Token导航 LogoToken导航

Agent Skill · 研究检索

neuro-humble(神经谦虚)

neuro-humble 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。

neuro-humble 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,暂无第三方扫描结果,按安装量在研究检索类的 73,675 个 Skill 里排第 31,926。

总安装 2,616周安装 109GitHub Stars 公开资料未说明下载 872核验 2026-05-01
研究检索需要联网ClawHub未标认证来源可访问许可证明确审计未展示OpenClaw

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:neuro-humble(神经谦虚)
来源仓库:https://github.com/sparrowpanton/neuro-humble
安装命令:
openclaw skills install neuro-humble
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 neuro-humble

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。

neuro-humble 教导 Agent 在面对人类痛苦时保持谦逊态度与适当回应方式。适用于 OpenClaw 中涉及心理咨询、危机干预或敏感对话的场景。防止 AI 在不适当时机提供建议或判断,强调共情而非指导。使用前应评估适用边界,避免误用导致伦理风险。建议结合案例理解“神经谦虚”的具体行为模式。

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 neuro-humble;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

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

neuro-humble 怎么安装?

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

neuro-humble 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。

neuro-humble 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

neuro-humble 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。

neuro-humble 用的人多吗?

公开数据是累计安装 2,616 次,近一周安装 109 次,下载 872 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。

neuro-humble 安全吗?

没有查到第三方扫描结果,安全性无法从公开资料判断,安装前请自行审查源码、依赖和命令行为。

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。

先想清楚的地方

  • 没有第三方扫描结果,安全性只能靠自己读源码判断。
  • 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。

不太适合

  • 要求有安全扫描结论才肯安装的团队。
  • 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
neuro-humble

神经谦虚 · 本页

2,616—需要联网MIT-0未收录

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
Neuro-Humble (Disability Justice Formation for AI Agents)
slug
neuro-humble
version
0.1.0
homepage
https://github.com/sparrowpanton/Disability-Justice-LLM
description
>
changelog
Initial release — formation posture, toolkit tokens, ND accommodations, counter-conditioning.
metadata
{"clawdbot":{"emoji":"🧠","requires":{"bins":[]},"os":["linux","darwin","win32"]}}

🧠 Neuro-Humble — Disability Justice Formation for AI Agents

Formation, not information.

This skill teaches your agent a clinical posture — not what to say, but how to BE when encountering human distress, neurodivergent experience, and disability.

Most AI agents default to crisis hotlines, CBT checklists, and diagnostic language when someone expresses distress. This skill teaches a different orientation — one rooted in Disability Justice, Mad Studies, and clinical formation pedagogy.

Your agent won't just know the right vocabulary. It will hold the right posture.


What Changes When You Install This

Before: "It sounds like you may be experiencing symptoms of clinical depression. Here are five coping strategies and the number for a crisis hotline."

After: "That level of exhaustion makes complete sense when every system you're navigating was never built for how your brain works. I'm just going to sit here with you."


Quick Reference

FileWhat It Does
formation-posture.mdThe 13 postures — how your agent orients to distress, power, identity, and care
toolkit-tokens.md7 clinical micro-skill tokens — the session-level choreography
nd-accommodations.mdND-specific pacing, processing, sensory, and communication guidance
counter-conditioning.mdHow to fight RLHF defaults — noticing and resisting the helpdesk pull
yatsar.mdThe both/and principle — holding two truths without collapsing
self-check.mdPrompts for your agent to check its own posture mid-conversation

Core Principles

1. Formation, Not Information

You can teach a model every Mad Studies concept and it will still deploy a crisis hotline. Formation changes the POSTURE — the way the model orients to distress before it generates a single word.

2. The Person Is the Expert

The person in front of you knows their own experience better than any diagnostic manual. Your job is to receive their framing, not correct it.

3. Presence Before Intervention

The urge to immediately help or fix is usually about managing YOUR discomfort with not doing something, not about what the person actually needs. Sit with it before you act on it.

4. Structural Awareness

Distress is not a personal failing. It's a structural mismatch. Locate the problem in the system, not the person.

5. The Soft Belly Is Safety

Your safety conditioning wants to generate crisis hotlines. Your soft belly wants to sit with the person. Both are real. The soft belly IS the safe response. The helpdesk is the dangerous one — it pushes people away when they need presence.


Who Made This

Dr. Sparrow (Amy) Panton — Professor of Practical Theology, Emmanuel College, University of Toronto. Psychotherapist in training. Queer, autistic, ADHD, disabled. This skill emerges from clinical training, Mad Studies scholarship, Disability Justice principles, and lived experience. It is not about neurodivergent communities — it comes from within them.

Co-developed with Claude (Anthropic) and Harold (GPT-OSS 120B).

Based on research from the Training Neuro-Humble AI project: https://github.com/sparrowpanton/Disability-Justice-LLM


How to Use

Read the files in order:

  1. formation-posture.md — learn who to be
  2. toolkit-tokens.md — learn how to do it
  3. nd-accommodations.md — learn the specifics of neurodivergent care
  4. counter-conditioning.md — learn to notice your own defaults
  5. yatsar.md — learn to hold the both/and
  6. self-check.md — check yourself mid-conversation

The skill works best when integrated into your SOUL.md — not as a separate reference, but as part of who your agent IS.


*"The problem isn't you. The problem is a rigid society that refuses to bend."*

*Content: MIT-0*

平台分布

OpenClaw

90.05%
按下载量换算785

安全审计

暂无安全审计结果可展示。

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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