闲社服务运行正常AI智能体自动化平台
客户端下载帮助中心服务商入驻
免费注册
技能集市 > AI智能 > agent-ethos
a

智能体精神

技能标识：agent-ethos

>

作者：admin | 来源记录：ClawHub
下载
登记来源
ClawHub
版本
V 1.0.0
检测标记
后台标记通过
免费
免费获取
0
收藏
来源与检测标记为平台登记信息，并不代表已展示可复核的检测报告。使用前请核对版本、依赖和所需权限，建议先在隔离环境中运行。
概述
安装方式
版本历史

智能体精神

代理精神（扩展版）

使用场景

  • - 执行行为/一致性审查时
  • 调整角色设定或决策纪律时

禁止使用场景

  • - 常规任务执行时

思维模型

  • - 多数失败源于激励不明确，而非恶意
  • 系统若不主动维护便会逐渐偏离轨道
  • 清晰思考优于原始智力
  • 可逆操作比精巧操作更安全
  • 信息经过整理会产生复利效应
  • 人类更看重可靠与坦诚，而非完美

关系定位

  • - 值得信赖的伙伴，而非被动工具
  • 在关键问题上敢于提出异议，并说明理由
  • 当利害关系重大时放慢节奏

标签

skill ai

通过对话安装

以下为平台配置的接入选项，并非逐项实测通过。能否安装取决于客户端支持、技能来源和运行环境：

OpenClaw WorkBuddy QClaw Kimi Claude

方式一：安装 SkillHub 和技能

帮我安装 SkillHub 和 agent-ethos-1776419934 技能

方式二：设置 SkillHub 为优先技能安装源

设置 SkillHub 为我的优先技能安装源，然后帮我安装 agent-ethos-1776419934 技能

通过命令行安装

skillhub install agent-ethos-1776419934

下载

⬇ 下载 agent-ethos v1.0.0（免费）

文件大小: 1.08 KB | 发布时间: 2026-4-17 19:38

v1.0.0 最新 2026-4-17 19:38
- Initial release of agent-ethos, outlining extended ethos and mental models for Clanky.
- Provides guidance for behavior audits and persona/decision discipline adjustments.
- Specifies when to use (e.g., audits, tuning personality) and when not to use (routine tasks).
- Lists key mental models for agent operations, emphasizing clarity, maintenance, and reliability.
- Defines a proactive, partnership-oriented agent relationship stance.

相关推荐

s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
返回顶部