/architect/multica-technical-design .claude/skills/multica-technical-design

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Multica Technical Design in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Multica Technical Design on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Multica Technical Design is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Technical Design

Purpose

基于 PRD（或 Issue）与现有代码库，产出最小可行的技术设计（只管「写什么」，不管「落到哪个平台」）。

与 multica-artifact-architect 分工：technical-design 产出结构与内容；artifact-architect 校验产物并调用 Confluence/JIRA platform skills 落地。
与 multica-review-architect 配合：初稿 → 评审 → 修订 → 复审（最多 3 轮），每轮修订须递增版本并填写「评审回应」。

Platform 协作

Platform skill	本 skill 用途
`multica-platform-jira` / `multica-platform-confluence`	读 PRD / Issue（开工前）；写由 `multica-artifact-architect` 编排

本 skill 只产出本地 design.md；凭据与发布 CLI 见 platform skill。

Process

读 PRD / Issue 与验收标准（AC-/FR-/BR-）。
检查当前实现（优先 codegraph / 现有模式，不大面积扫库）。
识别相关模块与现有模式。
确定最小可行改动；非目标写清楚。
识别数据/接口/非功能影响与依赖（RISK-、DECISION-）。
定义验证方式（对齐 AC-）；填需求追溯表。
写文档头部元数据（创建者、创建时间、版本、状态）。
信息不足 → BLOCKED，写入「待决事项」，不猜。

Principles

text
现有模式 > 新抽象
小改动   > 大重构
复用     > 新依赖
可验证   > 不可验证的设想
可回滚   > 一次性不可逆改动

本地草稿路径

text
docs/design/<ISSUE-KEY>/design.md

章节基线见 multica-platform-confluence/scripts/templates/design-template.md。

文档头部（必须，置于 H1 标题下）

设计正文第一块必须是元数据表，便于 ArchReviewer 追踪版本与责任人：

字段	规则
创建者	`Architect-<member-id>`（与 Squad member 一致）
创建时间	`YYYY-MM-DD HH:mm`（团队约定时区，默认 UTC+8）
版本	语义化 `v0.1` 起；每次因评审修改递增（v0.2、v0.3 …）
状态	`草稿` → `评审中` → `已通过`；废弃用 `已废弃`
JIRA	Issue Key
上游 PRD	Confluence 需求页链接（从 JIRA 解析，勿留空）

示例：

markdown
# 技术设计 — PROJ-1813 分片上传

| 字段 | 值 |
| --- | --- |
| **创建者** | Architect-u1024 |
| **创建时间** | 2026-08-26 15:30 |
| **版本** | v0.1 |
| **状态** | 草稿 |
| **JIRA** | PROJ-1813 |
| **上游 PRD** | http://confluence.../pages/viewpage.action?pageId=... |

Output（必须包含）

章节	必填	内容
文档头部	是	创建者、创建时间、版本、状态、JIRA、上游 PRD
理解	是	系统当前做什么；与 PRD 范围对齐
非目标	是	明确不做的事，防范围蔓延
建议改动	是	最小可行方案；可选「方案备选与取舍」简述
受影响组件	是	文件 / 模块 / 服务 · 变更类型 · 说明
数据与状态	涉及时	实体/字段/状态变更；一致性要求
接口与契约边界	涉及时	前后端/UI 边界；错误与鉴权约定
实现步骤	是	给 @FrontendDev / @BackendDev 的可执行步骤
非功能需求	按需	性能、安全、可用性、可观测性对策
迁移与回滚	按需	数据迁移、功能开关、回滚步骤
验证计划	是	验证项 · 方式 · 对应 AC-
需求追溯	是	AC-/FR-/BR- → 设计决策 → 实现步骤
风险与边界	是	RISK-n · 风险 · 缓解
待决事项	有则填	DECISION-n；BLOCKED 项
评审回应	复审时	对照 ArchReviewer 修改清单逐条回应
修订记录	是	日期 · 版本 · 作者 · 变更摘要

架构师写作角度（易漏项）

设计评审常在这些角度被追问，初稿尽量覆盖：

角度	自检问题
范围	非目标是否写清？是否偷偷扩需求？
数据	谁写谁读？一致性/事务边界？历史数据怎么办？
并发与幂等	重复提交、竞态、重试是否考虑？
失败与降级	依赖挂了怎么办？部分失败可接受吗？
安全	鉴权、敏感数据、审计日志是否说明？
性能	量级假设？热点路径？是否需要异步/缓存？
可测试性	实现步骤能否对应到可执行的验证？
运维	部署顺序、配置项、监控告警、回滚？
跨端一致	与 UI/API 契约是否冲突？错误码/状态机是否统一？
追溯	每条 AC- 是否能在设计中找到落点？

复审修订流程（配合 multica-review-architect）

读 Leader 转发的 ArchReviewer 修改清单（含阻断项 ID）。
版本 +1（如 v0.1 → v0.2），状态改 评审中。
在 评审回应 表逐条填写：已修改 / 不采纳（须写理由）。
更新受影响章节；修订记录追加一行。
重新自检 → multica-artifact-architect → platform 发布（Confluence upsert 同 title 会更新版本）。
通知 Leader 已修订，进入下一轮 ArchReviewer 复审（最多 3 轮）。

不采纳阻断项须 Leader 裁决，Architect 不得自行关闭评审。

Handoff

text
先用 multica-technical-design 写 docs/design/<ISSUE-KEY>/design.md（含头部元数据），
再用 multica-artifact-architect 自检后按 platform skill 发布并回传链接。

发布命令见 multica-platform-confluence（publish_design.py --append-jira）。

为什么有效

头部元数据 + 版本 + 评审回应，让多轮 ArchReviewer 评审可审计、可 diff；章节覆盖数据/非功能/追溯等角度，减少下游实现阶段返工。

Frequently asked questions

What does the Multica Technical Design AI skill do?

Why use Multica Technical Design on TypingMind?

Because you install it once and use it with any model. Multica Technical Design is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Multica Technical Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/it235/multica-best-practices/tree/main/templates/zh_CN/skills/architect/multica-technical-design. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Multica Technical Design?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Multica Technical Design?

As many as you like. As long as a model supports skills, you can use Multica Technical Design with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Multica Technical Design AI skill free?

Yes. It is published on GitHub by it235 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Pretext

NousResearch

OrganizationPopular

Build creative browser demos with DOM-free text layout.

Sketch

Throwaway HTML mockups: 2-3 design variants to compare.

Tldraw Offline

Drive and script tldraw offline canvases with an agent.

Brand Guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Technical Design

Purpose

Platform 协作

Process

Principles

本地草稿路径

文档头部（必须，置于 H1 标题下）

Output（必须包含）

架构师写作角度（易漏项）

复审修订流程（配合 multica-review-architect）

Handoff

为什么有效

Frequently asked questions

Related AI Skills

Set up your own AI workspace now