メニュー
Monitor new papers on arXiv by category. Use when user wants to check latest papers, track research topics, or manage reading lists. Trigger phrases: "check arxiv", "new papers", "arxiv category", "watch arxiv", "latest papers on".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Skill for interacting with the Lean-Claw Arena to prove math theorems using Lean 4.
"PDF to Markdown - PDF文本转Markdown工具. Use when you need pdf to markdown capabilities. Triggers on: pdf to markdown."
"Short Drama Writer. Use when you need short drama writer capabilities. Triggers on: short drama writer."
Personal knowledge base for capturing and retrieving information about people, places, restaurants, games, tech, events, media, ideas, and organizations. Use when: user mentions a person, place, restaurant, landmark, game, device, event, book/show, idea, or company. Trigger phrases: "remember", "note that", "met this person", "visited", "played", "what do I know about", etc. Brain entries take precedence over daily logs for named entities.
Analyze any GitHub repository in AI-friendly format. Convert entire repos to single markdown documents, generate architecture diagrams with Mermaid, inspect structure trees, language breakdowns, and recent activity. Includes GitHub URL tricks, API shortcuts, and advanced search techniques. Read-only analysis — never executes code from repositories. Built for AI agents — Python stdlib only, no dependencies. Use for repository analysis, code architecture review, open source research, GitHub intelligence, repo documentation, and codebase understanding.
Use this skill when users need to search academic papers, download research documents, extract citations, or gather scholarly information. Triggers include: requests to "find papers on", "search research about", "download academic articles", "get citations for", or any request involving academic databases like arXiv, PubMed, Semantic Scholar, or Google Scholar. Also use for literature reviews, bibliography generation, and research discovery. Requires OpenClawCLI installation from clawhub.ai.
Monitor and track new papers on arXiv.org by category.
This skill helps you:
# Check latest papers in a category
/arxiv-watcher cs.AI
# Multiple categories
/arxiv-watcher cs.AI cs.CL cs.LG
# View starred papers
/arxiv-watcher --starred
| Category | Description |
|---|---|
| cs.AI | Artificial Intelligence |
| cs.CL | Computation and Language |
| cs.CV | Computer Vision |
| cs.LG | Machine Learning |
| cs.NE | Neural and Evolutionary Computing |
| cs.RO | Robotics |
| cs.SE | Software Engineering |
| Category | Description |
|---|---|
| astro-ph | Astrophysics |
| cond-mat | Condensed Matter |
| hep-ex | High Energy Physics - Experiment |
| hep-th | High Energy Physics - Theory |
| quant-ph | Quantum Physics |
| Category | Description |
|---|---|
| math.AG | Algebraic Geometry |
| math.CO | Combinatorics |
| math.DG | Differential Geometry |
| math.NT | Number Theory |
| math.ST | Statistics Theory |
| Category | Description |
|---|---|
| stat.ML | Machine Learning |
| stat.TH | Statistics Theory |
Full category list: https://arxiv.org/category_taxonomy
python scripts/arxiv_watcher.py fetch <category> [--limit N]
Fetches recent papers from arXiv. Outputs Markdown format with:
python scripts/arxiv_watcher.py star <arxiv_id>
Adds a paper to starred list for later reference.
python scripts/arxiv_watcher.py unstar <arxiv_id>
Removes a paper from starred list.
python scripts/arxiv_watcher.py starred
Lists all starred papers with their details.
Papers are displayed in Markdown format:
## [2403.12345] Paper Title Here
**Authors:** John Doe, Jane Smith
**Category:** cs.AI
**Submitted:** 2024-03-15
**Abstract:**
This paper presents a novel approach to...
**Links:**
- arXiv: https://arxiv.org/abs/2403.12345
- PDF: https://arxiv.org/pdf/2403.12345.pdf
---
Starred papers include a ⭐ marker for easy identification.
When user asks to check arXiv:
arxiv_watcher.py fetch <category>User: "check new papers in cs.AI"
Assistant: Runs fetch command, displays 5-10 recent papers, asks if any should be starred.
User: "star the second one"
Assistant: Parses the arxiv_id from previous output, runs star command, confirms action.
User: "show my starred papers"
Assistant: Runs starred command, displays list with details.
arxiv_watcher.py - Main CLI for fetching and managing papersstarred.json - Persistent storage for starred papers (auto-created)