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 > codex-export
c

导出Codex会话

技能标识：codex-export

Export a Codex CLI or Codex Desktop (App) session to a Markdown transcript. Use when the user asks to export, save, share, or review a past chat, session, or transcript. Supports --brief mode (user + assistant only, no tool calls) and --list to browse recent sessions. Works with both Codex CLI and Codex Desktop app sessions (unlike similar tools that only support CLI).

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

导出Codex会话

codex-export

将任意 Codex 会话（~/.codex/sessions//*.jsonl）导出为干净的 Markdown 文件。

使用方法

bash

列出最近的会话（通过编号选择或复制会话 ID）


python3 scripts/export.py --list

按会话 ID 导出

python3 scripts/export.py <会话ID> output.md

简洁模式：仅保留用户和助手消息，不包含工具调用

python3 scripts/export.py <会话ID> output.md --brief

注意事项

  • - 支持 Codex Desktop（source=vscode）和 Codex CLI（source=cli/exec）
  • 会话 ID 来自 ~/.codex/state5.sqlite 或滚动文件名
  • 系统/开发者消息及 context> 块会被自动过滤
  • 默认包含工具调用输出；使用 --brief 可去除这些内容

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 codex-export-1776195781 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 codex-export-1776195781 技能

通过命令行安装

skillhub install codex-export-1776195781

下载

⬇ 下载 codex-export v0.1.0（免费）

文件大小: 4.47 KB | 发布时间: 2026-4-17 14:26

v0.1.0 最新 2026-4-17 14:26
Initial release of codex-export.

- Export Codex CLI or Codex Desktop sessions to Markdown transcripts.
- Supports listing recent sessions, brief mode (user + assistant only), and exporting by session ID.
- Automatically filters system messages and environment context blocks.
- Handles both Codex CLI and Desktop app sessions.
- Includes or omits tool call outputs based on `--brief` flag.

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User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task.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