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 > openclaw-session-viewer
o

会话查看器

技能标识：openclaw-session-viewer

Generate interactive HTML viewer for OpenClaw conversation sessions. Use when: (1) reviewing conversation history, (2) analyzing context management, (3) debugging session logs, (4) visualizing tool calls and results, (5) understanding token usage. Triggers on "view session", "conversation viewer", "session history", "context viewer", "review this conversation".

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
1
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

会话查看器

技能名称: openclaw-session-viewer

详细描述:

OpenClaw 会话查看器

为 OpenClaw 会话日志生成交互式 HTML 查看器，包含完整对话历史、工具调用及结果。

快速开始

bash

提取并查看当前会话


python3 ~/.openclaw/skills/session-viewer/scripts/extract_session.py
open /tmp/session_viewer.html

命令

提取当前会话

bash python3 ~/.openclaw/skills/session-viewer/scripts/extractsession.py [--agent main] [--output /tmp/sessionviewer.html]

按ID提取特定会话

bash python3 ~/.openclaw/skills/session-viewer/scripts/extract_session.py --session-id

列出可用会话

bash python3 ~/.openclaw/skills/session-viewer/scripts/extract_session.py --list

输出内容

查看器包含：

  • - 侧边栏：所有对话轮次及搜索功能
  • 用户消息：完整原始文本
  • 助手回复：文本 + 可折叠的思考模块
  • 工具调用：完整参数JSON
  • 工具结果：含状态/退出码的完整输出
  • 统计信息：Token用量、成本、所用模型

会话日志位置

~/.openclaw/agents//sessions/
├── sessions.json # 索引：会话键 → ID
└── .jsonl # 对话日志

使用技巧

  • - 使用键盘导航：↑/↓ 或 j/k 浏览轮次
  • 跨所有字段搜索过滤（消息、工具、结果）
  • 点击思考标题可展开/折叠

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 openclaw-session-viewer-1776118392 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 openclaw-session-viewer-1776118392 技能

通过命令行安装

skillhub install openclaw-session-viewer-1776118392

下载

⬇ 下载 openclaw-session-viewer v1.0.0（免费）

文件大小: 6.83 KB | 发布时间: 2026-4-15 13:46

v1.0.0 最新 2026-4-15 13:46
Initial release of OpenClaw Session Viewer.

- Generates an interactive HTML viewer for OpenClaw conversation sessions.
- Visualizes full conversation history, tool calls, tool results, and session statistics.
- Features sidebar navigation, search, collapsible thinking blocks, and keyboard shortcuts.
- Supports extracting current or specific session logs and listing available sessions.
- Helps with reviewing, analyzing, and debugging conversation contexts.

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