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 > firm-memory-audit-pack
f

固化记忆审计包

技能标识：firm-memory-audit-pack

>

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

固化记忆审计包

firm-memory-audit-pack

⚠️ AI生成内容 — 使用前需人工验证。

目的

审计记忆基础设施：验证pgvector扩展配置（维度、索引类型、距离度量）以及知识图谱完整性（节点连接性、孤立节点检测、循环检测）。

工具（2个）

工具描述
openclawpgvectormemorycheckpgvector配置验证（维度、索引、距离）
openclawknowledgegraphcheck
知识图谱完整性审计 |

使用方法

yaml
skills:
- firm-memory-audit-pack

审计记忆基础设施：

openclawpgvectormemorycheck configpath=/path/to/config.json openclawknowledgegraphcheck configpath=/path/to/config.json

要求

  • - mcp-openclaw-extensions >= 3.0.0

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 firm-memory-audit-pack-1776281779 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 firm-memory-audit-pack-1776281779 技能

通过命令行安装

skillhub install firm-memory-audit-pack-1776281779

下载

⬇ 下载 firm-memory-audit-pack v1.0.0（免费）

文件大小: 1.24 KB | 发布时间: 2026-4-16 15:32

v1.0.0 最新 2026-4-16 15:32
Initial release of the firm-memory-audit-pack skill.

- Provides tools to audit memory infrastructure, specifically pgvector configuration and knowledge graph integrity.
- Includes two tools: `openclaw_pgvector_memory_check` and `openclaw_knowledge_graph_check`.
- Validates pgvector extension settings (dimensions, index type, distance metric).
- Audits knowledge graph for node connectivity, orphan detection, and cycle detection.
- Requires `mcp-openclaw-extensions >= 3.0.0`.

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User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task.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User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task.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