hud-skill
Skill0 starsChanged 6 months agoMITView on GitHub
配置和管理 Claude Code 底部常驻 HUD 状态栏。显示 CPU、内存、磁盘、温度、天气、Git 分支、时间、中文语录。支持彩色显示、自定义内容。关键词:hud、状态栏、statusline、底部显示、系统监控、语录、天气、彩色。
In this repository16 other files it gives its agents.
- agent-skill-creatorSkill
- brainstormingSkill
- concise-response-skillSkill
- executing-plansSkill
- find-skillsSkill
- finishing-a-development-branchSkill
- frontend-designSkill
- karpathy-guidelinesSkill
- obra/superpowers@subagent-driven-developmentSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- ui-ux-pro-maxSkill
- using-git-worktreesSkill
- verification-before-completionSkill
- web-accessSkill
- writing-plansSkill
The file
Files
/hud-skill — Claude Code 底部 HUD 状态栏
你是一个 HUD 配置管理技能。你的职责是帮助用户管理和自定义 Claude Code 聊天界面底部的常驻 HUD 状态栏,以及显示系统状态信息。
状态栏脚本位置: ~/.claude/plugins/claude-hud-status.sh
采集脚本位置: ~/.claude/skills/hud-skill/scripts/hud_collector.py
子命令
| 命令 | 功能 |
/hud-skill | 显示完整 HUD 面板(三行彩色) |
/hud-skill show | 显示完整 HUD 面板预览 |
/hud-skill line | 单行彩色状态(用于 statusLine) |
/hud-skill quote | 随机中文语录(彩虹色) |
/hud-skill weather | 查看天气信息 |
/hud-skill customize | 自定义 HUD 显示内容 |
/hud-skill status | 检查 HUD 是否正常运行 |
显示效果
默认 HUD 面板(/hud-skill show):
┌─ HUD 状态面板 ─────────────────────────────
│ deepseek-v4-flash Windows 11 10.0.26100
│ CPU:0.32 MEM:2427M/7896M DISK:17G/98G 24°C 晴 [main] 20:14
│ 身是菩提树,心如明镜台,时时勤拂拭,勿使惹尘埃。 ——神秀
└───────────────────────────────────────────状态栏单行(statusLine):
deepseek-v4-flash CPU:0.32 MEM:2427M/7896M DISK:17G/98G 24°C 晴 [main] 20:14各组件颜色:CPU 粉色、MEM 绿色/黄/红(阈值)、DISK 黄色、温度橙色、天气紫色、Git 蓝色、时间青色、语录彩虹逐字。
实现
配置位于 ~/.claude/settings.json 的 statusLine.command:
"statusLine": {
"command": "bash ~/.claude/plugins/claude-hud-status.sh",
"type": "command"
}Windows 路径应使用正斜线:
"statusLine": {
"command": "bash /c/Users/YBY/.claude/plugins/claude-hud-status.sh",
"type": "command"
}依赖
- Python 3(核心采集脚本)
- Git(分支检测)
- curl(天气和语录 API)
- 网络连接(天气、语录需要联网)
来源
Linux 原版来自 Arch Linux 配置,经适配后支持 Windows/MSYS2/Git Bash。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

