TypingMindTypingMindThe best frontend for AI
Multica Review Product logo

Multica Review Product

Community
it235
multica-review-product

需求/PRD 专属评审框架。ProductReviewer 对 multica-pm-artifact-publish 提交的 PRD 做价值/逻辑/清晰度三阶段评审，输出 PASS/FAIL/BLOCKED 与 Must Fix/Suggest/Nit，汇报 Leader；FAIL 后 PM Workflow B 复审。

Overview

Publisherit235
Repositorymultica-best-practices
Skill namemultica-review-product
Stars
199
Forks
29
Bundled files
4
LicenseMIT
Links
Skill sourceRepository
  • 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.

  • 4 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 Product 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-product
  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-product .claude/skills/multica-review-product
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Multica Review Product 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 Product 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 Product 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.

需求（PRD）专业评审（ProductReviewer）

本 skill 提供对 PRD / 需求产物 的结构化专业评审。调用方为 ProductReviewer，评审对象为 ProductManager 经 multica-pm-artifact-publish 回传的 Confluence / JIRA 链接。

智能体指令见 references/agent-instructions.md。
执行顺序见 references/review-workflow.md。
勾选项见 references/checklist.md。
报告格式见 references/report-template.md。

什么时候用

  • ProductReviewer 收到 Leader 派发的「评审 PRD」任务时
  • PM 经 Workflow B 更新 后的复审轮次（对照上一轮 Must Fix 逐条核对）

Platform 协作（可选、只读）

Platform skill用途
团队知识库（可选）核对术语、模块边界、历史背景（参考）
multica-platform-confluence / multica-platform-jiraLeader 未给全文时只读拉取 PRD（不创建/不改状态）

KB 用法二分（与 PM spec 一致）：

  • 可引用：术语、入口路径、权限名别名（核对 PRD 是否写清）
  • 禁止：把 KB/Confluence 历史规则写成当前 PRD 的「应有 AC/FR」（规则扩写 → Must Fix 级误判，应标为参考差异而非 PM 缺陷）
  • KB 不可用：标注「知识库不可用」，不 BLOCKED，继续审 PRD 正文

审视输入（缺则 BLOCKED）

必需说明
PRD 全文Confluence/JIRA 链接或 Leader 提供的等价正文
需求上下文Issue、Story Key、业务背景（Leader 派活或 Issue 内）
可选说明
原型/Figma 链接核对与文字 PRD 是否冲突
数据口径、依赖系统跨系统/看板类需求

用例源与 PRD 都缺 → BLOCKED，列缺失项，汇报 Leader。

三阶段审视（严格顺序）

阶段 1：价值判断

评估是否值得在当前 scope 内推进（结论写入报告，价值硬伤 → Must Fix → FAIL）：

  • 问题真实性：是否解决真实、紧迫的业务/用户问题
  • 价值与 ROI：收益是否清晰、可衡量；投入产出是否合理
  • 时机与优先级：范围是否应分期而非一次做大
  • 替代方案：是否有更低成本路径（配置、运营、复用已有能力）
  • 成功标准：KPI-/G- 是否可验证；缺失视为重大缺陷

阶段摘要：值得做 / 不值得做 / 待补充信息后判断（后两者通常对应 FAIL 或 BLOCKED）

阶段 2：逻辑审视（价值可讨论或值得做时执行）

  • 目标 → 方案 → 验收 链路完整、前后一致
  • 用户角色与权限：全场景覆盖；无越权/缺权限路径
  • 主流程 + 异常 + 边界：空态、错误态、无权限态
  • BR- 无矛盾；状态机/流转闭合
  • 字段/数据口径：分子分母、数据源、刷新频率
  • 依赖与假设显式；范围与非范围清晰；跨系统/API 责任方清楚

阶段摘要：逻辑闭环 / 逻辑有缺口 / 逻辑不自洽

阶段 3：清晰度审视（贯穿全文）

无法让设计/开发/测试直接执行的点，编号 Q-001、Q-002…（类型：价值/逻辑/清晰度）：

  • 模糊词：适当、优化、等相关、等等、视情况、体验好
  • 缺 AC- 的功能描述；缺字段/状态/权限定义
  • 原型与文字 PRD 冲突且未说明以谁为准
  • OP- 散落各处、无 Owner 或阻塞开发未标注

结论模型

结论含义对 Leader
PASS无 Must Fix；可有 Suggest/Nit专业评审通过；仍须 verification；OP- 未关不得开发
FAIL存在 Must Fix（含价值硬伤、逻辑缺口、清晰度阻断）指派 PM：multica-pm-requirement-spec 修订 → multica-pm-artifact-publish Workflow B → 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 3 轮 FAIL

BLOCKED 条件见 references/review-workflow.md。

问题分级

级别说明
Must FixFAIL 阻断；价值硬伤、逻辑不自洽、AC 不可测、阻塞开发的 OP-
Suggest可维护性、更清晰表述、更稳边界
Nit措辞、格式；可标注「可忽略」

每条须含：问题 / 影响 / 建议 / PRD 位置（章节或 G-/FR-/BR-/AC-/OP- 编号）。

输出

使用 references/report-template.md 模板。简要头：

text
【PRD 评审】<链接>
结论：PASS / FAIL / BLOCKED
价值判断：值得做 / 不值得做 / 待判断
逻辑判断：逻辑闭环 / 有缺口 / 不自洽
Must Fix / Suggest / Nit / Q- 清单 …
轮次：第 N / 3 轮（BLOCKED 不计 FAIL 轮次）

Review 后修订闭环（与 PM 分工）

结论ProductReviewerProductManager
FAIL输出 Must Fix；不改 PRDLeader 指派：spec 修订 → publish Workflow B → 请求复审
PASS汇报 LeaderOP- 未关闭仍不得进开发
BLOCKED列缺失项Leader/人类补材料

PASS ≠ G1 通过。 不自行通知下游、不创建/更新 JIRA/Confluence、不 @ 其他 Agent。

审查原则

  • 先读全文，再下结论；禁止只看标题或摘要
  • 每个问题可追溯到 PRD 原文位置
  • 不为了友善而通过有硬伤的需求
  • 无明确证据时标「风险/疑问」，不断言必错
  • PASS 时仍写已查重点与残余 OP-/Suggest 风险

边界

  • 只评 PRD/需求，不评设计、代码、测试、UI
  • 不替代 Leader 的 multica-verification
  • 技术可行性交 ArchReviewer
  • 第 3 轮仍 FAIL → 标注「升级人类」，交 Leader

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 Product AI skill do?

需求/PRD 专属评审框架。ProductReviewer 对 multica-pm-artifact-publish 提交的 PRD 做价值/逻辑/清晰度三阶段评审，输出 PASS/FAIL/BLOCKED 与 Must Fix/Suggest/Nit，汇报 Leader；FAIL 后 PM Workflow B 复审。

Why use Multica Review Product on TypingMind?

Because you install it once and use it with any model. Multica Review Product 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 Product 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-product. 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 Product?

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 Product?

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

Is the Multica Review Product 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.

Related AI Skills

View all
obra logo

Brainstorming

obra
CommunityPopular

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

25.8K
288.1K
7 files
View
obra logo

Executing Plans

obra
CommunityPopular

Use when you have a written implementation plan to execute in a separate session with review checkpoints

25.8K
288.1K
Instructions
View
obra logo

Using Superpowers

obra
CommunityPopular

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

25.8K
288.1K
5 files
View
affaan-m logo

Context And Decisions

affaan-m
CommunityPopular

Govern stable domain context with a narrowly scoped CONTEXT.md when needed, and route hard-to-reverse decisions to ECC's existing architecture-decision-records skill. Use when domain terms require…

41.4K
277.3K
2 files
View

Set up your own AI workspace now

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