A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-performance systems.
- GitHub 星标
- 143
- 收录日期
- 2026-01-07
GitHub 信息
- GitHub 星标
- 143
- 主要语言
- Python
- 最近推送
- 2026年7月9日 09:35
- 维护者
- yzlnew
- 收录日期
- 2026-01-07
README 演示图
从仓库 README 提取的截图/GIF（已过滤徽章、头像等装饰图）。
Anthropic Theme Flowchart Review Demo
https://raw.githubusercontent.com/yzlnew/infra-skills/main/gallery/anthropic_theme_flowchart_review_demo.png
DeepSeek-V4-Flash Architecture
https://raw.githubusercontent.com/yzlnew/infra-skills/main/hf-architecture-tikz/examples/deepseek-v4-flash/deepseek-v4-flash.png
TikZ Flowchart Anthropic Theme
https://raw.githubusercontent.com/yzlnew/infra-skills/main/gallery/tikz_flowchart_anthropic_theme.png
安装
dsh plugin --profile web add github:yzlnew/infra-skills标签
README 徽章
将这段 Markdown 添加到插件 README，链接到对应的详情页。
[](https://dshget.com/plugins/yzlnew/infra-skills)相关插件
开发与运行时EverOS
★ 12559One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
dashi-taskboard
★ 2781现代化可灵活嵌入的任务面板，支持 Codex、DeepSeek Harness
memsearch
★ 2531A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.