Back to Details

prd

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

prd — the strategic layer of a product

PRD — 产品战略层

It interviews the operator and produces the strategic definition of a product: vision, problem, users, scope, competitors, opportunities, open questions and glossary. It is the entry door to the method — out of this layer come the specs.
It always writes into the 
context/
of the loaded product node of the brain, never into the body repo. The repo declared in 
repo:
of the node's head is the body: specs, technical decisions, as-built. The strategic layer lives in the head, not in the body.
The interview applies pressure with the method of 
.claude/skills/grill/SKILL.md#method
: it is cited by that heading, never copied. Any change to the method happens there, once.
它通过与运营人员访谈，生成产品的战略定义：包含愿景、问题、用户、范围、竞品、机会、待解决问题和术语表。这是该方法的入口——后续的规格文档将基于此层内容生成。
它始终写入已加载产品节点在brain中的
context/
目录，绝对不会写入body repo。 节点头部
repo:
字段声明的仓库即为body，包含规格文档、技术决策、已实现内容。战略层属于head，而非body。
访谈采用
.claude/skills/grill/SKILL.md#method
中的施压方法：仅通过该标题引用，绝不复制。对该方法的任何修改都仅在原文件中进行一次。

The files it produces

生成的文件

They go into 
context/
of the loaded product node. If the node has no 
context/
yet, it is born with 
README.md
first and the rest as the interview gets completed.
FileWhat it answers
README.md
Index: what the product is, in what order each file was filled, its state
vision.md
The finished system, where it gets to
problem.md
What problem it solves, for whom, why now, how you know whether it worked
users.md
Who it sells to, what they use instead today
scope.md
What it does NOT do, who it does NOT sell to, hard constraints, what goes into the first version
competitors.md
What it competes against and how it differs
opportunities.md
What might be worth it and has not been decided
open-questions.md
What is left to decide — live, it empties out as things close
glossary.md
The terms of the domain
No file in this list is written into the body repo. If completing a section forced touching the body repo or a resolver, the tool does not do it: it says so and stops — that is a stopping condition of the spec that brought it, not a decision of this session.
The KPI tree does not go here: it belongs to another tool's metric brief; this skill references it if it already exists, it does not produce it.
这些文件将存入已加载产品节点的
context/
目录。如果该节点尚未创建
context/
目录，则先创建
README.md
，其余文件将随着访谈的推进逐步生成。
文件核心内容
README.md
索引：产品定位、各文件填写顺序、当前状态
vision.md
最终系统形态及发展目标
problem.md
解决的问题、目标用户、为何此时推出、验证效果的方式
users.md
目标客户群体、当前替代方案
scope.md
产品不包含的功能、非目标用户、硬性约束、首个版本的内容范围
competitors.md
竞品分析及差异化优势
opportunities.md
潜在价值但尚未确定的方向
open-questions.md
待决策事项——随着问题解决，该文件内容将逐步清空
glossary.md
领域术语定义
上述所有文件均不会写入body repo。若完成某部分内容需要修改body repo或resolver，工具不会执行此操作：它会告知情况并停止——这是触发该工具的规格文档的终止条件，而非本次会话的决策。
KPI树不属于此范畴：它归属于另一工具的指标简报；若KPI树已存在，该技能会引用它，但不会生成它。

Phase 1 — Read what the brain already knows before asking

阶段1：提问前读取brain已有的信息

Before the first question:
  1. Identify the loaded product node and its 
    context/
    — if it does not exist, it is created with this interview.
  2. Read in full the files that 
    context/
    already has. This is incremental: it is completed in stages and a filled section is never overwritten without saying so first.
  3. Read the context of the owning organization and, if it exists, dated research that applies.
  4. Tell the operator what you read and which sections you can already fill on your own with that. Only then does the interview start, and only over what is missing — you do not ask them what the system already has written.
在提出第一个问题前：
  1. 确定已加载的产品节点及其
    context/
    目录——若该目录不存在，则在本次访谈中创建。
  2. 完整读取
    context/
    目录中已有的文件。此过程为增量式：分阶段完成，已填写的内容不会被随意覆盖，如需覆盖会提前告知。
  3. 读取所属组织的上下文信息，以及（若存在）相关的时效性研究资料。
  4. 告知运营人员已读取的内容，以及无需提问即可自行填充的部分。之后才开始访谈，且仅针对缺失的内容提问——不会询问系统已记录的信息。

Phase 2 — The interview

阶段2：访谈

One question at a time, with a line about why that section changes a decision before each one. Without that line the question sounds like bureaucracy.
每次提出一个问题，且每个问题前需说明该部分内容如何影响决策。若缺少此说明，问题会显得流于形式。

The six questions that force the truth

直击本质的六个问题

Opportunity and business stage, before touching the solution:
  1. What is the strongest evidence that someone wants this? Not interest: behavior.
  2. What do they solve it with today? If the answer is "with nothing", why do they live fine without this?
  3. Name me a concrete person. Their job title, and what happens to them if they do not solve it.
  4. What is the smallest version someone would pay for this week?
  5. What surprised you watching someone use it or try to solve it?
  6. In three years, does this become more necessary or less?
在讨论解决方案前，先聚焦机会与业务阶段：
  1. 有哪些最有力的证据表明用户需要这个产品？不是兴趣，而是实际行为。
  2. 用户当前用什么解决该问题？如果答案是‘没有解决方案’，那他们为何能正常运转？
  3. 请举例一个具体的用户。说明其职位，以及若未解决该问题会面临什么后果。
  4. 本周内用户愿意付费的最小版本是什么样的？
  5. 在观察用户使用现有方案或尝试解决问题时，你有哪些意外发现？
  6. 三年后，这个产品的必要性会增强还是减弱？

Research stage

研究阶段

Conclusions are not invented: if no research has been done, that is said and the matching discovery tool is offered. Questions cover the segment, the explicit non-target, and the alternatives the operator already uses today.
结论不能凭空捏造：若未开展相关研究，需告知情况并提供对应的发现工具。问题需覆盖用户细分、明确的非目标群体，以及运营人员当前使用的替代方案。

Solution stage

解决方案阶段

Before talking about what to build, the premise is challenged: is this the right problem? what happens if nothing is done? is there something already built that would do? Only then: vision, slicing, what it does NOT do with its reactivation condition, hard constraints, assumptions with their invalidation condition.
在讨论具体要构建的内容前，需先质疑前提：这是正确的问题吗？如果不解决会怎样？是否已有现成的解决方案？之后再讨论：愿景、版本拆分、产品不涉及的功能及重新激活条件、硬性约束、假设条件及其失效判定标准。

How to apply pressure

施压方法

The method of 
.claude/skills/grill/SKILL.md#method
decides when to counter-question, how many rounds, and what to do with the second resistance. It is not repeated here: it is applied.
.claude/skills/grill/SKILL.md#method
中的方法决定了何时反问、反问轮次，以及如何应对第二次抵触。此处不再重复该方法，直接应用即可。

Alternatives phase, mandatory

可选方案阶段（必填）

Before fixing the solution, 2 or 3 paths are presented, each with its effort, risk and what it reuses of what already exists:
  • the smallest shippable one — the smallest version that can be launched this week,
  • the one that ages best — the one that demands the least rework if the product grows,
  • a lateral one that reframes the problem — a way out that is not "more of the same, smaller".
The operator picks one. Without this phase the document records the first idea, not the best one.
在确定最终方案前，需提供2-3种可选路径，并说明每种路径的投入、风险以及可复用现有资源的情况：
  • 最小可交付版本：本周内可发布的最小版本，
  • 长期最优版本：产品扩展时所需返工最少的版本，
  • 重构问题的横向方案：跳出‘同类缩小版’思维的创新路径。
由运营人员选择其一。若跳过此阶段，文档记录的将是首个想法而非最优方案。

The explicit-gap rule

明确缺口规则

A gap is written only when the operator explicitly decides not to answer, and always with who closes it. A file full of gaps is not a deliverable: it is a failure dressed up as completeness. If a gap appears because the section was never asked about, it is not a gap: it is work not done, and the interview resumes.
缺口仅在运营人员明确决定不回答时才会记录，且需注明负责填补缺口的人员。充满缺口的文件不能作为交付物：这是伪装成完整性的失败。若缺口是因未询问该部分内容导致，则不属于缺口范畴，需继续访谈完成该部分内容。

Show before writing

先展示再写入

Before touching any file, the operator is shown exactly what is going to be written —the content, not a summary— and their go-ahead is awaited. Only the files the interview touched get written; the ones that were already complete are not overwritten.
在写入任何文件前，需向运营人员展示即将写入的具体内容——而非摘要——并等待其确认。仅写入访谈涉及的文件；已完整的文件不会被覆盖。

The closing verdict

最终结论

At the end, one of three, always explicit:
  • Complete — enough to write specs.
  • Complete with reservations — it is possible to move forward, and these are the open questions that remain.
  • Missing context — which file was left unclosed and what it takes to close it.
The minimums gate: if 
glossary.md
, 
scope.md
or the architecture of the body are left empty, no specs come out of there yet. It is said explicitly, never left to be discovered later.
最终需明确给出以下三种结论之一：
  • 完整：内容足够支撑规格文档的编写。
  • 有保留的完整：可推进后续工作，但仍存在以下待解决问题。
  • 上下文缺失：说明未完成的文件以及完成所需的条件。
最低要求关卡：若
glossary.md
、
scope.md
或body的架构为空，则无法生成规格文档。需明确告知此情况，绝不能留待后续发现。

Standalone use

独立使用场景

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
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.
若没有brain，交付物将写入当前目录的文件中：流程保持不变，但不会存入节点、待办事项或resolver，后续会话扫描也无法找回该内容。在AI First OS中，交付物将存入上述指定位置，本部分内容不适用。
技能包中的其他技能需逐个安装。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，因此无需提供以下安装选项：
  • grill
    — 
    npx skills add pedroromeroluna/ai-first-product-skills --skill grill
一次性安装整个技能包：
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，技能基于brain运行，而非当前目录。