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 > token-report
t

Token消耗报告

技能标识：token-report

生成 Token 消耗仪表盘截图并发送到飞书

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

Token消耗报告

技能名称: token-report
详细描述:

Token 消耗汇报

当 Simon 要求汇报 Token 用量时执行：

步骤

  1. 1. 推送到 Canvas
- 用 canvas action=present 推送 HTML 仪表盘 - 内容包含：主会话、Selina、Tars 的 tokens 和 context 用量
  1. 2. 截图
- 用 browser action=screenshot 截取 Canvas 画面 - profile=openclaw
  1. 3. 发送到飞书
- 用 message action=send 发送到目标群 - channel=feishu, target=chat:oc_ee1a93ad1eb6d46a8922d9ab898a0d10

HTML 模板

html


📊 Token 消耗汇总




主会话 (main)

336k

Context 52%




更新时间: 2026-02-27 17:00


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 token-report-1776294910 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 token-report-1776294910 技能

通过命令行安装

skillhub install token-report-1776294910

下载

⬇ 下载 token-report v1.0.0（免费）

文件大小: 1.4 KB | 发布时间: 2026-4-16 18:23

v1.0.0 最新 2026-4-16 18:23
token-report 1.0.0

- Initial release for generating Token usage dashboard screenshots and sending them to Feishu.
- Includes a workflow for presenting an HTML dashboard in Canvas, capturing a screenshot, and posting to a specified Feishu chat group.
- Provides a built-in HTML template for clear visualization of token usage across different bots.

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User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task.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User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task.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