memory-research

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Memory Research

记忆研究

Research an external subject, synthesize what you find, and create a structured Basic Memory entity — with the user's approval.

通过网页搜索研究外部主题，整合研究结果，并在获得用户批准后创建结构化的Basic Memory实体。

When to Use

使用场景

Explicit triggers:

"Research [subject]"
"Look up [subject]"
"What do you know about [subject]?"
"Evaluate [subject]"

Implicit triggers (also activate this skill):

A bare name: "Terraform"
A URL: "https://example.com"
A name with context: "Acme Corp — saw them at the conference"

明确触发条件：

"研究[主题]"
"查找[主题]"
"你了解[主题]的哪些信息？"
"评估[主题]"

隐含触发条件（同样会激活此技能）：

仅提供名称："Terraform"
提供URL："https://example.com"
带上下文的名称："Acme Corp — 我在会议上见过他们"

Workflow

工作流程

Step 1: Web Research

步骤1：网页搜索

Search for current information across multiple sources. Aim for 3-5 searches to build a well-rounded picture:

[subject name] site
[subject name] overview
[subject name] news [current year]
[subject name] [relevant domain keywords]

What to gather by entity type:

Entity Type	Key Information
Organization	What they do, products/services, stage (startup/growth/public), funding, leadership, headquarters, employee count, notable partnerships or contracts
Person	Current role, organization, background, expertise, notable work, public presence
Technology	What it does, who maintains it, maturity, ecosystem, alternatives, adoption
Topic/Domain	Definition, current state, key players, trends, relevance to user's context

在多个来源中搜索最新信息。建议进行3-5次搜索，以形成全面的认知：

[主题名称] site
[主题名称] overview
[主题名称] news [当前年份]
[主题名称] [相关领域关键词]

按实体类型收集信息：

实体类型	关键信息
组织	业务范围、产品/服务、发展阶段（初创/成长/上市）、融资情况、领导层、总部、员工数量、重要合作或合同
人物	当前职位、所属组织、背景、专业领域、重要成果、公开影响力
技术	功能、维护方、成熟度、生态系统、替代方案、采用情况
主题/领域	定义、当前状态、关键参与者、趋势、与用户上下文的相关性

Step 2: Check Existing Knowledge

步骤2：检查现有知识

Before proposing a new entity, search Basic Memory:

python

search_notes(query="Acme Corp")
search_notes(query="acme")

Try name variations — full name, abbreviation, acronym, domain name.

If the entity already exists:

Report what you found in Basic Memory alongside your web research
Offer to update the existing note with new information
Use
```
edit_note
```
to append new observations or update outdated ones

If the entity doesn't exist, proceed to evaluation.

在创建新实体前，先搜索Basic Memory：

python

search_notes(query="Acme Corp")
search_notes(query="acme")

尝试不同的名称变体——全名、缩写、首字母缩写、域名。

如果实体已存在：

同时报告Basic Memory中已有的信息和新的网页研究结果
提议用新信息更新现有记录
使用
```
edit_note
```
追加新发现或更新过时信息

如果实体不存在，进入评估阶段。

Step 3: Evaluate and Summarize

步骤3：评估与总结

Present your findings in a structured summary. Include all relevant information organized by section:

markdown

undefined

以结构化摘要的形式呈现研究结果，按板块组织所有相关信息：

markdown

undefined

[Subject Name]

[主题名称]

Type: [Organization / Person / Technology / Topic]

Summary: [2-4 sentences: what this is, why it matters, key distinguishing facts]

Key Details:

[Organized by what's relevant for the entity type]
[Stage, funding, leadership for orgs]
[Role, expertise, affiliations for people]
[Maturity, ecosystem, alternatives for tech]

Relevance: [Why this matters to the user — connection to their work, domain, or interests. If no obvious connection: "No specific connection identified."]

Sources:

[URLs of key sources consulted]

undefined

类型： [组织 / 人物 / 技术 / 主题]

摘要： [2-4句话：主题定义、重要性、关键区别性事实]

关键细节：

[根据实体类型整理相关内容]
[组织：发展阶段、融资、领导层]
[人物：职位、专业领域、关联机构]
[技术：成熟度、生态系统、替代方案]

相关性： [与用户的关联——和其工作、领域或兴趣的联系。若无明显关联："未发现特定关联。"]

来源：

[参考的关键来源URL]

undefined

Evaluation Guidelines

评估准则

Use hedging language. Web research is a snapshot, not ground truth:

"Appears to be", "Based on public information", "Estimated"
"As of [date]", "According to [source]"
Never state funding amounts, employee counts, or revenue as exact unless citing a primary source

Don't fabricate. If information isn't available, say so:

"Leadership information not publicly available"
"Funding details not disclosed"

Let the user define relevance. Don't impose a fixed evaluation framework. Instead, highlight facts and let the user draw conclusions. If the user has a specific evaluation rubric (strategic fit, buy/partner/compete, etc.), they'll tell you — apply it when asked.

使用模糊表述：网页研究只是快照，并非绝对事实：

"似乎是"、"根据公开信息"、"估计"
"截至[日期]"、"据[来源]报道"
除非引用原始来源，否则切勿将融资额、员工数或营收等数据表述为确切值

不要编造信息：若信息不可得，直接说明：

"领导层信息未公开"
"融资细节未披露"

由用户定义相关性：不要强加固定的评估框架。只需突出事实，让用户自行得出结论。如果用户有特定的评估标准（战略适配性、采购/合作/竞争等），他们会主动说明——此时再应用该标准。

Step 4: Propose Entity Creation

步骤4：提议创建实体

After presenting the summary, ask for approval:

Create Basic Memory entity for [Subject]?
  Location: [suggested-folder]/[entity-name].md
  Type: [entity type]

  [yes / no / modify]

If the user provided context with their request ("saw them at the conference"), include that context in the proposed entity.

在呈现摘要后，请求用户批准：

是否为[主题]创建Basic Memory实体？
  存储位置：[建议文件夹]/[实体名称].md
  类型：[实体类型]

  [是 / 否 / 修改]

如果用户在请求中提供了上下文（如"我在会议上见过他们"），请将该上下文包含在拟创建的实体中。

Step 5: Create the Entity

步骤5：创建实体

After approval, create a structured note. Adapt the template to the entity type:

获得批准后，创建结构化记录。可根据实体类型调整模板：

Organization

组织

python

write_note(
  title="Acme Corp",
  directory="organizations",
  note_type="organization",
  tags=["organization", "relevant-tags"],
  content="""# Acme Corp

python

write_note(
  title="Acme Corp",
  directory="organizations",
  note_type="organization",
  tags=["organization", "relevant-tags"],
  content="""# Acme Corp

Overview

概述

[2-3 sentence description from research]

[研究得出的2-3句描述]

Products & Services

产品与服务

[Key offerings discovered in research]

[研究发现的核心产品/服务]

Background

背景信息

Stage: [Startup / Growth / Public] Headquarters: [Location] Employees: [Estimate, hedged] Leadership: [Key people if found] Founded: [Year if found]

发展阶段： [初创 / 成长 / 上市] 总部： [地点] 员工数量： [估计值，使用模糊表述] 领导层： [若找到相关信息则列出] 成立时间： [若找到相关年份则列出]

Observations

观察结果

[relevance] Why this entity matters in user's context
[source] Researched on YYYY-MM-DD
[additional observations from research findings]

[相关性] 该实体与用户上下文的关联
[来源] 研究日期：YYYY-MM-DD
[研究得出的其他观察结果]

Relations

关联关系

[Link to related entities already in the knowledge graph]""" )

undefined

[链接到知识图谱中已有的相关实体]""" )

undefined

Person

人物

python

write_note(
  title="Jane Smith",
  directory="people",
  note_type="person",
  tags=["person", "relevant-tags"],
  content="""# Jane Smith

python

write_note(
  title="Jane Smith",
  directory="people",
  note_type="person",
  tags=["person", "relevant-tags"],
  content="""# Jane Smith

Overview

概述

[Current role and affiliation. Brief background.]

[当前职位及所属机构。简要背景。]

Background

背景信息

Role: [Title at Organization] Expertise: [Key domains] Notable: [Publications, talks, projects if found]

职位： [所属机构的头衔] 专业领域： [核心领域] 重要成果： [若找到相关出版物、演讲或项目则列出]

Observations

观察结果

[role] Title at Organization
[expertise] Key technical or domain expertise
[source] Researched on YYYY-MM-DD

[职位] 所属机构的头衔
[专业领域] 核心技术或领域专长
[来源] 研究日期：YYYY-MM-DD

Relations

关联关系

works_at [[Organization]]""" )

undefined

works_at [[Organization]]""" )

undefined

Technology

技术

python

write_note(
  title="Technology Name",
  directory="concepts",
  note_type="concept",
  tags=["concept", "technology", "relevant-tags"],
  content="""# Technology Name

python

write_note(
  title="Technology Name",
  directory="concepts",
  note_type="concept",
  tags=["concept", "technology", "relevant-tags"],
  content="""# Technology Name

Overview

概述

[What it is and what problem it solves]

[技术定义及解决的问题]

Key Details

关键细节

Maintained by: [Organization or community] Maturity: [Experimental / Stable / Mature] License: [If applicable] Alternatives: [Comparable tools or approaches]

维护方： [组织或社区] 成熟度： [实验性 / 稳定 / 成熟] 许可证： [若适用] 替代方案： [同类工具或方法]

Observations

观察结果

[definition] What this technology does in one sentence
[maturity] Current state and adoption level
[source] Researched on YYYY-MM-DD

[定义] 该技术的一句话功能描述
[成熟度] 当前状态及采用程度
[来源] 研究日期：YYYY-MM-DD

Relations

关联关系

[Link to related concepts, tools, or projects in the knowledge graph]""" )


Adapt these templates freely. The key elements are: note_type/tags parameters, an overview, structured details, observations with categories, and relations.

[链接到知识图谱中已有的相关概念、工具或项目]""" )


可灵活调整这些模板。核心要素包括：note_type/tags参数、概述、结构化细节、带分类的观察结果以及关联关系。

Step 6: Store Source Context

步骤6：存储源上下文

If the user provided context with their request, capture it in the entity:

python

undefined

如果用户在请求中提供了上下文，请将其添加到实体中：

python

undefined

User said: "Acme Corp — saw their demo at the conference last week"

用户表述："Acme Corp — 我上周在会议上看了他们的演示"

edit_note( identifier="Acme Corp", operation="append", section="Observations", content="- [context] Saw their demo at conference, week of 2026-02-17" )


This context is often the most valuable part — it's the user's relationship to the entity, which web research can't provide.

edit_note( identifier="Acme Corp", operation="append", section="Observations", content="- [context] 2026-02-17周在会议上观看了他们的演示" )


这类上下文通常是最有价值的部分——它代表了用户与该实体的关联，而这是网页搜索无法获取的。

Guidelines

指南

Always web search. Don't rely on training data alone. Research should reflect current, verifiable information.
Search Basic Memory first. Check for existing entities before creating new ones. Update rather than duplicate.
Hedge uncertain information. Use qualifiers for estimates, unverified claims, and inferred details.
Store source URLs. Include the URLs you consulted, either in observations or a Sources section. This enables the user to verify and dig deeper.
Get approval before creating. Present your findings and let the user decide whether to create the entity and what to include.
Capture user context. If the user told you why they're researching (met at a conference, evaluating as a vendor, etc.), that context belongs in the entity.
Don't over-research. 3-5 web searches is usually enough. The goal is a useful knowledge graph entry, not an exhaustive report.
Link to existing knowledge. Relate the new entity to things already in the knowledge graph. Connections compound value.

始终进行网页搜索：不要仅依赖训练数据。研究应反映最新、可验证的信息。
先搜索Basic Memory：创建新实体前先检查是否已存在。优先更新而非重复创建。
对不确定信息使用模糊表述：对估计值、未经验证的声明和推断的细节使用限定词。
存储来源URL：将参考的URL包含在观察结果或“来源”板块中。这能让用户验证信息并深入研究。
创建前需获得批准：先呈现研究结果，让用户决定是否创建实体及包含哪些内容。
捕捉用户上下文：如果用户说明了研究的原因（如在会议上见过、评估供应商等），请将该上下文添加到实体中。
不要过度研究：通常3-5次网页搜索已足够。目标是创建有用的知识图谱条目，而非详尽的报告。
关联现有知识：将新实体与知识图谱中已有的内容关联起来。关联能提升整体价值。