Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
- GitHub 星标
- 43
- 许可证
- Apache-2.0
- 收录日期
- 2026-08-11
GitHub 信息
- GitHub 星标
- 43
- 许可证
- Apache-2.0
- 主要语言
- Python
- 最近推送
- 2026年8月21日 04:44
- 维护者
- EverMind-AI
- 收录日期
- 2026-08-11
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）。
OpenClaw
https://github.com/user-attachments/assets/01d948fe-1e2b-48e8-9b32-b8057cb3f336
Raven
https://github.com/user-attachments/assets/27e1ea63-69d4-48b3-a884-7f0355926907
Hermes
https://github.com/user-attachments/assets/477eebc4-e615-4425-921e-368d7667e491
WorkBuddy
https://github.com/user-attachments/assets/ab2157dc-90fc-4196-bbf3-87066820f7b4
安装
dsh plugin --profile web add github:EverMind-AI/SkillCorpus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/EverMind-AI/SkillCorpus)相关插件
开发与运行时memsearch
★ 2531A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
memtrace-public
★ 467Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.
causal-memory
★ 51Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.