Macro Ray

What an agent can do with the note-curator corpus

Huayudong/note-curator: note-curator（给人看的笔记插件）：把网页链接和本地草稿整理成结构化中文/英文笔记，归档进 Obsidian。全库查重合并、自动双链、学习你的文风、去 AI 腔。支持 ZCode / Claude Code / Codex。

• Look up how note-curator implements agent-skills, claude-code, note-taking, with answers cited to file and line.
• Reuse a worked example: the commit “deepen Chinese style pack with AI-tell detection and zh-specifi…” (4 files · Python).
• Answer from note-curator's real Python source instead of memory (AI, prompts and agents).

• How does note-curator implement agent-skills?
• What does plugins do in note-curator?

Search the GitHub repository Huayudong/note-curator with XERJ (https://hub.xerj.org/corpus/huayudong--note-curator).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/Huayudong/note-curator note-curator && git -C note-curator checkout 32a78925051c761d3470e81b6649dbf59f300ed0
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./note-curator --url http://127.0.0.1:9200 --prefix note-curator --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

corpus huayudong--note-curator · AI, prompts and agents
Related corpora: gorilla, promptify, DavidLam-oss/wechat-writing-team, ravidsrk/open-fleet
AI search and retrieval with XERJ · Case study: reference coding for agents