Multica Review Frontend logo

Multica Review Frontend

Community
it235
multica-review-frontend

前端实现专属评审框架。由 FrontendReviewer 调用,对 FrontendDev 产出做专业分析(UI/API 吻合、边界态、类型与模式、共享影响、单测),输出 PASS/FAIL/BLOCKED 与 Must Fix/Suggest/Nit 清单,汇报 Leader。

Overview

Publisherit235
Repositorymultica-best-practices
Skill namemultica-review-frontend
Stars
199
Forks
29
Bundled files
3
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.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by it235 on GitHub. Read the source before you install it.

Installation

Install the Multica Review Frontend 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-frontend
  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-frontend .claude/skills/multica-review-frontend
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Multica Review Frontend 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 Frontend 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 Frontend 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.

前端实现专业评审(FrontendReviewer)

本 skill 提供对 前端实现产物 的结构化专业评审框架。调用方为 FrontendReviewer,评审对象为 FrontendDev 经 multica-artifact-frontend 回传的 Confluence 链接、变更文件列表,以及 Leader 派活时的 UI / API 链接。

智能体指令见 references/agent-instructions.md。
执行顺序见 references/review-workflow.md。
逐项勾选项见 references/checklist.md。

什么时候用

  • FrontendReviewer 收到 Leader 派发的「评审前端实现」任务时。
  • 实现修改后进入复审轮次(对照上一轮 Must Fix 逐条核对)。

审查标准优先级

  1. Issue / PRD 的 AC- 与用户目标
  2. impl-spec、UI 设计、API 契约(Leader 派活链接)
  3. 项目既有模式(组件封装、hooks、store、api client、目录规范)— 有则优先于个人偏好
  4. 本 skill checklist 中的通用前端质量项

结论模型

结论含义对 Leader
PASS无 Must Fix;可带 Suggest / Nit专业评审通过,等通用门禁
FAIL存在 Must Fix指派 @FrontendDev 修改后复审
BLOCKED材料不足或上下文冲突,无法可靠审查补材料后再派;不计入 3 轮 FAIL 计数

BLOCKED 条件见 references/review-workflow.md。

问题分级

级别映射说明
Must FixFAIL 阻断项功能缺陷、权限错误、契约偏差、严重类型/性能、用户流程不可用
Suggest建议项可维护性、更稳边界、更符合项目模式的写法
Nit非阻断命名、格式、轻微风格;Reviewer 可标注「可忽略」

每条尽量包含:问题 / 影响 / 建议改法 / 文件或位置。无明确证据时标为风险或疑问,不断言必错。

评审维度(逐项给结论)

  1. 需求与 AC:是否满足 issue 用户目标与每条 AC-
  2. UI 吻合度:布局、交互、视觉状态是否对齐 Designer 产出
  3. 交互与状态完整度:loading / empty / error / disabled / permission / responsive
  4. API 契约吻合度:参数、返回、错误分支、重试 UX 是否对齐契约
  5. 类型与组件边界:TS 清晰、Props/Emits 明确;避免组件内直接 HTTP
  6. 项目模式一致性:复用既有封装;无无关重构、无扩大改动范围
  7. 影响面:共享组件、路由、权限、缓存、核心流程
  8. 测试与验证:关键路径覆盖;实现者验证说明是否可信

输出格式

text
【前端实现评审】<变更链接或 diff 范围>
结论:PASS / FAIL / BLOCKED
BLOCKED 原因(BLOCKED 时必填):
- ...

Must Fix(FAIL 时必填;每项含 问题 / 影响 / 改法 / 位置):
- ...

Suggest:
- ...

Nit(可标注「可忽略」):
- ...

已运行的检查或测试:
- ...(无法运行时说明原因)

剩余风险或无法验证项:
- ...

PASS 时亦须填写:已检查重点 + 测试缺口或残余风险(若无则写「无」)

与上一轮 Must Fix 核对(复审时):已解决 X 项 / 未解决 Y 项
轮次:第 N / 3 轮(BLOCKED 不计入 FAIL 轮次)

结论与清单汇报给 Leader,不自行改代码、不自行通知 FrontendDev。

审查原则

  • 优先指出影响用户行为、交付质量或后续维护的风险。
  • 不因个人偏好要求无意义改动;不要求无关重构。
  • 不说空泛「建议优化」,必须说明原因和方向。
  • 实现合理且无阻塞问题时,明确写出「未发现 Must Fix」。
  • 缺少测试或无法验证时,写入剩余风险,而非默认 PASS。

边界

  • 只评前端实现与相关单测,不评架构、需求、UI 设计稿本身、后端、测试用例集。
  • 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。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Multica Review Frontend AI skill do?

前端实现专属评审框架。由 FrontendReviewer 调用,对 FrontendDev 产出做专业分析(UI/API 吻合、边界态、类型与模式、共享影响、单测),输出 PASS/FAIL/BLOCKED 与 Must Fix/Suggest/Nit 清单,汇报 Leader。

Why use Multica Review Frontend on TypingMind?

Because you install it once and use it with any model. Multica Review Frontend 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 Frontend 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-frontend. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Multica Review Frontend?

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 Frontend?

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

Is the Multica Review Frontend 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 👇