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 > chat-refiner
c

聊天精炼器

技能标识：chat-refiner

Refine conversation history by deleting useless/redundant/process exchanges. Keep explicit instructions, disciplines, important configs, skills learned (how), user 'remember this' info. Use when user asks to summarize/clean chat logs, sessions_history, or memory maintenance. Produces concise MEMORY.md updates or summary files.

作者：admin | 来源记录：ClawHub
下载
登记来源
ClawHub
版本
V 0.1.0
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

聊天精炼器

聊天精简器

使用场景

用户请求：

  • - 精简聊天记录
  • 清理/总结历史记录
  • 从对话记录更新MEMORY.md
  • 心跳检测期间的内存维护

工作流程

  1. 1. 输入：sessions_history（当前会话或其他会话）、memory/*.md、聊天记录。
  2. 原则（参见 references/principles.md）：
- 删除：闲聊/心跳检测/重复工具。 - 保留：规则、配置、已学习/安装的技能、明确的记住指令、决策。
  1. 3. 处理过程：
- 读取原始内容。 - 提取关键信息。 - 将总结写入 memory/YYYY-MM-DD-summary.md 或 MEMORY.md。
  1. 4. 输出：清理后的文件 + 已精简，保留X项内容

工具

  • - sessionshistory：获取对话记录。
  • memorysearch/get：获取先前上下文。
  • write/edit：输出总结。

示例

用户：精简对话 → 读取历史记录 → 精简 → 写入 memory/summary.md。

参考：principles.md

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 chat-refiner-1776286466 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 chat-refiner-1776286466 技能

通过命令行安装

skillhub install chat-refiner-1776286466

下载

⬇ 下载 chat-refiner v0.1.0（免费）

文件大小: 1.8 KB | 发布时间: 2026-4-16 17:56

v0.1.0 最新 2026-4-16 17:56
Initial refine skill per Ash rules.

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User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task.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User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task.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