idea-ingest

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Idea Ingest Skill

Filing rule: Read
skills/_brain-filing-rules.md
before creating any new page.

归档规则： 创建任何新页面之前，请阅读
skills/_brain-filing-rules.md
。

Contract

约定

This skill guarantees:

Every ingested item has a brain page with genuine analysis (not just a summary)
The author gets a people page (MANDATORY for anyone whose thinking is worth ingesting)
Cross-links created bidirectionally (source ↔ author, source ↔ mentioned entities)
Raw source preserved for provenance via
```
gbrain files upload-raw
```
Every fact has an inline
```
[Source: ...]
```
citation
Filing follows primary subject rules (not format-based)

本技能保证：

每个存入的条目都有一个包含真实分析（而非仅摘要）的大脑页面
为作者创建人物页面（对于任何其思想值得存入的人，这是强制性要求）
双向创建交叉链接（来源 ↔ 作者，来源 ↔ 提及的实体）
通过
```
gbrain files upload-raw
```
保留原始来源以确保溯源
每个事实都有一个内联的
```
[Source: ...]
```
引用
归档遵循主题优先规则（而非基于格式）

Iron Law: Back-Linking (MANDATORY)

铁律：反向链接（强制性要求）

Every mention of a person or company with a brain page MUST create a back-link. Format:

- **YYYY-MM-DD** | Referenced in [page title](path) — brief context

任何提及已有大脑页面的个人或公司时，必须创建反向链接。格式：

- **YYYY-MM-DD** | 在[页面标题](路径)中被引用 — 简要上下文

Phases

流程

Fetch the content. Use appropriate tools for the content type (web fetch for articles, API for tweets, PDF reader for documents).
Upload raw source. Save the fetched content for provenance:
```
gbrain files upload-raw <file> --page <slug>
```
Identify the author — MANDATORY people page. Anyone whose thinking is worth ingesting is worth tracking.
- Search brain for existing author page
- If no page → CREATE ONE with compiled truth + timeline format
- If page exists → update timeline with this new publication
- Cross-link both directions
Save to brain. File by PRIMARY SUBJECT (read
```
skills/_brain-filing-rules.md
```
):
- About a person →
```
people/
```
- About a company →
```
companies/
```
- A reusable framework →
```
concepts/
```
- Raw data dump →
```
sources/
```
Analyze for the user. Reply with analysis that connects the content to what the brain knows. Think about:
- Active projects — is this relevant?
- Contradictions — does this challenge existing brain knowledge?
- Connections — does this involve known people/companies?
- Don't just summarize. Tell the user things they wouldn't have noticed.
Sync.
```
gbrain sync
```
to update the index.

获取内容：根据内容类型使用合适的工具（文章用网页抓取，推文用API，文档用PDF阅读器）。
上传原始来源：保存获取的内容以确保溯源：
```
gbrain files upload-raw <file> --page <slug>
```
识别作者 — 强制性人物页面：任何其思想值得存入的人都值得被追踪。
- 在大脑中搜索现有作者页面
- 若无页面 → 创建一个包含整合信息+时间线格式的页面
- 若页面已存在 → 在时间线中更新此新发布内容
- 建立双向交叉链接
存入大脑：按主题优先归档（阅读
```
skills/_brain-filing-rules.md
```
）：
- 关于个人 →
```
people/
```
- 关于公司 →
```
companies/
```
- 可复用框架 →
```
concepts/
```
- 原始数据转储 →
```
sources/
```
为用户分析：回复时将内容与大脑已有的知识关联起来进行分析。思考以下方面：
- 活跃项目 — 这是否相关？
- 矛盾点 — 这是否挑战了大脑中的现有知识？
- 关联点 — 这是否涉及已知的个人/公司？
- 不要仅做摘要。告诉用户他们可能没注意到的点。
同步：执行
```
gbrain sync
```
更新索引。

Output Format

输出格式

markdown

undefined

markdown

undefined

{Title} — {Author}

{标题} — {作者}

Source: {URL} Author: {Author}, {role} Published: {date} Ingested: {date}

来源： {URL} 作者： {作者}, {职位} 发布日期： {日期} 存入日期： {日期}

Context

背景

{Why this matters now, connected to brain knowledge}

{为何现在重要，与大脑知识的关联}

Summary

摘要

{3-5 bullet core arguments}

{3-5个核心论点要点}

Key Data / Claims

关键数据/主张

{Specific facts, numbers, quotes}

{具体事实、数字、引用}

Analysis

分析

{How this connects to existing brain knowledge. What's new. What contradicts.}

undefined

{这与大脑现有知识的关联。新内容是什么。有哪些矛盾点。}

undefined

Anti-Patterns

反模式

Just summarizing without connecting to brain knowledge
Filing everything in
```
sources/
```
(sources is for raw data dumps only)
Skipping the author people page
Not cross-linking to mentioned entities
Ingesting without checking brain first for existing coverage

仅做摘要而不关联大脑知识
将所有内容归档到
```
sources/
```
（sources仅用于原始数据转储）
跳过作者人物页面
未与提及的实体建立交叉链接
存入前未先检查大脑中是否已有相关内容