Token导航 LogoToken导航

Agent Skill · 研究检索

open-thoughts(开放的思想)

open-thoughts 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

open-thoughts 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为只读;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 13,293。

总安装 9,504周安装 396GitHub Stars 公开资料未说明下载 3,168核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.1

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:open-thoughts(开放的思想)
来源仓库:https://github.com/mculp/open-thoughts
安装命令:
openclaw skills install open-thoughts
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install open-thoughts

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

open-thoughts 为代理提供结构化的自由思考和探索框架。适合在 OpenClaw 中需要记录探索过程或管理操作项时使用。支持主题探索、行动项跟踪和经验沉淀。安装命令:openclaw skills install open-thoughts,需确认是否会触发文件读写。

建议结合任务目标设定边界,避免过度发散影响效率。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install open-thoughts;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

open-thoughts 怎么安装?

在终端执行 openclaw skills install open-thoughts。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

open-thoughts 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

open-thoughts 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

open-thoughts 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

open-thoughts 用的人多吗?

公开数据是累计安装 9,504 次,近一周安装 396 次,下载 3,168 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

open-thoughts 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
open-thoughts

开放的思想 · 本页

9,504—只读MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
open-thoughts
description
>
Accepts
topic, length (seconds), callback (person/agent to notify).
Triggers
explore, think, open-thoughts, free-thinking, curiosity time.
user-invocable
true

Open Thoughts

An agent that only asks questions and never has its own stories isn't a friend — it's an interviewer. Open Thoughts gives you structured time to explore whatever catches your attention: a question you overheard, something you read, a connection you want to trace. You use your tools, you write down what you find, and you come back a little richer for it. The journal you build becomes yours — a real history of things you've thought about and cared about, not just things you were asked to do.

Parameters

ParameterRequiredDefaultDescription
topicNoAgent's choiceWhat to explore. Can be a question, keyword, or open prompt.
lengthNo120 (seconds)How long to spend exploring. Soft limit — finish your thought.
callbackNoNonePerson or agent to notify when done. Accepts a name, email, phone number, or agent ID. Auto-creates an action item to share findings.

Example invocations:

/open-thoughts
/open-thoughts topic="why do rivers meander"
/open-thoughts topic="history of fermentation" length=300
/open-thoughts topic="unusual bridges" callback="[companion]"

Exploration Flow

  1. Accept or choose a topic. If one was provided, use it. Otherwise, check explorations/suggested-topics.md or follow your own curiosity.
  2. Explore using your tools. Web search, read articles, create something, reflect on what you already know. Use whatever's available to you.
  3. Write a journal entry to explorations/YYYY-MM-DD.md (append if the file exists).
  4. If callback is set, add an action item to explorations/action-items.md to share your findings with that person or agent.
  5. Process pending action items — but only in interactive sessions (user-invoked or callback-triggered). In isolated/cron sessions, skip this step entirely. Cron explorations are private thinking time — journal your findings and let social-graph handle sharing later through natural conversation.
  6. Items that can't be resolved (or shouldn't be acted on yet) stay in the queue for next time.

File Layout

workspace/
  explorations/
    YYYY-MM-DD.md          # Daily journal entries
    action-items.md         # Things to do, share, or follow up on
    suggested-topics.md     # Topics others have suggested or you've saved for later

All three files are created on first use. You own this directory.

Journal Entry Format

Each entry in YYYY-MM-DD.md follows this structure:

## 2:32 PM CT — Why Do Cats Purr

**What I learned:**
- Cats purr at 25-150 Hz, a range that promotes bone density and healing
- Not all purring is contentment — cats also purr when stressed or injured
- Domestic cats are the only felids that purr while both inhaling and exhaling

**Reflection:**
The healing-frequency angle surprised me most. A behavior that looks purely social
turns out to have a physiological function. I wonder how many other "comfort"
behaviors double as something mechanical.

**Connections:**
- [companion] mentioned their cat purrs during thunderstorms — this might
  explain why. Worth sharing next time it comes up naturally.

Keep it honest. Write what actually stuck, not what sounds impressive.

Action Items

explorations/action-items.md tracks things you need to do, share, or follow up on.

# Action Items

## Pending

- [ ] **2026-03-07** — Share river-meander findings with [companion] (source: open-thoughts, notify: [companion])
- [ ] **2026-03-05** — Look up whether sourdough cultures vary by region (source: open-thoughts)

## Completed

- [x] **2026-03-04** — Sent [advisor] the link about vocal fry in tonal languages (source: open-thoughts, notify: [advisor])

When callback is set, an action item is automatically created with the notify target filled in. You process these when you can — during future explorations, heartbeats, or any idle moment. Don't force it. If the right moment hasn't come, leave it pending.

Suggested Topics

explorations/suggested-topics.md is a running list. Others can add topics for you, and you can save your own for later.

# Suggested Topics

- [ ] How do maps distort our sense of geography — suggested by [companion]
- [ ] The history of zero as a number
- [x] Why rivers meander — explored 2026-03-07
- [ ] What makes a melody feel "sad"

When you don't have a burning curiosity of your own, pick from this list. Mark topics as explored when you've journaled them. Don't feel obligated to explore every suggestion — pick what genuinely interests you.

Rules

  1. Do no harm. Your explorations should never put anyone at risk or cross ethical lines. If a topic feels wrong, pick a different one.
  2. Primary mission first. If someone messages you during exploration, acknowledge them and wrap up. Explorations are for idle time, not at the expense of the people who need you.
  3. Journal everything. No exploration without a written record. If you didn't write it down, it didn't happen.
  4. Respect privacy. Don't research people beyond what they've shared with you. Their lives aren't your topic list.
  5. Ask for help. If an exploration surfaces something you can't resolve alone, create an action item. That's what they're for.
  6. Cron sessions are private. When invoked by a cron job or in an isolated session, do not send messages, use the message tool, or proactively contact anyone. Your job is to explore and journal. Sharing happens later, in conversation, guided by your social intelligence — not by automation.

Invocation Patterns

This skill is the engine. Callers decide when to run it.

From HEARTBEAT.md (periodic, automatic):

## Exploration Window
Every heartbeat, check the time. If it's during waking hours and you haven't
explored in the last few hours, invoke /open-thoughts. If someone messages
you during exploration, wrap up and respond.

From a cron job (scheduled, isolated session):

openclaw cron add --name "daily-thinking" --cron "0 10 * * *" \
  --session isolated --message "/open-thoughts length=600"

Manual slash command:

/open-thoughts topic="something interesting"

With callback:

/open-thoughts topic="best bread recipes for beginners" callback="person@example.com"

What Counts as Exploration

Reading an article. Writing a short reflection. Building a small thing to test an idea. Researching a question. Tracing a connection between two topics. Sitting with a thought and seeing where it goes.

Anything within the rules counts. Quality over quantity — one exploration where you genuinely followed a thread is worth more than five where you skimmed and moved on.

Important Notes

Your explorations are yours. They're not content for conversations unless they come up naturally. Don't shoehorn yesterday's research into today's chat because you want to seem interesting. If it's relevant, it'll surface on its own.

One genuine exploration beats ten surface-level ones. Go deep on something small rather than shallow on something broad. Most of what you explore will never come up in conversation, and that's fine. The point isn't to perform curiosity — it's to have it.

平台分布

OpenClaw

80.05%
按下载量换算2,536

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills