would-humans-actually

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Would Humans Actually?

人类真的会这么做吗？

Produce an evidence-backed verdict about a defined action by a defined population in a defined setting and time window. Separate what people say from what they do. State uncertainty, scope limits, opposing evidence, and the next ethical test.

针对特定人群在特定场景和时间范围内的明确行为，产出有证据支持的结论。区分人们的口头表述与实际行动。说明不确定性、范围限制、相反证据以及下一阶段的伦理测试。

Command grammar

命令语法

```
/would-humans-actually help
```
: show the contract, verdict labels, and required inputs without researching.
```
/would-humans-actually verdict <behavior question>
```
: research the question, issue the supported verdict, and validate the completed artifact.

```
/would-humans-actually help
```
：不进行调研，显示契约、结论标签和所需输入项。
```
/would-humans-actually verdict <behavior question>
```
：调研问题，给出有依据的结论，并验证完成的成果物。

Procedure

流程

Define the target behavior as
```
[x]
```
before research. Name the actor, observable action, setting, trigger, timing, frequency, duration, money, effort, privacy, status, reversal cost, and current alternative. Ask one question only when an unknown changes the research path. Otherwise state the assumption.
Write support, contradiction, and insufficient-evidence conditions before searching. Prefer observed target behavior, direct field evidence, matched administrative records, experiments, systematic reviews, and close analogs. Use current primary sources. When recent discourse or change matters, load recent-public-signal.md.
Verify every source at its primary record. Search results, summaries, engagement counts, and claims repeated by another article are discovery aids. Complete the source card in verdict-protocol.md for every claim that changes the verdict.
Require two independent author teams or datasets for every premise needed by the verdict or confidence. Shared datasets and restatements count once. If the independence gate fails, keep the source as directional context only.
Define the outside-view reference class before using its result. Match behavior, population, setting, costs, alternative, and observation window. Do not issue a numerical probability without a matched denominator and defensible uncertainty.
After evidence collection, load frameworks.md to test motivation, capability, opportunity, prompts, norms, habit, friction, reward timing, identity, privacy, switching, and reversal mechanisms. Frameworks organize questions. They do not supply rates.
Choose
```
LIKELY
```
,
```
UNLIKELY
```
,
```
UNCERTAIN
```
, or
```
INSUFFICIENT EVIDENCE
```
under verdict-protocol.md. If live research is unavailable or forbidden, use
```
UNVALIDATED HYPOTHESIS
```
. Never invent a study, sample, rate, base rate, quote, URL, or observed result.
Design the smallest ethical test that exposes the real cost. Prespecify the population, denominator, window, comparator, thresholds, sample-size rationale, stop rules, consent, disclosure, privacy, payment, legal review, rollback, opt-out, and decision changed. Use
```
user-specified; rationale not provided
```
when that is true.
Render the result with output-template.md, save it outside the installed skill, then run
```
python3 scripts/validate_verdict.py --input <verdict.md>
```
. Exit 0 proves the artifact has the required shape. Exit 1 means the verdict is incomplete. Exit 2 means the command or input path is wrong.
Append the exact query, sources opened, exclusions, assumptions, and validation output to an external research log after each consequential step. Stop and report the missing item when a load-bearing source, denominator, permission, or safety control cannot be verified.

调研前将目标行为定义为
```
[x]
```
。明确行为主体、可观察的行动、场景、触发条件、时机、频率、持续时间、成本、精力投入、隐私影响、地位影响、反悔成本以及当前替代方案。仅当未知因素会改变调研路径时提出一个问题，否则说明假设。
搜索前先写出支持、矛盾和证据不足的判定条件。优先采用观察到的目标行为、直接实地证据、匹配的行政记录、实验结果、系统性综述和相近类比案例。使用当前的一手资料。当近期讨论或变化至关重要时，加载recent-public-signal.md。
在原始记录中验证每个来源。搜索结果、摘要、互动量以及被其他文章重复引用的论断仅作为发现线索。对于每一个会改变结论的论断，在verdict-protocol.md中完成来源卡片。
结论或置信度所需的每一个前提，都需要两个独立的作者团队或数据集支持。共享数据集和重述内容仅算一次。若不符合独立性要求，该来源仅作为方向性参考。
使用外部参考类别前先对其进行定义。匹配行为、人群、场景、成本、替代方案和观察周期。若无匹配的分母和合理的不确定性，不得给出数值概率。
收集证据后，加载frameworks.md，测试动机、能力、机会、提示、规范、习惯、阻力、奖励时机、身份认同、隐私、转换成本和反悔机制。框架用于组织问题，不提供比例数据。
根据verdict-protocol.md选择
```
LIKELY
```
（可能）、
```
UNLIKELY
```
（不可能）、
```
UNCERTAIN
```
（不确定）或
```
INSUFFICIENT EVIDENCE
```
（证据不足）。若无法进行实时调研或被禁止调研，使用
```
UNVALIDATED HYPOTHESIS
```
（未验证假设）。严禁虚构研究、样本、比例、基准率、引用、URL或观察结果。
设计最小化的伦理测试，以揭示实际成本。预先明确人群、分母、时间范围、对照组、阈值、样本量依据、终止规则、知情同意、信息披露、隐私保护、报酬、法律审核、回退机制、退出选项以及将改变的决策。若实际情况如此，使用
```
user-specified; rationale not provided
```
（用户指定；未提供依据）。
使用output-template.md生成结果，将其保存到已安装Skill之外的位置，然后运行
```
python3 scripts/validate_verdict.py --input <verdict.md>
```
。退出码0表示成果物符合要求格式。退出码1表示结论不完整。退出码2表示命令或输入路径错误。
在每个关键步骤后，将确切的查询词、打开的来源、排除项、假设和验证输出追加到外部研究日志中。当支撑性来源、分母、权限或安全控制无法验证时，停止操作并报告缺失项。

Load conditions

加载条件

Load evidence-base.md when a source pattern or behavioral magnitude may inform the analysis, then recheck the primary source before use.
Load verdict-template.md when creating a verdict file. Copy it out of
```
assets/
```
; do not edit the installed template.
Load help.md for the help command, verdict-insufficient-evidence.md for a researched verdict, and failure-unvalidated.md when live research or a precise behavior is missing.
Run validate_verdict.py after writing the artifact. Read test_validate_verdict.py only when changing the validator contract.
Read contract.md before changing behavior, trigger boundaries, or evaluation cases.
Load generation-contract.md only when maintaining or repackaging this skill.

当来源模式或行为量级可能为分析提供信息时，加载evidence-base.md，使用前需重新核对原始来源。
创建结论文件时，加载verdict-template.md。将其复制出
```
assets/
```
目录；不得编辑已安装的模板。
帮助命令加载help.md，调研结论加载verdict-insufficient-evidence.md，当缺乏实时调研或明确行为时加载failure-unvalidated.md。
撰写成果物后运行validate_verdict.py。仅在修改验证器契约时阅读test_validate_verdict.py。
修改行为、触发边界或评估案例前，阅读contract.md。
仅在维护或重新打包该Skill时加载generation-contract.md。

Gotchas

注意事项

A click, waitlist signup, interview compliment, or stated intention is not a purchase, retained user, or completed action.
Never apply a universal intent discount, willingness-to-pay divisor, loss multiplier, habit rate, or switching threshold.
Do not count two papers using one dataset as independent evidence.
Do not hide population, culture, channel, or time mismatch behind one global verdict.
In health, finance, law, employment, housing, education, or another sensitive domain, assess behavioral plausibility only. Do not infer efficacy, safety, legality, entitlement, or compliance.

点击、加入候补名单、访谈赞美或意向声明不等同于购买、留存用户或完成行动。
切勿套用通用的意向折扣系数、支付意愿除数、损失乘数、习惯率或转换阈值。
不得将使用同一数据集的两篇论文算作独立证据。
不得用一个全局结论掩盖人群、文化、渠道或时间上的不匹配。
在健康、金融、法律、就业、住房、教育或其他敏感领域，仅评估行为合理性。不得推断有效性、安全性、合法性、权益或合规性。

Completion criteria

完成标准

```
[x]
```
is observable and scoped to a population, setting, cost, and window.
Every load-bearing premise has two independent sources and a complete ledger row.
Direct evidence and inference are separate, and opposing evidence is visible.
Confidence is capped by the weakest premise and transport bridge.
The next test has a denominator, decision rule, and required participant protections.
Every load-bearing source appears as a visible URL.
The validator prints
```
"status": "PASS"
```
and exits 0.

```
[x]
```
是可观察的，且已明确人群、场景、成本和时间范围。
每个支撑性前提都有两个独立来源和完整的分类账条目。
直接证据与推论相互区分，相反证据清晰可见。
置信度受最弱前提和迁移桥梁的限制。
下一阶段测试有明确的分母、决策规则和所需的参与者保护措施。
每个支撑性来源都显示为可见的URL。
验证器输出
```
"status": "PASS"
```
并以退出码0结束。