ux-research
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chineseux-research — the Research Plan
ux-research — 研究计划
Third station of the pipeline. It designs the research round that attacks the riskiest hypothesis of
the Discovery Brief — never all of them at once — and closes with a Research Plan ready to pilot.
作为流程的第三站，它设计针对《Discovery Brief》中最高风险假设的研究轮次——绝不一次性覆盖所有假设——最终产出可试点的研究计划。
When it is invoked
调用时机
| When | From / to |
|---|---|
The Market Brief from | Entry from |
| The Research Plan is written | Exit toward |
| With no prior Market Brief | Invocable on its own, over the loaded product node, with the Discovery Brief as the minimum input |
| 时机 | 来源/去向 |
|---|---|
来自 | 从 |
| 研究计划撰写完成 | 输出至 |
| 无前置《Market Brief》 | 可独立调用，基于已加载的产品节点，以《Discovery Brief》为最低输入 |
The interview
访谈环节
It is run with the pressure method of — cited by path, never copied —
over the choice of hypothesis, the screening criterion and every question in the guide.
.claude/skills/grill/SKILL.md#method访谈采用中的施压法——通过路径引用，绝不复制——针对假设选择、筛选标准及指南中的每个问题进行。
.claude/skills/grill/SKILL.md#methodOne objective per round
每轮一个目标
Each round attacks a single hypothesis: the riskiest one in the Discovery Brief, the same risk ×
impact prioritization already did. Faced with a request to "research everything
together", pressure is applied: which is the one that costs the most if it turns out wrong? That one
belongs to this round; the others wait for the next.
product-strategy每轮研究仅针对一个假设：即《Discovery Brief》中经已完成风险×影响优先级排序后的最高风险假设。若收到“一起研究所有内容”的请求，需施压确认：哪一个假设若被证伪，代价最高？该假设即为本轮研究对象，其余假设留待下一轮。
product-strategyScreening that avoids "users in general"
避免“泛用户”的筛选标准
The criterion for who gets interviewed is written in verifiable behavior, never in demographics
alone. "Active users" is not screening; "people who bought in the last two weeks and abandoned
checkout at least once" is. Faced with a criterion that is too broad ("any user of the app"), it is
returned with a counter-question: what behavior must this person have done or not done for their
answer to be useful?
访谈对象的筛选标准需基于可验证的行为，而非仅依赖人口统计数据。“活跃用户”不属于有效筛选标准；“过去两周内购买过且至少放弃过一次结账流程的用户”才是。若收到过于宽泛的筛选标准（如“应用的任意用户”），需退回并反问：为使受访者的回答具备价值，该用户必须做过或未做过哪些行为？
Exploratory → qualitative; sizing → quantitative
探索性研究→定性；规模评估→定量
The modality is decided by what question the round asks. If the question is "why does this happen?"
or "what do people do today?", qualitative — interviews, few people, depth. If the question is "how
many people does this happen to?" or "how often?", quantitative — survey, representative sample.
Mixing the two without deciding which one leads produces a plan without focus; one is chosen and the
reason is stated.
研究模式由本轮要解答的问题决定。若问题是“为什么会发生这种情况？”或“人们当前的做法是什么？”，则采用定性研究——访谈、少量样本、深度挖掘。若问题是“这种情况发生在多少人身上？”或“发生频率如何？”，则采用定量研究——调研、代表性样本。若未明确方向就混合两种模式，会导致研究计划缺乏焦点；需选择其中一种并说明理由。
JTBD in four dimensions
JTBD的四个维度
When the round explores a job-to-be-done, the guide covers the four forces of change, not just the
functional one:
| Dimension | What it looks for |
|---|---|
| Push | What about the current situation pushes toward looking for something different |
| Pull | What about the new solution attracts |
| Anxiety | What doubt or fear holds the change back |
| Habit | What about the current solution weighs by habit, even when it does not work well |
A guide that only asks about the desired feature covers one of the four and is returned incomplete.
当研究轮次探索“待完成工作（JTBD）”时，研究指南需涵盖四大变革驱动力，而非仅关注功能层面：
| 维度 | 关注内容 |
|---|---|
| 推力（Push） | 当前情境中促使人们寻求替代方案的因素 |
| 拉力（Pull） | 新解决方案具备的吸引力 |
| 焦虑（Anxiety） | 阻碍变革的疑虑或恐惧 |
| 习惯（Habit） | 当前方案因习惯产生的惯性，即便其效果不佳 |
若指南仅询问期望功能，仅覆盖了四个维度之一，需退回补充完整。
Master technique: reconstruct the last real time
核心技巧：还原最近一次真实场景
The master question of any guide is not "what do you think of X?": it is "tell me about the last time
[situation]" — reconstructing step by step what happened, at what moment, with whom, what they did
right before and right after. Opinion questions ("would you like it if...?") are taken out of the
guide unless they serve to close the session, never to explore.
任何研究指南的核心问题都不是“你对X有什么看法？”，而是“告诉我最近一次[场景]发生时的情况”——逐步还原事件发生的过程、时间点、涉及人员，以及事件前后的行为。除非用于结束访谈，否则需删除意见类问题（如“你希望有……功能吗？”），绝不用于探索环节。
Every question tied, or it comes out
每个问题都需关联，否则移除
Every question in the guide is tied explicitly to a hypothesis from the Discovery Brief or to one of
the four job dimensions. A question that cannot be tied to either is taken out of the guide — "just
in case" is not an inclusion criterion.
指南中的每个问题都需明确关联《Discovery Brief》中的某个假设或JTBD的四个维度之一。若某问题无法关联两者之一，则需从指南中移除——“以防万一”不能成为保留问题的理由。
The Research Plan
研究计划
It closes by writing the deliverable as dated research of the loaded product node, in:
context/<YYYY-MM-DD>-research-plan.mdDated, never overwritten. The path falls inside of
: no new glob and no resolver row are needed.
content: orgs/*/products/*/context/*.mdtree.mdThe Plan carries these four sections, in this order, each with its literal heading:
undefined最终产出的研究计划需作为已加载产品节点的带日期研究文档，保存至：
context/<YYYY-MM-DD>-research-plan.md带日期命名，绝不覆盖。路径需位于中的范围内：无需新增通配符或解析器行。
tree.mdcontent: orgs/*/products/*/context/*.md研究计划需包含以下四个部分，按顺序排列，每个部分使用指定标题：
undefinedObjective of the round
本轮研究目标
Screening criterion
筛选标准
Modality
研究模式
Question guide
问题指南
- **Objective of the round**: the chosen hypothesis and why it is the riskiest.
- **Screening criterion**: in verifiable behavior, never demographics alone.
- **Modality**: qualitative or quantitative, with the question that decides it.
- **Question guide**: every question with the hypothesis or job dimension it is tied to.
- **本轮研究目标**：选定的假设及其成为最高风险假设的原因。
- **筛选标准**：基于可验证行为，而非仅依赖人口统计数据。
- **研究模式**：定性或定量，说明决定该模式的核心问题。
- **问题指南**：每个问题需标注其关联的假设或JTBD维度。What this deliverable does not claim
本交付物的局限性
The Research Plan is the v1 guide: it has not been piloted yet. Piloting it against synthetic
personas —before spending the first minute of real fieldwork— is the job of ,
the next station.
synthetic-users研究计划为v1版本指南：尚未经过试点。在开展首次实际实地调研前，针对虚拟用户进行试点是下一站的工作。
synthetic-usersStandalone 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 first and offer only
the ones that are not there — inside AI First OS they are all installed already, so nothing here
gets offered:
.claude/skills/- —
grillnpx skills add pedroromeroluna/ai-first-product-skills --skill grill - —
market-researchnpx skills add pedroromeroluna/ai-first-product-skills --skill market-research - —
product-strategynpx skills add pedroromeroluna/ai-first-product-skills --skill product-strategy - —
synthetic-usersnpx skills add pedroromeroluna/ai-first-product-skills --skill synthetic-users
The whole pack at once: .
npx skills add pedroromeroluna/ai-first-product-skillsThe system these skills come from is AI First OS —
— where they run over a brain instead of over the current
folder.
github.com/pedroromeroluna/ai-first-os若未接入系统核心，交付物将保存至当前文件夹：流程不变，但不会归档至节点、待办清单或解析器，后续也不会被会话扫描找回。在AI First OS中，上述目标路径为实际存储位置，本部分内容不适用。
其余技能需逐个安装。请先查看目录，仅提供尚未安装的技能——在AI First OS中所有技能已预先安装，因此无需提供以下内容：
.claude/skills/- —
grillnpx skills add pedroromeroluna/ai-first-product-skills --skill grill - —
market-researchnpx skills add pedroromeroluna/ai-first-product-skills --skill market-research - —
product-strategynpx skills add pedroromeroluna/ai-first-product-skills --skill product-strategy - —
synthetic-usersnpx skills add pedroromeroluna/ai-first-product-skills --skill synthetic-users
一键安装全部技能：。
npx skills add pedroromeroluna/ai-first-product-skills这些技能源自AI First OS系统————在该系统中，技能基于系统核心运行，而非当前文件夹。
github.com/pedroromeroluna/ai-first-os