跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

Telegram Crabbox E2e Proof

技能 已验证 活跃

Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.

目的

To provide a robust and automated way to review, reproduce, or prove OpenClaw Telegram behavior in a realistic user-controlled environment, generating visual artifacts for PR reviews and bug reproduction.

功能

  • Agent-controlled Telegram user sessions
  • End-to-end testing with visual proof (recordings, screenshots)
  • TDLib and Telegram Desktop integration
  • Secure credential leasing from Convex
  • Automated session management (start, finish, status)
  • Command execution and message sending within the session

使用场景

  • Reproducing complex Telegram-related bugs.
  • Verifying OpenClaw Telegram integration behavior for pull request reviews.
  • Generating visual evidence of system behavior for documentation or debugging.
  • Automating the process of testing edge cases in a live Telegram environment.

非目标

  • Using personal Telegram accounts or adding credentials to the repository.
  • Automating direct user interactions outside of the specified testing workflow.
  • Providing general-purpose Telegram bot management.

安装

npx skills add steipete/clawdis

通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。

质量评分

已验证
100 /100
about 23 hours ago 分析

信任信号

最近提交about 24 hours ago
星标371.6k
许可证MIT
状态
查看源代码