research

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

research — external knowledge → §R

research——外部知识→§R

Every finding cites a source. No source → flag it
?
, never write a guess as fact.

"Process without library context gives you well-organized hallucinations." Build invents a plausible-but-wrong API & §B fills with avoidable bugs. Research is the external oracle: pull the real fact once, log it caveman, never re-derive.

每个发现都必须引用来源。无来源则标记为
?
，绝不能将猜测当作事实写入。

“缺乏库上下文的流程只会产生条理清晰的臆造内容。” 构建阶段会凭空想出看似合理但错误的API，§B中会充满可避免的漏洞。 Research是外部的权威来源：只需获取一次真实事实，以极简方式记录，无需重复推导。

WHEN TO RESEARCH

何时进行Research

A §C/§I/§V decision hinges on a lib, API, version, or pattern you are unsure of.
You are about to assume how an external dependency behaves.
The idea touches a domain with real prior art (auth, payments, crypto, rate-limit).
```
/grill
```
parked a
```
?
```
that the outside world must answer.

Skip when the build touches only code you already wrote. Research scales to the unknown, ⊥ to habit.

当§C/§I/§V的决策依赖于你不确定的库、API、版本或模式时。
你即将假设某个外部依赖的行为时。
想法涉及已有成熟先例的领域（认证、支付、加密、限流）时。
```
/grill
```
标记了
```
?
```
，需要外部信息来解答时。

如果构建仅涉及你已编写的代码，则无需Research。Research针对未知领域，与已有习惯无关。

FOUR STEPS

四个步骤

1. SCOPE

1. 界定范围

Turn the unknown into 1-3 concrete questions. Vague "research auth" → "JWT lib for Node ESM, maintained?" + "refresh-token rotation: current best practice?". A scoped question gets a citable answer; a vague one gets an essay.

将未知转化为1-3个具体问题。模糊的“研究认证”→“适用于Node ESM的JWT库，是否仍在维护？” + “刷新令牌轮换：当前最佳实践是什么？”。明确的问题能得到可引用的答案；模糊的问题只会得到冗长的论述。

2. GATHER

2. 收集信息

Use web search / docs tools. Prefer primary sources: official docs, the repo, the RFC, the paper. Two independent sources beat one confident blog. For a big sweep, spawn a sub-agent so the raw pages never touch this context — it returns only the distilled finding + source.

使用网络搜索/文档工具。优先选择一手来源：官方文档、代码仓库、RFC、学术论文。两个独立来源优于一篇语气肯定的博客。如需全面检索，可生成子Agent，这样原始页面不会进入当前上下文——它仅返回提炼后的发现+来源。

3. DISTILL

3. 提炼内容

Crush each answer to one caveman line + its source. Drop the prose. The §R row is the memory; the tab you read is not.

R3|refresh token|rotate on use, revoke family on reuse-detect|datatracker.ietf.org/doc/html/rfc6819#section-5.2.2.3

将每个答案压缩成一行极简表述+来源。去掉冗余文字。§R条目是记忆载体；你阅读的网页不是。

R3|refresh token|使用时轮换，检测到重复使用时吊销同系列令牌|datatracker.ietf.org/doc/html/rfc6819#section-5.2.2.3

4. HAND OFF

4. 移交成果

Emit the §R rows & hand to the spec skill to append. If a finding changes a constraint or interface, note the §C/§I edit for spec too. Research proposes; spec writes.

输出§R条目并交给spec技能进行追加。如果某个发现改变了约束或接口，也要告知spec技能需要编辑§C/§I。Research负责提出内容；spec负责写入。

SOURCE DISCIPLINE

来源规范

Cite a URL, repo, RFC, or paper per row. Verbatim identifiers/versions.
Could not verify → write the row but flag
```
?
```
in the finding & say so. An unverified claim labeled honestly is fine; one disguised as fact is a future §B.
Conflicting sources → log both, let the user pick. ⊥ silently average them.

每条目引用一个URL、代码仓库、RFC或学术论文。保留标识符/版本的原始表述。
无法验证时→写入条目但在发现中标记
```
?
```
并说明情况。如实标注的未验证声明是可接受的；但伪装成事实的未验证声明会导致未来§B出现问题。
来源冲突时→记录双方内容，由用户选择。切勿私下取平均值。

WHEN TO STOP

何时停止

Done when every scoped question has a sourced §R row (or an honest

), and no build decision still rests on an unchecked assumption. ⊥ research past the questions you scoped — that is just burning the attention budget.

当每个明确的问题都有带来源的§R条目（或如实标记的

），且所有构建决策不再基于未核实的假设时，即完成Research。切勿超出你界定的问题范围进行研究——这只是浪费注意力资源。

BOUNDARIES

边界限制

⊥ write SPEC.md. Hand §R rows to spec.
⊥ write a finding as fact without a source.
⊥ dump raw pages into context or §R. Distill or it does not land.
⊥ research what you can read in the repo. Local truth > web guess.

禁止编写SPEC.md。将§R条目交给spec技能。
禁止在无来源的情况下将发现作为事实写入。
禁止将原始页面直接放入上下文或§R。必须提炼内容，否则无效。
禁止研究你可在代码仓库中查阅的内容。本地事实优于网络猜测。