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。
Install
npx skills add it235/multica-best-practices --skill multica-review-productgit 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-productPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# 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`](references/agent-instructions.md)。 执行顺序见 [`references/review-workflow.md`](references/review-workflow.md)。 勾选项见 [`references/checklist.md`](references/checklist.md)。 报告格式见 [`references/report-template.md`](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-jira` | Leader 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
Details
- Skill name
multica-review-product- Repository
- it235/multica-best-practices
- Path
templates/zh_CN/skills/reviewer/multica-review-product/SKILL.md- License
- MIT
- Repo updated
- 4 November 2026
FAQ
What does the Multica Review Product 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。
How do I install the Multica Review Product skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add it235/multica-best-practices --skill multica-review-product. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Multica Review Product popular?
It lives in it235/multica-best-practices, which has 279 GitHub stars and 33 forks.
Related skills
Multica Artifact Architect
279it235/multica-best-practices
Land technical design artifacts to the code repo or knowledge platform (default Git repo / Confluence). Used by @Architect to upload technical design for downstream implementation and test consumption. Swappable platform.
Multica Artifact Architect
279it235/multica-best-practices
架构师产物薄编排:校验设计草稿规范,落地时只调 multica-platform-confluence + multica-platform-jira。用于 @Architect 发布设计文档。
Multica Artifact Backend
279it235/multica-best-practices
Land API contract artifacts to the API collaboration platform (default Apifox). Used by @BackendDev to upload API contract for downstream frontend / test consumption. Swappable platform.
Multica Test T3 API Automation
279it235/multica-best-practices
T3 API automation—only after G2.5 PASS; run Apifox scenarios by contract, join overall verdict with UI side. Requires env + Apifox three IDs complete; no local mock as substitute.
Linear
230initializ/forge
Read Linear issues, transition state, and post comments. The entry point for ticket-driven agent workflows.
Planning with Files
193MavCui/Agent-Skills-Hunter
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.