memory-research by basicmachines-co/basic-memory-skills
npx skills add https://github.com/basicmachines-co/basic-memory-skills --skill memory-research研究外部主题,综合你的发现,并创建一个结构化的基础记忆实体——在用户批准后。
显式触发词:
隐式触发词(同样会激活此技能):
在多个来源中搜索最新信息。目标是进行 3-5 次搜索以建立一个全面的认知:
[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]
根据实体类型收集的信息:
| 实体类型 | 关键信息 |
|---|---|
| 组织 | 他们做什么、产品/服务、阶段(初创/成长/上市)、融资、领导层、总部、员工人数、重要的合作伙伴关系或合同 |
| 人物 | 当前职位、所属组织、背景、专长、知名作品、公开形象 |
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| 技术 |
| 它做什么、谁维护它、成熟度、生态系统、替代方案、采用情况 |
| 主题/领域 | 定义、现状、关键参与者、趋势、与用户上下文的相关性 |
在提议新实体之前,先搜索基础记忆:
search_notes(query="Acme Corp")
search_notes(query="acme")
尝试名称变体——全名、缩写、首字母缩写、域名。
如果实体已存在:
edit_note 来追加新观察结果或更新过时的信息如果实体不存在,则继续评估。
以结构化摘要的形式呈现你的发现。按部分组织所有相关信息:
## [主题名称]
**类型:** [组织 / 人物 / 技术 / 主题]
**摘要:** [2-4 句话:这是什么,为什么重要,关键的区分性事实]
**关键细节:**
- [根据实体类型组织相关信息]
- [对于组织:阶段、融资、领导层]
- [对于人物:职位、专长、隶属关系]
- [对于技术:成熟度、生态系统、替代方案]
**相关性:** [为什么这对用户重要——与其工作、领域或兴趣的联系。
如果没有明显联系:"未发现特定联系。"]
**来源:**
- [所查阅的关键来源的 URL]
使用留有余地的语言。 网络研究是快照,并非绝对真理:
不要捏造。 如果信息不可用,请如实说明:
让用户定义相关性。 不要强加固定的评估框架。相反,突出事实,让用户得出结论。如果用户有特定的评估标准(战略契合度、购买/合作/竞争等),他们会告诉你——在被要求时应用它。
呈现摘要后,请求批准:
Create Basic Memory entity for [主题]?
位置: [建议文件夹]/[实体名称].md
类型: [实体类型]
[是 / 否 / 修改]
如果用户在请求时提供了上下文("在会议上见过他们"),请将该上下文包含在提议的实体中。
获得批准后,创建一个结构化的笔记。根据实体类型调整模板:
write_note(
title="Acme Corp",
directory="organizations",
note_type="organization",
tags=["organization", "relevant-tags"],
content="""# Acme Corp
## 概述
[来自研究的 2-3 句话描述]
## 产品与服务
- [研究中发现的关键产品/服务]
## 背景
**阶段:** [初创 / 成长 / 上市]
**总部:** [地点]
**员工:** [估计值,需注明不确定性]
**领导层:** [如果找到的关键人物]
**成立时间:** [如果找到的年份]
## 观察
- [相关性] 该实体在用户上下文中的重要性
- [来源] 研究于 YYYY-MM-DD
- [来自研究发现的其他观察]
## 关系
- [链接到知识图谱中已有的相关实体]"""
)
write_note(
title="Jane Smith",
directory="people",
note_type="person",
tags=["person", "relevant-tags"],
content="""# Jane Smith
## 概述
[当前职位和隶属关系。简要背景。]
## 背景
**职位:** [在组织的头衔]
**专长:** [关键领域]
**知名事迹:** [如果找到的出版物、演讲、项目]
## 观察
- [职位] 在组织的头衔
- [专长] 关键的技术或领域专长
- [来源] 研究于 YYYY-MM-DD
## 关系
- works_at [[组织]]"""
)
write_note(
title="Technology Name",
directory="concepts",
note_type="concept",
tags=["concept", "technology", "relevant-tags"],
content="""# Technology Name
## 概述
[它是什么以及它解决什么问题]
## 关键细节
**维护者:** [组织或社区]
**成熟度:** [实验性 / 稳定 / 成熟]
**许可证:** [如果适用]
**替代方案:** [可比较的工具或方法]
## 观察
- [定义] 用一句话描述该技术的作用
- [成熟度] 当前状态和采用水平
- [来源] 研究于 YYYY-MM-DD
## 关系
- [链接到知识图谱中相关的概念、工具或项目]"""
)
自由调整这些模板。关键要素是:note_type/tags 参数、概述、结构化细节、带分类的观察以及关系。
如果用户在请求时提供了上下文,请将其捕获到实体中:
# 用户说:"Acme Corp — 上周在会议上看到了他们的演示"
edit_note(
identifier="Acme Corp",
operation="append",
section="Observations",
content="- [上下文] 在会议上看到他们的演示,2026-02-17 那一周"
)
这个上下文通常是最有价值的部分——它是用户与该实体的关系,这是网络研究无法提供的。
每周安装数
27
代码库
GitHub 星标数
4
首次出现
2026年2月23日
安全审计
安装于
codex24
opencode22
gemini-cli22
claude-code22
github-copilot22
amp22
Research an external subject, synthesize what you find, and create a structured Basic Memory entity — with the user's approval.
Explicit triggers:
Implicit triggers (also activate this skill):
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 |
Before proposing a new entity, search Basic Memory:
search_notes(query="Acme Corp")
search_notes(query="acme")
Try name variations — full name, abbreviation, acronym, domain name.
If the entity already exists:
edit_note to append new observations or update outdated onesIf the entity doesn't exist, proceed to evaluation.
Present your findings in a structured summary. Include all relevant information organized by section:
## [Subject Name]
**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]
Use hedging language. Web research is a snapshot, not ground truth:
Don't fabricate. If information isn't available, say so:
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.
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.
After approval, create a structured note. Adapt the template to the entity type:
write_note(
title="Acme Corp",
directory="organizations",
note_type="organization",
tags=["organization", "relevant-tags"],
content="""# Acme Corp
## Overview
[2-3 sentence description from research]
## Products & Services
- [Key offerings discovered in research]
## Background
**Stage:** [Startup / Growth / Public]
**Headquarters:** [Location]
**Employees:** [Estimate, hedged]
**Leadership:** [Key people if found]
**Founded:** [Year if found]
## Observations
- [relevance] Why this entity matters in user's context
- [source] Researched on YYYY-MM-DD
- [additional observations from research findings]
## Relations
- [Link to related entities already in the knowledge graph]"""
)
write_note(
title="Jane Smith",
directory="people",
note_type="person",
tags=["person", "relevant-tags"],
content="""# Jane Smith
## Overview
[Current role and affiliation. Brief background.]
## Background
**Role:** [Title at Organization]
**Expertise:** [Key domains]
**Notable:** [Publications, talks, projects if found]
## Observations
- [role] Title at Organization
- [expertise] Key technical or domain expertise
- [source] Researched on YYYY-MM-DD
## Relations
- works_at [[Organization]]"""
)
write_note(
title="Technology Name",
directory="concepts",
note_type="concept",
tags=["concept", "technology", "relevant-tags"],
content="""# Technology Name
## Overview
[What it is and what problem it solves]
## Key Details
**Maintained by:** [Organization or community]
**Maturity:** [Experimental / Stable / Mature]
**License:** [If applicable]
**Alternatives:** [Comparable tools or approaches]
## Observations
- [definition] What this technology does in one sentence
- [maturity] Current state and adoption level
- [source] Researched on YYYY-MM-DD
## Relations
- [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.
If the user provided context with their request, capture it in the entity:
# User said: "Acme Corp — saw their demo at the conference last week"
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.
Weekly Installs
27
Repository
GitHub Stars
4
First Seen
Feb 23, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
codex24
opencode22
gemini-cli22
claude-code22
github-copilot22
amp22
AI 代码实施计划编写技能 | 自动化开发任务分解与 TDD 流程规划工具
49,800 周安装
Google Workspace 事件订阅命令 gws-events-subscribe:实时流式监控与自动化处理
8,000 周安装
Google Calendar 会议重新安排技能 - 自动更新会议时间并通知参与者
7,900 周安装
冲刺回顾模板:敏捷团队回顾会议指南与模板(开始-停止-继续/愤怒-悲伤-高兴/4Ls)
10,400 周安装
任务估算指南:敏捷开发故事点、计划扑克、T恤尺码法详解
10,500 周安装
站立会议模板:敏捷开发每日站会指南与工具(含远程团队异步模板)
10,500 周安装
OpenContext AI助手持久化记忆工具:跨会话上下文管理,减少重复解释
10,500 周安装