deep-research

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Deep research — gather wide, lose nothing

深度研究——广泛收集，全程留存

The failure mode this skill exists to prevent: a big parallel research fan-out gathers 80–100K tokens of detail, each subagent returns a trimmed summary, the orchestrator compresses again into a short brief, and the raw findings live only in ephemeral agent transcripts (scratchpad task outputs) that vanish when the container is reclaimed. Net: expensive research → a thin artifact, detail gone. Don't do that.

本技能旨在避免的失败模式：大规模并行研究扩散收集了80–100K tokens的细节内容，每个子Agent返回一份精简摘要，协调器再次压缩成简短报告，而原始研究结果仅存在于临时Agent对话记录（草稿任务输出）中，容器回收后便会消失。最终结果：投入大量成本的研究只产出一份单薄的成果，细节全部丢失。切勿如此操作。

The rule: two durable artifacts, never just one

规则：生成两份持久化成果，而非仅一份

Every nontrivial research effort produces, and SAVES to disk:

A synthesis — the brief / answer (tables, thesis, recommendation).
A full appendix — the per-source / per-company / per-angle DETAIL (raw numbers, funding histories, surfaces, dates, verbatim source URLs) the synthesis compressed.

If the saved synthesis is dramatically smaller than what was gathered, the appendix is how you reconcile that — the detail must land somewhere durable, not only in chat or a transcript. "I summarized it in chat" is not saved.

所有非琐碎的研究工作都需生成并保存至磁盘两份成果：

研究综述——简短报告/答案（含表格、核心论点、建议）。
完整附录——按来源/公司/研究角度整理的详细内容（原始数据、融资历史、公开信息、日期、原文来源URL），即研究综述中压缩掉的信息。

若保存的研究综述远小于收集到的原始内容，附录便是你还原细节的依据——所有细节必须存储在持久化位置，不能仅存在于聊天记录或对话中。“我在聊天里总结过了”不算保存。

Running a fan-out

执行并行研究扩散的步骤

Plan the angles — one subagent per distinct angle (company, source class, sub-question). Tell the user which model each runs on and why (the subagent-model-note rule).
Mandate write-to-disk in the subagent prompt. Every research subagent must WRITE its full findings to a durable file (e.g. the session scratchpad dir, one file per angle) with sources verbatim, and return only a short pointer + the headline findings. Do NOT rely on the agent's returned summary as the record — it is trimmed by construction and its transcript is ephemeral.
Capture sources verbatim — every claim carries [number] [source URL] [date] [reported vs estimate]. URLs are the first thing lost in compression; keep them.
Synthesize from the files, not from memory — read back the written files to build the synthesis, so nothing silently drops.
Save both artifacts before declaring done — commit/write the synthesis AND the appendix. Then it's saved.

规划研究角度——为每个独特的研究角度（公司、来源类别、子问题）分配一个子Agent。告知用户每个子Agent使用的模型及原因（遵循子Agent模型说明规则）。
在子Agent提示词中强制要求写入磁盘。每个研究子Agent必须将其完整研究结果写入持久化文件（例如会话草稿目录，每个角度对应一个文件），并保留原文来源，仅返回简短的文件指针 + 核心研究结论。切勿依赖Agent返回的摘要作为记录——它本质上是经过精简的，且其对话记录是临时的。
完整保留来源信息——每个结论需标注[编号] [来源URL] [日期] [事实报道 vs 估算]。URL是压缩过程中最容易丢失的信息，务必留存。
基于文件而非记忆生成综述——读取已写入的文件来构建研究综述，确保无信息被悄悄遗漏。
完成前保存两份成果——提交/写入研究综述和附录。至此，内容才算保存完成。

Where to save

存储位置

Generic / technical research →
```
research/<topic>.md
```
(+ appendix), referenced from a keyFile or
```
research/README.md
```
so it isn't an orphan doc.
Sensitive: competitive / VC / strategy / fundraising → the encrypted
```
startup/
```
vault (see
```
startup/CLAUDE.md
```
). Verify the vault is UNLOCKED before writing, and keep the strategic vocabulary out of any public doc.
When in doubt which, ask — but never let "unsure where" become "saved nowhere."

通用/技术研究 →
```
research/<topic>.md
```
（+附录），在关键文件或
```
research/README.md
```
中添加引用，避免文件成为孤立文档。
敏感内容：竞争情报/风投/战略/融资 → 加密的
```
startup/
```
vault（详见
```
startup/CLAUDE.md
```
）。写入前需确认vault已解锁，且战略相关词汇不得出现在任何公开文档中。
若不确定存储位置，请询问——但绝不能因“不确定存储位置”而导致“无处保存”。

Don't

禁忌

Don't present a one-paragraph chat summary as the deliverable for a 15-agent fan-out.
Don't trim sources/URLs/dates to make the brief shorter — that detail goes in the appendix.
Don't leave the only full copy in an ephemeral transcript or scratchpad you didn't commit.

切勿将一段聊天摘要作为15个Agent并行研究的交付成果。
切勿为缩短报告篇幅而删减来源/URL/日期——这些细节应放入附录。
切勿将唯一的完整副本留在未提交的临时对话记录或草稿中。