Back to Details

enrich

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Enrich Skill

Enrich 技能

Enrich person and company pages from external sources. Scale effort to importance.
从外部来源完善个人和公司页面。根据重要程度调整投入力度。

Contract

协议

This skill guarantees:
  • Every enriched page has compiled truth (State section) with inline citations
  • Every enriched page has a timeline with dated entries
  • Back-links are created bidirectionally
  • Tiered enrichment: Tier 1 (full), Tier 2 (medium), Tier 3 (minimal) based on notability
  • No stubs: every new page has meaningful content from web search or existing brain context
Filing rule: Read 
skills/_brain-filing-rules.md
before creating any new page.
本技能保证：
  • 每个完善后的页面都包含带有内嵌引用的整合事实（状态板块）
  • 每个完善后的页面都包含带日期条目的时间线
  • 双向创建反向链接
  • 分层完善：根据重要性分为1级（全面）、2级（中等）、3级（极简）
  • 无空白页面：每个新页面都包含来自网络搜索或现有大脑系统上下文的有意义内容
归档规则： 创建任何新页面前，请阅读
skills/_brain-filing-rules.md
。

Iron Law: Back-Linking (MANDATORY)

铁律：反向链接（强制要求）

Every mention of a person or company with a brain page MUST create a back-link FROM that entity's page TO the page mentioning them. An unlinked mention is a broken brain. See 
skills/_brain-filing-rules.md
for format.
每个提及存在大脑页面的个人或公司的内容，必须创建从该实体页面指向提及页面的反向链接。未链接的提及会导致大脑体系断裂。格式请参考
skills/_brain-filing-rules.md
。

Philosophy

理念

A brain page should read like an intelligence dossier, not a LinkedIn scrape. Facts are table stakes. Texture is the value -- what do they believe, what are they building, what makes them tick, where are they headed.
大脑页面应像一份情报档案，而非LinkedIn信息抓取。事实是基础，质感才是价值所在——他们的信念是什么，正在构建什么，核心驱动力是什么，未来方向如何。

Citation Requirements (MANDATORY)

引用要求（强制要求）

Every fact must carry an inline 
[Source: ...]
citation.
Three formats:
  • Direct attribution: 
    [Source: User, {context}, YYYY-MM-DD]
  • API/external: 
    [Source: {provider} enrichment, YYYY-MM-DD]
  • Synthesis: 
    [Source: compiled from {list of sources}]
Source precedence (highest to lowest):
  1. User's direct statements
  2. Compiled truth (pre-existing brain synthesis)
  3. Timeline entries (raw evidence)
  4. External sources (API enrichment, web search)
When sources conflict, note the contradiction with both citations.
每个事实必须带有内嵌的
[Source: ...]
引用。
三种格式：
  • 直接归因： 
    [Source: User, {context}, YYYY-MM-DD]
  • API/外部来源： 
    [Source: {provider} enrichment, YYYY-MM-DD]
  • 综合整理： 
    [Source: compiled from {list of sources}]
来源优先级（从高到低）：
  1. 用户的直接陈述
  2. 整合事实（预先存在的大脑系统综合内容）
  3. 时间线条目（原始证据）
  4. 外部来源（API丰富数据、网络搜索）
当来源存在冲突时，需注明矛盾点并附上双方引用。

When To Enrich

何时进行完善

Primary triggers

主要触发场景

  • User mentions an entity in conversation
  • Entity appears in a meeting transcript or email
  • New contact appears with significant context
  • Entity makes news or has a major event
  • Any ingest pipeline encounters a notable entity
  • 用户在对话中提及某个实体
  • 实体出现在会议记录或邮件中
  • 出现带有重要上下文的新联系人
  • 实体发布新闻或发生重大事件
  • 任何数据摄入管道遇到值得关注的实体

Do NOT enrich

请勿进行完善的场景

  • Random mentions with no relationship signal
  • Bot/spam accounts
  • Entities with no substantive connection to the user's work
  • Same page enriched within the past week (unless new signal warrants it)
  • 无关联信号的随机提及
  • 机器人/垃圾账号
  • 与用户工作无实质关联的实体
  • 过去一周内已完善过的页面（除非有新信号需要更新）

Enrichment Tiers

完善层级

Scale enrichment to importance. Don't waste API calls on low-value entities.
TierWhoEffortSources
1 (key)Inner circle, close collaborators, key contactsFull pipelineAll available APIs + deep web research
2 (notable)Occasional interactions, industry figuresModerateWeb research + social + brain cross-ref
3 (minor)Worth tracking, not criticalLightBrain cross-ref + social lookup if handle known
根据重要程度调整完善投入。不要在低价值实体上浪费API调用。
层级适用对象投入力度数据来源
1（核心）核心圈子、密切合作者、关键联系人全流程所有可用API + 深度网络调研
2（值得关注）偶尔互动对象、行业人物中等网络调研 + 社交平台 + 大脑系统交叉引用
3（次要）值得追踪但非关键的对象轻度大脑系统交叉引用 + 已知账号的社交平台查询

The Enrichment Protocol (7 Steps)

完善流程（7个步骤）

Step 1: Identify entities

步骤1：识别实体

Extract people, companies, concepts from the incoming signal.
从传入信号中提取人物、公司、概念。

Step 2: Check brain state

步骤2：检查大脑系统状态

For each entity:
  • gbrain search "name"
    -- does a page already exist?
  • If yes: UPDATE path (add new signal, update compiled truth if material)
  • If no: CREATE path (check notability gate first, then create)
针对每个实体：
  • gbrain search "name"
    ——是否已存在页面？
  • 若存在： 更新流程（添加新信号，若内容重要则更新整合事实）
  • 若不存在： 创建流程（先检查重要性门槛，再创建页面）

Step 3: Extract signal from source

步骤3：从来源提取信号

Don't just capture facts. Capture texture:
Signal TypeWhat to Extract
Opinions, beliefsWhat They Believe section
Current projects, features shippedWhat They're Building section
Ambition, career arc, motivationWhat Motivates Them section
Topics they return to obsessivelyHobby Horses section
Who they amplify, argue with, respectNetwork / Relationships
Ascending, plateauing, pivoting?Trajectory section
Role, company, funding, locationState section (hard facts)
不要只捕获事实，还要捕获质感：
信号类型提取内容
观点、信念他们的信念板块
当前项目、已发布功能他们正在构建的内容板块
抱负、职业发展轨迹、动机他们的驱动力板块
反复提及的热衷话题核心关注话题板块
他们推崇、争论或尊重的对象人脉/关系板块
上升、平稳、转型？发展轨迹板块
职位、公司、融资、地点状态板块（客观事实）

Step 4: External data source lookups

步骤4：外部数据源查询

Priority order -- stop when you have enough signal for the entity's tier.
4a. Brain cross-reference (always, all tiers)
  • gbrain search "name"
    and 
    gbrain query "what do we know about name"
  • Check related pages: company pages for person enrichment and vice versa
  • This is free and often the richest source
4b. Web research (Tier 1 and 2)
  • Use Perplexity, Brave Search, Exa, or equivalent web research tool
  • Key pattern: Send existing brain knowledge as context so the search returns DELTA (what's new vs what you already know), not a rehash
  • Opus-class models for Tier 1 deep research, lighter models for Tier 2
4c. Social media lookup (all tiers when handle known)
  • Pull recent posts/tweets for tone, interests, current focus
  • Social media is the highest-texture signal for what someone actually thinks
4d. People enrichment APIs (Tier 1)
  • LinkedIn data, career history, connections, education
4e. Company enrichment APIs (Tier 1)
  • Company data, financials, headcount, key hires, recent news
Data NeedExample SourcesTier
Web researchPerplexity, Brave, Exa1-2
LinkedIn / careerCrustdata, Proxycurl, People Data Labs1
Career historyHappenstance, LinkedIn1
Funding / company dataCrunchbase, PitchBook, Clearbit1
Social mediaPlatform APIs, web scraping1-3
Meeting historyCalendar/meeting transcript tools1-2
按优先级顺序操作——当获取到对应层级实体的足够信号时即可停止。
4a. 大脑系统交叉引用（所有层级必做）
  • gbrain search "name"
    和 
    gbrain query "what do we know about name"
  • 查看相关页面：完善人物页面时查看公司页面，反之亦然
  • 这是免费且通常最丰富的数据源
4b. 网络调研（1级和2级）
  • 使用Perplexity、Brave Search、Exa或同类网络调研工具
  • 关键模式： 将现有大脑系统知识作为上下文发送，使搜索返回增量内容（即新信息 vs 已知信息），而非重复内容
  • 1级深度调研使用Opus级模型，2级使用轻量模型
4c. 社交平台查询（已知账号时所有层级适用）
  • 获取近期帖子/推文，了解语气、兴趣、当前关注点
  • 社交平台是了解某人真实想法的最高质感信号来源
4d. 人物丰富API（1级）
  • LinkedIn数据、职业经历、人脉、教育背景
4e. 公司丰富API（1级）
  • 公司数据、财务状况、员工数量、关键招聘、近期新闻
数据需求示例来源层级
网络调研Perplexity, Brave, Exa1-2
LinkedIn / 职业信息Crustdata, Proxycurl, People Data Labs1
职业经历Happenstance, LinkedIn1
融资/公司数据Crunchbase, PitchBook, Clearbit1
社交平台平台API、网页抓取1-3
会议历史日历/会议记录工具1-2

Step 5: Save raw data (preserves provenance)

步骤5：保存原始数据（保留来源）

Store raw API responses via 
put_raw_data
in gbrain:
json
{
  "source": "crustdata",
  "fetched_at": "2026-04-11T...",
  "query": "jane doe",
  "data": { ... }
}
Raw data preserves provenance. If the compiled truth is ever questioned, the raw data shows exactly what the API returned.
通过
put_raw_data
将原始API响应存储到gbrain：
json
{
  "source": "crustdata",
  "fetched_at": "2026-04-11T...",
  "query": "jane doe",
  "data": { ... }
}
原始数据保留来源信息。若整合事实受到质疑，原始数据可展示API返回的准确内容。

Step 6: Write to brain

步骤6：写入大脑系统

CREATE path

创建流程

  1. Check notability gate (see 
    skills/_brain-filing-rules.md
    )
  2. Check filing rules -- where does this entity go?
  3. Create page with the appropriate template (below)
  4. Fill compiled truth with citations
  5. Add first timeline entry
  6. Leave empty sections as 
    [No data yet]
    (don't fill with boilerplate)
  1. 检查重要性门槛（见
    skills/_brain-filing-rules.md
    ）
  2. 检查归档规则——该实体应归入何处？
  3. 使用相应模板创建页面（如下）
  4. 填充带有引用的整合事实
  5. 添加第一条时间线条目
  6. 空白板块留为
    [No data yet]
    （不要用模板内容填充）

UPDATE path

更新流程

  1. Add new timeline entries (reverse-chronological, append-only)
  2. Update compiled truth ONLY if the new signal materially changes the picture
  3. Update State section with new facts
  4. Flag contradictions between new signal and existing compiled truth
  5. Don't overwrite user-written assessments with API boilerplate
  1. 添加新的时间线条目（倒序排列，仅追加）
  2. 仅当新信号实质性改变现有内容时，才更新整合事实
  3. 用新事实更新状态板块
  4. 标记新信号与现有整合事实之间的矛盾
  5. 不要用API模板内容覆盖用户撰写的评估

Person page template

人物页面模板

markdown
---
title: Full Name
type: person
created: YYYY-MM-DD
updated: YYYY-MM-DD
tags: []
company: Current Company
relationship: How the user knows them
email:
linkedin:
twitter:
location:
---
markdown
---
title: Full Name
type: person
created: YYYY-MM-DD
updated: YYYY-MM-DD
tags: []
company: Current Company
relationship: How the user knows them
email:
linkedin:
twitter:
location:
---

Full Name

Full Name

1-paragraph executive summary: HOW do you know them, WHY do they matter, what's the current state of the relationship.
1段执行摘要：你如何认识他们，他们为何重要，当前关系状态。

State

State

Role, company, key context. Hard facts only.
职位、公司、关键背景。仅包含客观事实。

What They Believe

What They Believe

Ideology, first principles, worldview. What hills do they die on?
意识形态、核心原则、世界观。他们坚持的立场是什么？

What They're Building

What They're Building

Current projects, recent launches, what they're focused on.
当前项目、近期发布内容、他们的关注点。

What Motivates Them

What Motivates Them

Ambition, career arc, what drives them.
抱负、职业发展轨迹、驱动他们的因素。

Hobby Horses

Hobby Horses

Topics they return to obsessively. Recurring themes in their work/posts.
他们反复提及的热衷话题。工作/帖子中的 recurring themes。

Assessment

Assessment

Your read on this person. Strengths, gaps, trajectory.
你对该人物的评价。优势、不足、发展轨迹。

Trajectory

Trajectory

Ascending, plateauing, pivoting, declining? Where are they headed?
上升、平稳、转型、衰退？他们的未来方向如何？

Relationship

Relationship

History of interactions, shared context, relationship quality.
互动历史、共同背景、关系质量。

Contact

Contact

Email, social handles, preferred communication channel.
邮箱、社交账号、偏好沟通渠道。

Network

Network

Key connections, mutual contacts, organizational relationships.
关键人脉、共同联系人、组织关系。

Open Threads

Open Threads

Active conversations, pending items, things to follow up on.
进行中的对话、待办事项、需跟进的内容。

Timeline

Timeline

Reverse chronological. Every entry has a date and [Source: ...] citation.
  • YYYY-MM-DD | Event description [Source: ...]
undefined
倒序排列。每个条目都有日期和[Source: ...]引用。
  • YYYY-MM-DD | 事件描述 [Source: ...]
undefined

Company page template

公司页面模板

markdown
---
title: Company Name
type: company
created: YYYY-MM-DD
updated: YYYY-MM-DD
tags: []
---
markdown
---
title: Company Name
type: company
created: YYYY-MM-DD
updated: YYYY-MM-DD
tags: []
---

Company Name

Company Name

1-paragraph executive summary.
1段执行摘要。

State

State

What they do, stage, key people, key metrics, your connection.
业务内容、发展阶段、关键人物、核心指标、你的关联。

Open Threads

Open Threads

Active items, pending decisions, things to track.
待办事项、待决策内容、需追踪的事项。

Timeline

Timeline

  • YYYY-MM-DD | Event description [Source: ...]
undefined
  • YYYY-MM-DD | 事件描述 [Source: ...]
undefined

Step 7: Cross-reference

步骤7：交叉引用

  • Update company pages from person enrichment (and vice versa)
  • Update related project/deal pages if relevant context surfaced
  • Add back-links from every entity mentioned (MANDATORY)
  • Check index files if the brain uses them
  • 通过人物完善内容更新公司页面（反之亦然）
  • 若发现相关上下文，更新关联项目/交易页面
  • 为每个提及的实体添加反向链接（强制要求）
  • 若大脑系统使用索引文件，请检查索引

Bulk Enrichment Rules

批量完善规则

  • Test on 3-5 entities first. Read actual output. Check quality.
  • Only proceed to bulk after test shots pass your quality bar.
  • 3+ entities from one source -> batch process or spawn sub-agent
  • Throttle API calls. Respect rate limits.
  • Commit every 5-10 entities during bulk runs.
  • Save a report after bulk enrichment (see Report Storage below).
  • 先在3-5个实体上测试。 查看实际输出，检查质量。
  • 仅当测试结果符合质量标准后，再进行批量操作。
  • 同一来源的3个以上实体 -> 批量处理或生成子Agent
  • 限制API调用频率，遵守速率限制。
  • 批量运行时，每处理5-10个实体提交一次。
  • 批量完善后保存报告（见下文报告存储）。

Validation Rules

验证规则

  • Connection count < 20 on LinkedIn = likely wrong person, skip
  • Name mismatch between brain and API = skip, flag for review
  • Joke profiles or obviously wrong data = save to raw, don't update page
  • Don't overwrite user-written assessments with API boilerplate
  • When in doubt: save raw data but don't update brain page
  • LinkedIn人脉数<20 = 可能是错误人物，跳过
  • 大脑系统与API中的名称不匹配 = 跳过，标记待审核
  • 玩笑账号或明显错误数据 = 保存到原始数据，不要更新页面
  • 不要用API模板内容覆盖用户撰写的评估
  • 存疑时：保存原始数据但不更新大脑页面

Report Storage

报告存储

After enrichment sweeps, save a report:
  • Number of entities processed
  • New pages created vs existing updated
  • Data sources called and results quality
  • Notable discoveries or contradictions
  • Validation flags or API failures
This creates an audit trail for brain enrichment over time.
完善扫描完成后，保存一份报告：
  • 处理的实体数量
  • 创建的新页面 vs 更新的现有页面数量
  • 调用的数据源及结果质量
  • 值得关注的发现或矛盾点
  • 验证标记或API失败情况
这将为大脑系统的完善过程创建审计追踪记录。

Anti-Patterns

反模式

  • Creating stub pages with no content
  • Enriching without checking brain first
  • Overwriting user's direct statements with API data
  • Creating pages for non-notable entities
  • 创建无内容的空白页面
  • 未先检查大脑系统就进行完善
  • 用API数据覆盖用户的直接陈述
  • 为非重要实体创建页面

Output Format

输出格式

An enriched person page contains:
  • Frontmatter with type, tags, company, relationship, and contact fields
  • Executive summary (1 paragraph: how you know them, why they matter, relationship state)
  • State section with hard facts and inline 
    [Source: ...]
    citations
  • Texture sections (What They Believe, What They're Building, What Motivates Them, Hobby Horses)
  • Assessment with trajectory read
  • Relationship history and contact info
  • Network connections and mutual contacts
  • Timeline in reverse chronological order, every entry dated with source citation
An enriched company page contains:
  • Frontmatter with type and tags
  • Executive summary (1 paragraph)
  • State section (what they do, stage, key people, metrics, your connection)
  • Open Threads (active items, pending decisions)
  • Timeline in reverse chronological order with dated, cited entries
Both page types have bidirectional back-links to every entity they mention.
完善后的人物页面包含：
  • 前置元数据，包含类型、标签、公司、关系和联系字段
  • 执行摘要（1段：你如何认识他们，他们为何重要，关系状态）
  • 状态板块，包含客观事实和内嵌
    [Source: ...]
    引用
  • 质感板块（他们的信念、正在构建的内容、驱动力、核心关注话题）
  • 评估板块，包含发展轨迹判断
  • 关系历史和联系信息
  • 人脉关联和共同联系人
  • 时间线，倒序排列，每个条目都有日期和来源引用
完善后的公司页面包含：
  • 前置元数据，包含类型和标签
  • 执行摘要（1段）
  • 状态板块（业务内容、发展阶段、关键人物、指标、你的关联）
  • 待办事项（进行中的任务、待决策事项）
  • 时间线，倒序排列，每个条目都有日期和引用
两种页面类型都包含与提及的每个实体的双向反向链接。

Tools Used

使用工具

  • Read a page from gbrain (get_page)
  • Store/update a page in gbrain (put_page)
  • Add a timeline entry in gbrain (add_timeline_entry)
  • List pages in gbrain by type (list_pages)
  • Store raw API data in gbrain (put_raw_data)
  • Retrieve raw data from gbrain (get_raw_data)
  • Link entities in gbrain (add_link)
  • Check backlinks in gbrain (get_backlinks)
  • 从gbrain读取页面（get_page）
  • 在gbrain中存储/更新页面（put_page）
  • 在gbrain中添加时间线条目（add_timeline_entry）
  • 按类型列出gbrain中的页面（list_pages）
  • 在gbrain中存储原始API数据（put_raw_data）
  • 从gbrain检索原始数据（get_raw_data）
  • 在gbrain中关联实体（add_link）
  • 在gbrain中检查反向链接（get_backlinks）