synthetic-users

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

synthetic-users — the Diagnosis + Script v2

合成用户 — 《诊断报告+脚本v2》

Fourth station of the pipeline. It pilots the guide that

ux-research

built against synthetic personas —simulated profiles with explicit traits— before spending the first minute of real fieldwork. Generic domain example: a B2B appointment-management app could simulate an administrator of a small clinic and a skeptical one who already tried and abandoned a similar tool.

这是流程的第四个环节。在投入第一分钟真实实地调研前，它会用合成角色——带有明确特征的模拟用户档案——来测试

ux-research

构建的研究指南。通用领域示例：一款B2B预约管理应用可以模拟小型诊所的管理员，以及一位曾试用过类似工具后放弃的持怀疑态度的管理员。

When it is invoked

触发时机

When	From / to
The Research Plan from `ux-research` already has a v1 guide	Entry from `ux-research` ( `.claude/skills/ux-research/SKILL.md` )
The Diagnosis + Script v2 is written	Exit: real fieldwork — interviews with real people, the work the operator picks up; it is not a skill of this pack
After real fieldwork	The raw answers are converged by `insight-engine` ( `.claude/skills/insight-engine/SKILL.md` ), and from there the pipeline reaches the strategic layer that `prd` writes ( `.claude/skills/prd/SKILL.md` )

时机	来源/去向
`ux-research` 产出的研究计划已有v1指南	从 `ux-research` 输入（ `.claude/skills/ux-research/SKILL.md` ）
《诊断报告+脚本v2》撰写完成	输出：真实实地调研——与真实用户的访谈，由操作人员接手；这不属于本技能包的技能范畴
真实实地调研完成后	原始回答由 `insight-engine` 汇总（ `.claude/skills/insight-engine/SKILL.md` ），之后流程进入 `prd` 负责的战略层（ `.claude/skills/prd/SKILL.md` ）

Rule number one

核心规则

This validates NOTHING. It opens the session with this sentence and repeats it on closing: no answer from a synthetic persona is evidence that something works with real users. It serves one purpose —finding defects in the guide before spending fieldwork time— and no other. A Diagnosis that reads as if it validated the hypothesis is badly written, no matter how many times the rule was repeated in the text.

本环节不做任何验证。 会话开始时会说明这句话，结束时再次重申：合成角色的任何回答都不能作为产品对真实用户有效的证据。它只有一个目的——在投入实地调研前发现指南中的缺陷——别无其他。如果诊断报告看起来像是在验证假设，那么这份报告撰写得不合格，无论文本中重复多少次这条规则。

The synthetic personas

合成角色

It is run with the pressure method of

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

— cited by path, never copied — while building each profile: every trait proposed is pressured for its origin before entering the profile.

Every simulated persona carries its traits with an explicit origin, marked one by one: (evidence) if it comes from real research already done —an interview, a usage figure, something the Discovery Brief or the Market Brief brings— or (assumption) if it is a construction with no research behind it. A trait with no mark does not enter the profile.

At least one skeptical persona, with a reason: someone who already tried something similar and abandoned it, someone with a business objection (the cost, the process change), or someone who simply does not have the problem the hypothesis assumes. A set of personas that only confirm the hypothesis is no use for finding defects: it is useful for confirming them.

No "I love it!" without a cost next to it. Every enthusiastic answer from a synthetic persona is accompanied by its cost or its friction: what it costs them, what worries them, what they would have to stop doing. An answer made only of enthusiasm is the signal that the guide is built to confirm, not to learn.

构建每个用户档案时，会采用

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

中的施压法——仅通过路径引用，绝不复制——对每个提出的特征，都会先确认其来源，再纳入档案。

每个模拟角色的所有特征都带有明确的来源标记，逐一标注： (evidence) 表示该特征来自已完成的真实研究——如访谈、使用数据，或发现简报、市场简报中的内容；(assumption) 表示该特征是无研究依据的假设性设定。未标记来源的特征不得纳入档案。

至少包含一个持怀疑态度的角色，且需说明原因：比如曾试用过类似工具后放弃的用户、对成本或流程变更有异议的用户，或根本不存在假设中所述问题的用户。仅能验证假设的角色组对发现缺陷毫无用处：它们仅适用于确认假设。

没有无代价的“我喜欢它！”。 合成角色的每一个积极回应都必须伴随对应的成本或摩擦：比如他们需要付出什么、担心什么、需要停止做什么。如果只有积极回应，说明研究指南是为了验证假设而设计的，而非为了获取新知。

The taxonomy of question defects

问题缺陷分类

Every question of the v1 script is reviewed against this list; the defect found is recorded with its rewrite next to it, never merely pointed at:

Defect	Example	Rewrite
Leading question (suggests the answer)	"Don't you think an automatic reminder would be useful?"	"How do you keep from missing an appointment today?"
Hypothetical question ("would you use...?")	"Would you use a feature that rescheduled appointments on its own?"	"Tell me about the last time you had to reschedule an appointment"
Double question	"Is the dashboard clear and fast to use?"	Split into two questions, one per attribute
Question with no behavior behind it	"What do you think about appointment management in general?"	"When was the last time you managed appointments for your team?"
Jargon the segment does not use	An internal technical term of the product team	The word the segment uses, taken from prior research

v1脚本中的每个问题都会对照以下列表进行审查；发现的缺陷需记录下来，并附上改写后的问题，不能仅指出问题：

缺陷类型	示例	改写
诱导性问题（暗示答案）	“你不觉得自动提醒很有用吗？”	“你现在是如何避免错过预约的？”
假设性问题（“你会使用...吗？”）	“你会使用能自动重新安排预约的功能吗？”	“告诉我你上次不得不重新安排预约的经历”
双重问题	“仪表盘是否清晰且使用快捷？”	拆分为两个问题，每个问题对应一个属性
无行为支撑的问题	“你对预约管理总体有什么看法？”	“你上次为团队管理预约是什么时候？”
目标用户群体不使用的行话	产品团队的内部技术术语	使用目标用户群体的常用词汇，取自先前的研究

The Diagnosis + Script v2

《诊断报告+脚本v2》

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

context/<YYYY-MM-DD>-diagnostico-guion.md

Dated, never overwritten. The path falls inside

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

tree.md

: no new glob and no resolver row are needed.

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

undefined

最终产出物会作为加载产品节点的时效性研究文档，写入以下路径：

context/<YYYY-MM-DD>-diagnostico-guion.md

文档带有日期，永不覆盖。该路径位于

tree.md

中的

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

下：无需新增glob规则或解析器行。

诊断报告包含以下四个部分，按顺序排列，每个部分使用指定标题：

undefined

Synthetic personas

合成角色

Simulation

模拟过程

Defects found and rewrites

发现的缺陷及改写方案

Script v2

脚本v2


- **Synthetic personas**: each profile, with its traits marked `(evidence)` or `(assumption)`, and
  the skeptical persona identified as such.
- **Simulation**: the simulated answers against the v1 script, every enthusiasm with its cost next
  to it.
- **Defects found and rewrites**: every defect from the taxonomy that showed up, with its rewrite.
- **Script v2**: the corrected guide, ready for real fieldwork.

The **Script v2** section opens and closes with rule number one written out: "this validates
NOTHING" — before the first question and after the last one.


- **合成角色**：每个用户档案，其特征标记为`(evidence)`或`(assumption)`，并明确指出持怀疑态度的角色。
- **模拟过程**：针对v1脚本的模拟回答，每个积极回应都附带对应的成本。
- **发现的缺陷及改写方案**：所有出现的符合上述分类的缺陷，及其改写后的内容。
- **脚本v2**：修正后的研究指南，可直接用于真实实地调研。

**脚本v2**部分的开头和结尾都需明确写出核心规则：“本环节不做任何验证”——在第一个问题之前和最后一个问题之后。

What this deliverable does not claim

产出物的局限性

The Diagnosis + Script v2 does not replace real fieldwork: it is the step that reduces how much broken script reaches the first interview with a real person. Synthesizing what comes out of real fieldwork —transcripts into findings— is not the job of this skill: that is

insight-engine

《诊断报告+脚本v2》不能替代真实实地调研：它只是减少了有缺陷的脚本进入首次真实用户访谈的概率。将真实实地调研的结果（如访谈记录）转化为研究结论，不属于本技能的职责范畴：这是

insight-engine

的工作。

Standalone use

独立使用

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

insight-engine

—

npx skills add pedroromeroluna/ai-first-product-skills --skill insight-engine

prd

—

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

ux-research

—

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

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.

若未接入AI First OS的核心系统，产出物会写入当前文件夹的文件中：流程与之前一致，但不会归档到节点、待办事项或解析器中，后续也不会被会话扫描检索到。在AI First OS中，上述目标路径才是正式存储位置，本部分内容不适用。

技能包中的其余技能需逐个安装。请先查看

.claude/skills/

目录，仅提供尚未安装的技能——在AI First OS中，所有技能已预先安装，因此无需提供以下安装选项：

grill

—

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

insight-engine

—

npx skills add pedroromeroluna/ai-first-product-skills --skill insight-engine

prd

—

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

ux-research

—

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

一键安装整个技能包：

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，它们运行于核心系统之上，而非当前文件夹。