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 > value-aware-guard
v

价值守护

技能标识：value-aware-guard

价值守护系统：监控价值漂移，检查边界违规，执行渐进式干预，支持独立CLI和proactive-engine协作。触发条件：价值偏离检测、边界违规、能量低警报、用户模式发现。

作者：admin | 来源记录：ClawHub
下载
登记来源
ClawHub
版本
V 0.7.0
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

价值守护

价值守护系统

使用方法

直接调用

bash node scripts/guard.js <命令> [选项]

信号处理模式

bash node scripts/guard.js --process-signal <信号>

命令

  • - monitor [选项] - 监控价值状态
  • check [选项] - 检查边界
  • intervene - 执行干预
  • report [选项] - 生成报告

示例

bash

监控边界


node scripts/guard.js monitor --check-boundaries

检查价值对齐

node scripts/guard.js check --alignment

信号处理

node scripts/guard.js --process-signal valuedriftdetected

与proactive-engine集成

该技能通过--process-signal参数与proactive-engine信号系统集成，支持自动价值监控和干预。

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 value-aware-guard-1775877482 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 value-aware-guard-1775877482 技能

通过命令行安装

skillhub install value-aware-guard-1775877482

下载

⬇ 下载 value-aware-guard v0.7.0（免费）

文件大小: 28.75 KB | 发布时间: 2026-4-12 11:48

v0.7.0 最新 2026-4-12 11:48
- Improved skill description to include support for standalone CLI and proactive-engine collaboration, as well as new trigger conditions.
- Simplified and reorganized usage instructions for both direct command and signal processing modes.
- Clarified and updated command list and usage examples.
- Added section detailing integration with proactive-engine signal system.
- Removed redundant reference files for a leaner repository.

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User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task.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