pm-prd-review SKILL.md skillA

pm-prd-review from konglong87/superpm is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add konglong87/superpm/pm-prd-review@git:20260924.3ac45f5

Pins git:20260924.3ac45f5 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
konglong87/superpm
Path
skills/02-solution-design/pm-prd-review/SKILL.md
Versions recorded
4
Latest version
git:20260924.3ac45f5, committed Sep 24, 2026
First version recorded
Jul 30, 2026
Size
6,238 bytes
Repository stars
86
License
MIT

Use when: 需要评审 PRD/BRD/MRD 等需求文档的质量、检查完整性/清晰度/可行性/指标/风险/一致性、在开发前做文档把关 Do NOT use when: 文档尚未产出(应先 /pm-docs 生成);仅需口头讨论无需书面评审.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

## Preamble (run first)

```bash
# 检查待评审文档
echo "📋 查找待评审文档..."
for f in "docs/02-方案设计/PRD产品需求文档.md" "docs/02-方案设计/BRD商业需求文档.md" "docs/02-方案设计/MRD市场需求文档.md" "docs/02-方案设计/PRD.md"; do
  if [ -f "$f" ]; then echo "✅ 找到: $f"; fi
done
```

---

## 写入时边界

只讨论时不写文件,启动检查不创建目录。用户要求保存产物时,先确认当前产品、精确输出路径及已有文件的覆盖/追加选择;确认后**仅在实际 Write 前**创建该输出文件的父目录。完整安装可参见 `skills/_shared/artifact-policy.md`,单独安装本 skill 也按本段执行。

---

## 前置门禁

本技能用于**评审已有文档**,必须先有可评审文件:

1. 检查 `docs/02-方案设计/` 下是否存在 PRD/BRD/MRD(或用户提供的其他路径)。
2. 若存在 → 读取并进入评审流程。
3. 若不存在 → 停止,告知用户先执行 `/pm-docs` 生成文档,或提供文档路径/内容后再评审。

不得在门禁不满足时编造评审对象。

---

## 跨 Agent 交互规则

当流程要求与用户交互时:

1. 如果当前环境支持 AskUserQuestion,使用 AskUserQuestion(最佳体验)。
2. 如果当前环境不支持 AskUserQuestion,必须用普通聊天消息提出同样问题。
3. 一次只问一个问题。
4. 提问后必须停止当前回合,等待用户回答(STOP and WAIT)。
5. 不得在用户回答前生成文档、写入 docs。
6. 已有 docs 文件不能替代本轮用户回答。

---

## 适用场景

- 用户说"评审 PRD""PRD 写得怎么样""帮我审一下需求文档""文档质量检查""BRD 复盘"
- 与 `pm-docs` 区分:pm-docs 是"写",本技能是"审"——在开发/评审会前做质量把关。

---

## 执行流程

### 步骤 1: 确定评审范围与标准(主 agent - 用户交互)

使用 AskUserQuestion 询问:

> 🔍 评审设置
>
> 你要评审哪个文档 / 哪些维度?
>
> A) 评审 PRD(默认全套维度)
> B) 评审 BRD
> C) 评审 MRD
> D) 自定义维度(仅完整性 / 仅可行性 / 仅风险 …)
>
> 评审严格度:
> 1) 快速体检(关键问题)
> 2) 深度评审(逐条清单,推荐用于评审会前)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add konglong87/superpm/pm-prd-review@sha256:8b611954e684c958

The line at the top of this page pins the label git:20260924.3ac45f5, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_yvozd3td6ejhbuuz.svg)](https://markdownregistry.com/a/art_yvozd3td6ejhbuuz)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Jul 30, 2026 and Sep 24, 2026, about one every 19 days.

versioncommittedcommitsizeaudit
git:20260924.3ac45f5 latest2026-09-24 3ac45f5 6,238 BA view · diff
git:20260924.26fb3bb2026-09-24 26fb3bb 5,926 BA view · diff
git:20260730.fea8df72026-07-30 fea8df7 6,006 BA view · diff
git:20260730.1745f932026-07-30 1745f93 6,331 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6238 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

konglong87/superpm · 86 stars · license MIT · pushed 2026-10-26 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_yvozd3td6ejhbuuz
GET https://markdownregistry.com/api/v1/resolve?ref=konglong87/superpm/pm-prd-review
GET https://markdownregistry.com/api/v1/blob/8b611954e684c958bea4bc4221ed3c433de2b39df08b3df4b7c38470825d1602

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from konglong87/superpm

analyze-growth SKILL.md skill
konglong87/superpm · commands/analyze-growth/SKILL.md
git:20260924.7250d3a · audit C · 86 stars
define-strategy SKILL.md skill
konglong87/superpm · commands/define-strategy/SKILL.md
git:20260924.7250d3a · audit C · 86 stars
discover SKILL.md skill
konglong87/superpm · commands/discover/SKILL.md
git:20260924.7250d3a · audit C · 86 stars
plan-launch SKILL.md skill
konglong87/superpm · commands/plan-launch/SKILL.md
git:20260924.7250d3a · audit C · 86 stars
validate-idea SKILL.md skill
konglong87/superpm · commands/validate-idea/SKILL.md
git:20260924.7250d3a · audit C · 86 stars
write-prd SKILL.md skill
konglong87/superpm · commands/write-prd/SKILL.md
git:20260924.7250d3a · audit C · 86 stars
llms.txt llms.txt file
konglong87/superpm · llms.txt
git:20261023.471cbf9 · audit A · 86 stars
pm-evidence-audit SKILL.md skill
konglong87/superpm · skills/00-tools/pm-evidence-audit/SKILL.md · Use when: 审核产品调研、市场分析、增长报告或 PRD 中的关键结论是否有可追溯证据,核对来源、日期、推断与冲突 Do NOT use when: 只需评审 PRD 的完整性和表达(用…
git:20260924.0fc202e · audit A · 86 stars
pm-selfcheck SKILL.md skill
konglong87/superpm · skills/00-tools/pm-selfcheck/SKILL.md · Use when: 需要检查 super-pm 技能包安装完整性、元数据和体积 Do NOT use when: 正在执行具体 PM 任务且不需要安装诊断
git:20260924.26fb3bb · audit A · 86 stars
prompt-pe SKILL.md skill
konglong87/superpm · skills/00-tools/prompt-pe/SKILL.md · Use when the user explicitly invokes /prompt-pe or explicitly asks to clarify, enhance, or rewrite a vague prompt Do…
git:20261014.43f3bc2 · audit A · 86 stars
pm-brainstorm SKILL.md skill
konglong87/superpm · skills/01-demand-insight/pm-brainstorm/SKILL.md · Use when: 需要创意方案、探索产品方向、发散思维、本质问题分析 用户说"我想做一个XX""帮我规划XX产品""帮我设计一下需求" 用户给出新产品方向,但尚未完成本轮 brainstorm 交互确认 新产品从0到1的第一步 Do…
git:20261023.471cbf9 · audit A · 86 stars
pm-clarify SKILL.md skill
konglong87/superpm · skills/01-demand-insight/pm-clarify/SKILL.md · Use when: 有初步需求清单需要细化细节、需明确需求场景和边界条件、需求描述模糊需要结构化 Do NOT use when: 需求已足够详细可直达开发、仅需快速立项无需深入
git:20260924.3ac45f5 · audit A · 86 stars

Every file in konglong87/superpm

Browse by kind, by grade A, or by owner.