Back to Details

decide

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

/decide — Structured decision workflow + archive

/decide — 结构化决策工作流 + 归档

Picks load-bearing questions from the 37signals guide, walks through them, reaches a call, archives the rationale with a revisit date.
从37signals指南中挑选核心关键问题，引导你梳理决策过程、得出结论，并将决策理由与复查日期一起归档。

Step 1 — Capture the decision

步骤1 — 记录决策信息

Get from the user:
  • The decision in one sentence (what are we deciding between?)
  • Stakes: low / medium / high (how much does this matter?)
  • Reversibility: easy / hard / one-way door
  • Deadline: when does this need to be decided? Or "open"?
  • Context (optional, 1–3 sentences)
If any are missing, ask. Don't proceed with vague framing.
向用户收集以下信息：
  • 决策内容：用一句话描述（我们要在哪些选项间做决策？）
  • 重要程度：低/中/高（这个决策的影响有多大？）
  • 可逆性：易/难/单向不可逆
  • 截止日期：决策需要在何时完成？或标记为“无截止”？
  • 背景信息（可选，1-3句话）
若有信息缺失，需向用户询问。不要在框架模糊的情况下继续推进。

Step 2 — Triage the question set

步骤2 — 筛选问题集

Read 
references/questions.md
for the full 38 and category mapping. Pick 6–8 based on the decision's characteristics:
Default 5 (always ask):
  • Q1 — Does this decision actually need to be made?
  • Q2 — Is the right person making this decision?
  • Q8 — How easily can we reverse it?
  • Q9 — First instinct? (capture before "thinking" muddies it)
  • Q3 — A year from now, how will we feel about this?
Add based on type:
If…Add
Reversibility = hard / one-way doorQ14 (is there a wrong decision?), Q17 (knock-on effects), Q34 (principles bent)
Time pressureQ5 (why hesitating?), Q15 (different tomorrow?), Q22 (when do we have to decide?)
Multiple people involvedQ21 (someone else's practice rep?), Q27 (would another opinion help?), Q35 (multiple people deciding what one should?)
Lots of data / analysisQ19 (what missing info would change it?), Q26 (data vs gut?), Q9 deepened
Recurring decisionQ11 (last time?), Q23 (one-and-done or repeating?)
Customer-facingQ24 (anyone outside depending?), Q25 (customer vs us impact?)
Money decisionQ38 (in the end, is this about money?), Q36 (return on effort?)
Stuck / not decidingQ4 (why hasn't it been made already?), Q10 (what if we don't decide?), Q31 (do you even care?)
Cap at ~8 questions. More than that turns into analysis paralysis (which is itself one of the things this skill exists to prevent).
Tell the user which questions you picked and why, then proceed.
查看
references/questions.md
获取完整的38个问题及分类映射。根据决策的特征挑选6-8个问题：
默认必问的5个问题：
  • Q1 — 这个决策真的有必要做吗？
  • Q2 — 做出这个决策的是合适的人选吗？
  • Q8 — 我们能轻易推翻这个决策吗？
  • Q9 — 第一直觉是什么？（在“理性思考”干扰前记录下来）
  • Q3 — 一年后，我们会如何看待这个决策？
根据决策类型补充问题：
如果…补充问题
可逆性 = 难 / 单向不可逆Q14（是否存在错误决策的可能？）、Q17（连锁影响是什么？）、Q34（是否违背了原则？）
时间紧迫Q5（为什么犹豫不决？）、Q15（明天的情况会不同吗？）、Q22（我们必须在何时做出决策？）
涉及多人Q21（是否关乎他人的职业声誉？）、Q27（是否需要其他意见？）、Q35（是否本该由一人决策却由多人参与？）
涉及大量数据/分析Q19（哪些缺失信息会改变决策？）、Q26（数据 vs 直觉？）、深入询问Q9
重复性决策Q11（上次的决策是什么？）、Q23（是一次性决策还是重复性决策？）
面向客户Q24（是否有外部人员依赖这个决策？）、Q25（对客户和我们的影响分别是什么？）
涉及资金Q38（最终是否是关于资金的决策？）、Q36（投入产出比如何？）
陷入决策僵局Q4（为什么至今尚未做出决策？）、Q10（如果不做决策会怎样？）、Q31（你真的在意这个决策吗？）
问题数量上限约为8个。超过这个数量会导致分析瘫痪，而这正是本工具要避免的问题之一。
告知用户你挑选的问题及原因，然后继续推进。

Step 3 — Walk through

步骤3 — 逐一梳理

Ask the questions one at a time, or in a tight cluster if the user wants to write fast. Capture his answers verbatim — don't paraphrase into corporate-speak.
For Q9 (first instinct), get the answer BEFORE diving into analysis. The point is to surface the gut call so we can later check if "analysis" was just rationalization.
逐个提问，或如果用户希望快速作答，可以集中提问。如实记录用户的回答——不要转述为官方话术。
对于Q9（第一直觉），要在深入分析前获取答案。目的是捕捉直觉判断，以便后续检查“理性分析”是否只是合理化借口。

Step 4 — Reach a call

步骤4 — 得出结论

Synthesize the answers into a decision. Options:
  • Decide now — answers point to a clear call
  • Decide smaller — break into 2–3 smaller decisions (Q7)
  • Wait — flag what info / time would change the answer (Q19, Q15)
  • Don't decide — the decision doesn't need to be made (Q1, Q10)
  • Wrong person — kick to the right decider (Q2, Q35)
State the call clearly. No hedging.
综合回答得出决策结论。可选结论类型：
  • 立即决策 — 回答指向明确结论
  • 拆分决策 — 将决策拆分为2-3个更小的决策（对应Q7）
  • 暂缓决策 — 指出哪些信息/时间会改变答案（对应Q19、Q15）
  • 无需决策 — 这个决策没有必要做（对应Q1、Q10）
  • 转交决策 — 将决策交给合适的人选（对应Q2、Q35）
清晰陈述结论，不要含糊其辞。

Step 5 — Set the revisit

步骤5 — 设置复查日期

Pick a revisit date based on when consequences would show up:
  • Decisions about tools/processes: 30 days
  • Decisions about strategy/positioning: 90 days
  • Decisions about hires/partnerships: 90–180 days
  • Decisions about products/launches: 30–60 days post-launch
Write what to look for on the revisit ("did MRR move? did the partner ship? do clients still ask for X?").
根据决策后果显现的时间选择复查日期：
  • 工具/流程相关决策：30天
  • 战略/定位相关决策：90天
  • 招聘/合作相关决策：90-180天
  • 产品/发布相关决策：发布后30-60天
写下复查时需要关注的内容（“MRR是否变化？合作伙伴是否履约？客户是否仍在需求X？”）。

Step 6 — Archive

步骤6 — 归档

Write to 
references/decisions-archive/<YYYY-MM-DD>-<slug>.md
:
markdown
undefined
将内容写入
references/decisions-archive/<YYYY-MM-DD>-<slug>.md
：
markdown
undefined

Decision: <one-line>

决策：<一句话描述>

Date: YYYY-MM-DD Decide by: <date or "open"> Reversibility: easy / hard / one-way door Stakes: low / medium / high
日期： YYYY-MM-DD 决策截止日期： <日期或“无截止”> 可逆性： 易 / 难 / 单向不可逆 重要程度： 低 / 中 / 高

Context

背景信息

<1–3 sentences>
<1-3句话>

Questions

问题与回答

<Q3 phrasing>

<Q3的问题表述>

<answer>
<回答内容>

<Q8 phrasing>

<Q8的问题表述>

<answer>
(only questions actually applied — heading is the question text, not "Q3")
<回答内容>
（仅包含实际使用的问题——标题为问题文本，而非“Q3”）

Decision

决策结论

<the call, stated clearly>
<清晰陈述的结论>

Rationale

决策理由

<2–3 sentences synthesizing the answers>
<2-3句话综合回答内容>

Expected outcome

预期结果

<what should be true if this was right, by <date>>
<若决策正确，到<日期>时应达成的结果>

Revisit

复查安排

<YYYY-MM-DD> — <what to look for>
<YYYY-MM-DD> — <需要关注的内容>

Source

来源

Questions adapted from The 37signals Guide to Making Decisions

Append to `references/decisions-archive/INDEX.md`:

```markdown
- 2026-06-16 — [<decision>](./<filename>.md) — **<call>** — <one-line rationale> — revisit 2026-09-16
问题改编自The 37signals Guide to Making Decisions

将内容追加到`references/decisions-archive/INDEX.md`：

```markdown
- 2026-06-16 — [<决策内容>](./<文件名>.md) — **<结论>** — <一句话理由> — 复查日期2026-09-16

Step 7 — Surface

步骤7 — 展示结果

Show the archive entry in chat. Tell the user the archive path. Offer:
  • "Want me to schedule a /loop reminder for the revisit date?" (would use the 
    loop
    skill to fire at the right time)
  • "Push to Notion as a decision card?"
  • "Need a follow-up decision after this one?"
在聊天中展示归档条目，告知用户归档路径。提供以下选项：
  • “需要我为复查日期安排/loop提醒吗？”（将使用
    loop
    工具在指定时间触发提醒）
  • “是否要推送至Notion作为决策卡片？”
  • “需要在此决策后进行后续决策吗？”

Future enhancements

未来优化方向

  • Auto-create a calendar event or cron reminder for the revisit (via 
    compound-engineering:schedule
    )
  • Composable with 
    business-brainstorm
    — brainstorm scores the idea on 9 dimensions; 
    decide
    formalizes the go/no-go after
  • Grep past decisions for patterns ("show me decisions I made that were marked 'easy reverse' but didn't reverse")
  • 通过
    compound-engineering:schedule
    自动创建日历事件或定时任务提醒复查
  • 与
    business-brainstorm
    集成——brainstorm从9个维度为创意打分；
    decide
    在之后正式确定是否推进
  • 检索过往决策以寻找规律（“显示我标记为‘易可逆’但未实际推翻的决策”）

Composes with

可集成工具

  • business-brainstorm
    — brainstorm → decide is a natural pipeline for "should I build X"
  • deep-research
    — when a decision is waiting on info (Q19), trigger research first
  • Memory — load 
    feedback_*.md
    for principles that might be at play (Q34)
  • loop
    / 
    compound-engineering:schedule
    — for revisit reminders
  • business-brainstorm
    — brainstorm → decide是“是否开发X”这类需求的自然流程
  • deep-research
    — 当决策等待信息时（对应Q19），先触发研究
  • Memory — 加载
    feedback_*.md
    以查看可能涉及的原则（对应Q34）
  • loop
    / 
    compound-engineering:schedule
    — 用于复查提醒

Notes on quality

质量注意事项

  • Don't ask all 38. The point of triage is to skip questions that don't apply. Eight relevant questions > thirty-eight padded ones.
  • Don't soften the call. "Probably yes, lean toward, maybe should" wastes the skill. Pick.
  • The first instinct (Q9) is sacred. Always capture it before analysis. If the final call differs from the first instinct, the rationale needs to explain why — that's the whole point of the question.
  • Archive every decision, even small ones. The compounding value comes from being able to grep "what did I decide about pricing last year" — and that requires writing them down even when they feel obvious in the moment.
  • 不要问全部38个问题。筛选的目的是跳过不相关的问题。8个相关问题远胜于38个冗余问题。
  • 不要弱化结论。“可能是，倾向于，也许应该”这类表述会浪费本工具的价值。明确选择。
  • 第一直觉（Q9）至关重要。务必在分析前记录下来。如果最终结论与第一直觉不同，决策理由需要解释原因——这正是该问题的意义所在。
  • 归档所有决策，即使是小决策。其复合价值在于能够检索“去年我对定价做出了什么决策”——这要求即使在当下觉得决策显而易见时也要记录下来。