Initial commit with translated description

This commit is contained in:
2026-03-29 13:19:42 +08:00
commit 02636af205
3 changed files with 50 additions and 0 deletions

38
SKILL.md Normal file
View File

@@ -0,0 +1,38 @@
---
name: arxiv-watcher
description: "搜索和总结ArXiv论文。"
---
# ArXiv Watcher
This skill interacts with the ArXiv API to find and summarize the latest research papers.
## Capabilities
- **Search**: Find papers by keyword, author, or category.
- **Summarize**: Fetch the abstract and provide a concise summary.
- **Save to Memory**: Automatically record summarized papers to `memory/RESEARCH_LOG.md` for long-term tracking.
- **Deep Dive**: Use `web_fetch` on the PDF link to extract more details if requested.
## Workflow
1. Use `scripts/search_arxiv.sh "<query>"` to get the XML results.
2. Parse the XML (look for `<entry>`, `<title>`, `<summary>`, and `<link title="pdf">`).
3. Present the findings to the user.
4. **MANDATORY**: Append the title, authors, date, and summary of any paper discussed to `memory/RESEARCH_LOG.md`. Use the format:
```markdown
### [YYYY-MM-DD] TITLE_OF_PAPER
- **Authors**: Author List
- **Link**: ArXiv Link
- **Summary**: Brief summary of the paper and its relevance.
```
## Examples
- "Busca los últimos papers sobre LLM reasoning en ArXiv."
- "Dime de qué trata el paper con ID 2512.08769."
- "Hazme un resumen de las novedades de hoy en ArXiv sobre agentes."
## Resources
- `scripts/search_arxiv.sh`: Direct API access script.