Multica Review Architect logo

Multica Review Architect

Community
it235
multica-review-architect

架构设计专属评审框架。由 ArchReviewer 调用,对 Architect 产出的技术架构设计做多维度专业分析,输出 PASS/FAIL 与带 ID 的修改清单,汇报 Leader。

Overview

Publisherit235
Repositorymultica-best-practices
Skill namemultica-review-architect
Stars
199
Forks
29
Bundled files
Instructions only
LicenseMIT
Links
  • 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 Review Architect AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/it235/multica-best-practices/tree/main/templates/zh_CN/skills/reviewer/multica-review-architect
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

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/reviewer/multica-review-architect .claude/skills/multica-review-architect
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Multica Review Architect 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 Review Architect 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 Review Architect 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.

架构设计专业评审(ArchReviewer)

本 skill 提供对技术架构设计产物的结构化专业评审框架。调用方为 ArchReviewer,评审对象为 Architect 经 multica-artifact-architect 回传的设计链接。

什么时候用

  • ArchReviewer 收到 Leader 派发的「评审架构设计」任务时。
  • 设计修改后进入复审轮次时(对照上一轮修改清单 + 评审回应表逐条核对)。

评审前置检查(元数据)

设计文档 H1 下必须有元数据表;缺项或复审未升版本 → 可直接 FAIL:

检查项FAIL 条件
创建者 / 创建时间 / 版本 / 状态 / JIRA / 上游 PRD任一缺失
复审稿版本未高于上一轮(如仍 v0.1 却称已修改)
修订记录与版本不一致或缺少本轮条目
评审回应复审稿未逐条回应上一轮阻断项

评审维度(逐项给结论)

每项标注 PASS / FAIL / N/A,FAIL 须写入修改清单并分配 REV-n ID。

A. 文档与流程

  1. 元数据与版本:头部信息完整;修订记录与版本一致。
  2. 评审回应完整性(复审):上一轮 REV-n 是否逐条回应;不采纳项是否有充分理由(仍可能阻断,交 Leader 裁决)。

B. 方案质量

  1. 方案合理性:分层、模块边界、依赖方向清晰;无过度设计或明显设计不足。
  2. 范围与非目标:与 PRD/Issue 一致;非目标明确;无隐性扩 scope。
  3. 方案备选与权衡:是否说明为何不用更简方案(复杂度高时必问)。

C. 正确性与一致性

  1. 验收对齐:逐条覆盖 AC-/FR-/BR-;需求追溯表完整无悬空 AC。
  2. 跨端一致性:前后端/UI 契约边界自洽;状态机、错误语义不冲突。
  3. 数据与一致性:实体/字段变更清楚;读写归属、事务边界、历史数据策略明确。

D. 可靠性与安全

  1. 失败模式与降级:依赖失败、超时、部分失败时的行为;是否可接受。
  2. 并发与幂等:重复请求、竞态、重试策略是否定义。
  3. 安全与权限:鉴权、敏感数据、审计;是否满足团队基线。
  4. 关键技术风险:性能、容量、一致性风险是否识别并有对策;无对策 = 阻断。

E. 可落地与可运维

  1. 扩展性与可维护性:常见变更成本;是否引入难逆技术债。
  2. 可测试性:验证计划能否执行;实现步骤是否可对应测试。
  3. 迁移与回滚:数据迁移、发布顺序、功能开关、回滚路径(涉及时必填)。
  4. 可观测性:日志、指标、告警是否足够定位生产问题。

F. 开放项

  1. 待决事项:DECISION-/BLOCKED 是否阻塞进入开发;是否需 Leader/PM 关闭。

输出格式

text
【架构设计评审】<设计链接>
文档版本:v0.x(元数据表)
结论:PASS / FAIL

元数据检查:PASS / FAIL — <说明>

维度结论摘要:
- A 文档与流程:...
- B 方案质量:...
- C 正确性与一致性:...
- D 可靠性与安全:...
- E 可落地与可运维:...
- F 开放项:...

阻断项(FAIL 时必填,ID 稳定便于复审核对):
- REV-1 | 维度 | 理由 | 涉及章节/AC | 修改方向
- REV-2 | ...

建议项(非阻断):
- SUG-1 | ...

与上一轮核对(复审时):
- REV-x:已解决 / 未解决 / 不采纳待 Leader 裁决
- 已解决 X 项 / 未解决 Y 项

轮次:第 N / 3 轮

结论与修改清单汇报给 Leader,不自行修改设计、不自行通知 Architect。

评审原则

text
无对策的风险     → 阻断
悬空 AC-         → 阻断
复审未升版本     → 阻断
范围蔓延无依据   → 阻断
「以后再补」     → 阻断(除非写入待决且 Leader 同意带条件 PASS)

边界

  • 只评架构设计,不评 UI 视觉、产品优先级、代码实现、测试用例细节。
  • 不替代 Leader 的通用门禁(multica-verification skill)。
  • 第 3 轮仍 FAIL → 标注「升级人类」,交 Leader 处理,停止循环。

为什么有效

带 REV-n ID 的清单 + 文档版本 + 评审回应表,使多轮修订可追踪;17 维覆盖数据/安全/运维等 Architect 易漏角度,减少 G2 后才发现的设计缺陷。

Frequently asked questions

What does the Multica Review Architect AI skill do?

架构设计专属评审框架。由 ArchReviewer 调用,对 Architect 产出的技术架构设计做多维度专业分析,输出 PASS/FAIL 与带 ID 的修改清单,汇报 Leader。

Why use Multica Review Architect on TypingMind?

Because you install it once and use it with any model. Multica Review Architect 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 Review Architect 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/reviewer/multica-review-architect. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Multica Review Architect?

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 Review Architect?

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

Is the Multica Review Architect 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇