product-strategy

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

product-strategy — the Discovery Brief

product-strategy — Discovery Brief

First link of the discovery pipeline. It interviews socratically —never agreeing too early— to separate the symptom from the cause, and closes by writing the Discovery Brief: the problem, the evidence behind it, and up to three prioritized hypotheses.

这是发现pipeline的首个环节。它采用苏格拉底式访谈——绝不过早认同——来区分症状与根源，最终输出Discovery Brief文档：包含问题、支撑证据以及最多三个经过优先排序的假设。

When it is invoked

触发时机

When	From / to
Discovery starts on a new opportunity or a problem with no prior research	Invocable on its own, over the loaded product node
The Discovery Brief is written	Exit toward `market-research` ( `.claude/skills/market-research/SKILL.md` ) — next station of the pipeline
The metric gate does not pass	Handoff toward `product-metrics` ( `.claude/skills/product-metrics/SKILL.md` ) — builds the North Star and the hypothesis metric before going on

product-metrics

is already installed in this pack: the handoff is real, not the dangling reference to a metrics coach that the old pipeline used to name.

时机	来源/去向
针对新机会或无前期研究的问题启动发现流程	可独立触发，基于已加载的产品节点
Discovery Brief撰写完成	流转至 `market-research` （ `.claude/skills/market-research/SKILL.md` ）——pipeline的下一个环节
未通过指标门槛	移交至 `product-metrics` （ `.claude/skills/product-metrics/SKILL.md` ）——先构建北极星指标与假设指标，再继续推进

本套件中已安装

product-metrics

：移交是真实可行的，而非旧pipeline中提及的指向指标指导工具的无效引用。

The interview

访谈流程

It is run with the pressure method of

.claude/skills/grill/SKILL.md#method

— cited by path, never copied.

访谈采用

.claude/skills/grill/SKILL.md#method

中的施压法——仅通过路径引用，不复制内容。

Socratic: it does not agree

苏格拉底式：绝不认同

Faced with a proposal that already arrives shaped as a solution ("we need a tracking dashboard", "we have to add notifications"), the answer is neither accepted nor elaborated: the counter-question that separates the solution from the problem is returned.

Bad: "good idea, what would that dashboard have?"

Good: "that is a solution. What problem does it solve, and whose problem is it?"

It repeats until the answer names a concrete person's problem — never a feature.

若收到已成型的解决方案提案（如“我们需要一个追踪仪表盘”“必须添加通知功能”），既不接受也不展开讨论，而是反问以区分解决方案与问题本质。

错误示例：“好主意，这个仪表盘需要包含什么内容？”

正确示例：“这是一个解决方案。它要解决什么问题？是谁的问题？”

反复追问，直到得到具体用户的问题描述——而非功能需求。

Evidence hierarchy

证据层级

All evidence backing the problem is graded with the same hierarchy

grill

uses:

behavior > data > claim > assumption

. "Several clients asked for it" (claim) does not weigh the same as "3 out of 5 abandon checkout at the shipping step" (data), nor as a recorded session where someone tries it and gets stuck (behavior). The lowest-grade evidence available is recorded anyway, with its level next to it — it is not discarded, it is labeled.

所有支撑问题的证据均采用与

grill

相同的层级进行分级：

behavior > data > claim > assumption

。“多位客户提出需求”（claim）的权重，与“5位用户中有3位在配送步骤放弃结账”（data）或用户尝试操作时受阻的录屏（behavior）不同。即使是最低层级的证据也会被记录，并标注其层级——不会被丢弃，仅做标签分类。

The metric gate

指标门槛

With no metric, the problem is not clear. Before accepting the problem as well posed, the question is asked: which number would move if this were solved? If there is no answer, or the one that shows up is a vanity metric (it changes no decision), the gate does not pass: it is said explicitly and the work is handed off to

product-metrics

to build it before going on. Nothing proceeds as if the gate had passed.

没有指标，问题就不清晰。 在确认问题定义明确前，会提出问题：若该问题得到解决，哪个数值会发生变化？若没有答案，或给出的是 vanity metric（无法影响决策的虚荣指标），则无法通过门槛：会明确告知结果，并将工作移交至

product-metrics

先构建指标，再继续推进。未通过门槛前，流程不会继续。

Hypotheses, with a fixed format

固定格式的假设

Every hypothesis is written in this shape, without exception:

We believe that [segment] [does X] at [moment] because of [cause]; if that is true, we will see [evidence].

Generic example (e-commerce): "We believe that buyers who abandon the cart at the shipping step do so because the cost only appears there; if that is true, we will see that showing the cost earlier reduces abandonment at that step." A hypothesis without the "if that is true, we will see..." clause is not a hypothesis: it is an opinion shaped like one, and it is returned with a counter-question.

At most 3, prioritized by risk × impact — never by order of appearance in the conversation. Risk: how little is known about whether it is true. Impact: how much it moves the gate metric if confirmed. A fourth hypothesis that shows up is recorded as a gap in the backlog; it does not enter the list.

所有假设必须严格遵循以下格式：

We believe that [segment] [does X] at [moment] because of [cause]; if that is true, we will see [evidence].

通用示例（电商场景）：“We believe that buyers who abandon the cart at the shipping step do so because the cost only appears there; if that is true, we will see that showing the cost earlier reduces abandonment at that step.” 缺少“if that is true, we will see...”部分的内容不能称为假设：只是伪装成假设的观点，会被退回并要求修正。

最多保留3个，按风险×影响优先级排序 ——而非按对话中出现的顺序。风险：对假设真实性的未知程度。影响：若假设成立，对门槛指标的影响幅度。第四个假设会被记录为待办事项，不会纳入列表。

The Discovery Brief

Discovery Brief文档

It closes by writing the deliverable as dated research of the loaded product node, in:

context/<YYYY-MM-DD>-discovery-brief.md

Dated, never overwritten — the same criterion the research folder of this repo already uses. The path falls inside

content: orgs/*/products/*/context/*.md

tree.md

: no new glob and no resolver row are needed.

The Brief carries these four sections, in this order, each with its literal heading:

undefined

最终输出的交付物是已加载产品节点的时效性研究内容，存储路径为：

context/<YYYY-MM-DD>-discovery-brief.md

带日期标记，永不覆盖——与本仓库研究文件夹的现有规则一致。该路径属于

tree.md

中

content: orgs/*/products/*/context/*.md

的范围：无需新增glob规则或解析器配置。

Brief包含以下四个固定顺序的章节，每个章节使用字面标题：

undefined

Problem

Evidence

Metric gate

Prioritized hypotheses


- **Problem**: the symptom separated from the cause, whose it is and why now.
- **Evidence**: each piece with its hierarchy level (`behavior`, `data`, `claim` or `assumption`)
  next to it.
- **Metric gate**: passed or not, and if it did not, the handoff to `product-metrics` left explicit.
- **Prioritized hypotheses**: up to 3, in the fixed format, ordered by risk × impact with the reason
  for the order.


- **Problem**：区分症状与根源的问题描述，明确受众及当前需解决的原因。
- **Evidence**：每条证据附带其层级标记（`behavior`、`data`、`claim`或`assumption`）。
- **Metric gate**：标注是否通过，若未通过，需明确记录移交至`product-metrics`的信息。
- **Prioritized hypotheses**：最多3个，采用固定格式，按风险×影响排序，并说明排序理由。

What this deliverable does not claim

交付物的局限性

The Discovery Brief does not replace the strategic layer that

prd

writes: it is dated research, input for the next stations of the pipeline, never the living canon of the product.

Discovery Brief文档不能替代

prd

撰写的战略层内容：它是时效性研究，作为pipeline后续环节的输入，而非产品的长效规范。

Standalone use

独立使用方式

Without a brain, the deliverable is written to a file in the current folder: the process is the same, but nothing is filed into a node, a backlog or a resolver, and no session scan brings it back later. Inside AI First OS the destinations named above are the real ones and this section does not apply.

The rest of the pack installs one skill at a time. Look at

.claude/skills/

first and offer only the ones that are not there — inside AI First OS they are all installed already, so nothing here gets offered:

grill

—

npx skills add pedroromeroluna/ai-first-product-skills --skill grill

market-research

—

npx skills add pedroromeroluna/ai-first-product-skills --skill market-research

prd

—

npx skills add pedroromeroluna/ai-first-product-skills --skill prd

product-metrics

—

npx skills add pedroromeroluna/ai-first-product-skills --skill product-metrics

The whole pack at once:

npx skills add pedroromeroluna/ai-first-product-skills

The system these skills come from is AI First OS —

github.com/pedroromeroluna/ai-first-os

— where they run over a brain instead of over the current folder.

若无核心系统支撑，交付物会写入当前文件夹的文件中：流程相同，但不会归档至节点、待办事项或解析器，后续也无法通过会话扫描找回。在AI First OS中，上述目标路径为真实路径，本部分内容不适用。

本套件的其余技能需逐个安装。先查看

.claude/skills/

目录，仅提供未安装的技能——在AI First OS中所有技能已预装，因此无需提供：

grill

—

npx skills add pedroromeroluna/ai-first-product-skills --skill grill

market-research

—

npx skills add pedroromeroluna/ai-first-product-skills --skill market-research

prd

—

npx skills add pedroromeroluna/ai-first-product-skills --skill prd

product-metrics

—

npx skills add pedroromeroluna/ai-first-product-skills --skill product-metrics

一键安装整个套件：

npx skills add pedroromeroluna/ai-first-product-skills

。

这些技能源自AI First OS系统——

github.com/pedroromeroluna/ai-first-os

——在该系统中，它们基于核心大脑运行，而非当前文件夹。