pm-demand SKILL.md skillA

pm-demand 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-demand@git:20260924.1f44a4d

Pins git:20260924.1f44a4d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
konglong87/superpm
Path
skills/01-demand-insight/pm-demand/SKILL.md
Versions recorded
5
Latest version
git:20260924.1f44a4d, committed Sep 24, 2026
First version recorded
Jul 30, 2026
Size
14,236 bytes
Repository stars
86
License
MIT

Use when: 用户明确要求需求调研、痛点验证,或已有产品需要验证一个具体需求 Do NOT auto-select when: 用户只想发散新产品方向(优先 pm-brainstorm)或只是简短讨论且不需正式调研 Direct /pm-demand requests may proceed with their own evidence checks; a full new-product chain can recommend brainstorm first.

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

## 输入与前置检查

先理解本次范围:完整调研报告还是只讨论一个需求?**只讨论时不写文件**,不自动创建 `docs/`。若已有相关且有效的需求报告,读取并复用,**无需重复提问**;仅同名却与当前产品不相关的文件不能复用。

完整新产品链默认建议先 `/pm-brainstorm`。用户显式要求局部需求验证、明确跳过 brainstorm 或已有相关创意材料时,直接验证需求,不强迫走完整链;缺少目标用户或问题定义时只问缺失的关键信息。不要把建议跳过解释为“头脑风暴已完成”。

---

产出要求:区分已核实证据(来源、日期)、待验证假设与用户决策;不要把访谈或市场数据编造成事实。后续优先级与 PRD 应能引用本报告中的需求及证据。

## 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. 只讨论时不写文件;正式产物仅在用户要求并确认目标后生成。
6. 已有相关且有效的 docs 可以复用,无需重复提问;不相关文档不能替代证据。

---

## 执行流程

下述为**完整调研报告模式**的详细步骤。轻量讨论仅执行当前问题所需的环节;信息已提供时直接引用而不是重复询问。任何跳过的验证均标注为待验证,不能伪称完成。

### 步骤 1: 补齐必要的产品基础信息

**关键原则**:
- 只问缺失的关键信息;已提供的信息无需重复提问
- 每个问题清晰、聚焦
- 等待用户回答后再问下一个

---

**问题 1: 产品名称**

使用 AskUserQuestion 询问:

> 请问您的产品名称是什么?
>
> 💡 提示:例如"每日优鲜"、"小红书"、"微信"

用户输入后,记录到变量 `PRODUCT_NAME`

---

**问题 2: 目标用户**

> 目标用户是谁?
>
> A) C端用户(个人消费者)
> B) B端用户(企业客户)
> C) 双边市场(平台模式)
> D) 其他(请手动输入)
>
> 💡 提示:选择后请进一步细化,如"25-35岁一线城市女性"、"中小型餐饮老板"

用户回答后,记录到变量 `TARGET_USER`

---

**问题 3: 核心业务目标**

> 您希望达成的核心业务目标是什么?
>
> A) 提升收入(如GMV、付费转化)
> B) 提升用户规模(如DAU、MAU)
> C) 提升用户留存(如复购率、日活)
> D) 降低成本(如人力、运营成本)
> E) 其他(请手动输入)
>
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add konglong87/superpm/pm-demand@sha256:39b3966bc2760b6a

The line at the top of this page pins the label git:20260924.1f44a4d, 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_wkp5qm7m6ywljhvl.svg)](https://markdownregistry.com/a/art_wkp5qm7m6ywljhvl)

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

Versions

The registry has recorded 5 versions of this file, between Jul 30, 2026 and Sep 24, 2026, about one every 14 days.

versioncommittedcommitsizeaudit
git:20260924.1f44a4d latest2026-09-24 1f44a4d 14,236 BA view · diff
git:20260924.26fb3bb2026-09-24 26fb3bb 14,445 BA view · diff
git:20260924.7250d3a2026-09-24 7250d3a 14,525 BA view · diff
git:20260730.fea8df72026-07-30 fea8df7 14,314 BA view · diff
git:20260730.1745f932026-07-30 1745f93 14,639 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 (14236 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_wkp5qm7m6ywljhvl
GET https://markdownregistry.com/api/v1/resolve?ref=konglong87/superpm/pm-demand
GET https://markdownregistry.com/api/v1/blob/39b3966bc2760b6a21f29c64540a471c65532feb66ebd539530a1419fea756cc

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.