nutshellai-tech/mobius/mobius-self-test

Claude Code and agent skill by nutshellai-tech/mobius

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Mobius 自我测试能力。部署后自动跑、也可手动跑一组 HTTP 冒烟(健康/鉴权/核心读 API/语音配置, 可选写往返), 快速确认重新部署后系统是否真的可用。当你怀疑系统异常、或刚部署完需要验收时使用。

Install

npx vskill@latest install nutshellai-tech/mobius/mobius-self-test

SKILL.md

何时使用

  • 刚部署/重启完 Mobius 后端,需要确认服务正常
  • 用户反馈"系统好像坏了"、"打不开"、"接口报错"
  • 用户要求"跑个自检"、"检查下服务"
  • 自我迭代修改后端代码后,验证没有破坏基本功能

触发方式

1. CLI(服务器上直接跑)
bash
cd /app/mobius
npm run test:self-test

带写往返(建 memory → 列 memory → 删 memory):

bash
MOBIUS_SELF_TEST_WRITE=1 npm run test:self-test
2. HTTP 端点(agent/网页可触发)
bash
curl -sS http://localhost:33316/api/admin/self-test \
-H "Authorization: Bearer <admin-token>"

怎么看结果

  • ✅ = 通过,❌ = 失败,⏭ = 跳过
  • 末行 SELF_TEST_JSON 包含完整 JSON 报告
  • 部署后自检日志:/data/logs/self-test.log
  • 全 ✅ 且 exit 0 = 系统正常
  • 有 ❌ → 逐个检查失败项的错误信息

检查项目

#类别端点说明
1健康GET /api/health{"status":"ok"}
2健康GET /api/v2/health版本信息
3鉴权GET /api/auth/config认证配置
4鉴权GET /api/auth/mesystem token
5核心读GET /api/projects项目列表
6核心读GET /api/sessions/model-options模型列表
7核心读GET /api/tasks/recent最近任务
8核心读GET /api/extensions扩展列表
9搜索GET /api/search?q=test全局搜索
10群聊GET /api/conversations群聊列表
11会话GET /api/sessions?limit=5会话列表
12语音GET /api/assistant/tts/voicesTTS 配置
13上传POST /api/upload文件上传 (仅 write)
14SSEGET /api/sessions/:id/events流式连接 + 首事件
15写POST→DELETE /api/memories往返 (仅 write)

部署后自动自检

server.js 启动后自动跑(MOBIUS_SELF_TEST_ON_BOOT=0 可关闭):

  • 延迟 5s(等 server 完全就绪)
  • 结果 append 到 /data/logs/self-test.log
  • 失败绝不阻塞/崩 server

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
208
Repository forks
8
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/nutshellai-tech/mobius/mobius-self-test/badge)](https://verified-skill.com/skills/nutshellai-tech/mobius/mobius-self-test)

Something wrong with this skill or its page? Tell us.