/latest
Get the latest paper submissions for a specific arXiv category.
> /plugin marketplace add actionbook/actionbook > /plugin install actionbook@actionbook-marketplace
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/latest
Context preview
What this command does when you run it.
Get the latest paper submissions for a specific arXiv category.
Command definition
latest.md/arxiv-viewer:latest
Get the latest paper submissions for a specific arXiv category.
Usage
/arxiv-viewer:latest <category> [--max <n>]
Parameters
- `category` (required): arXiv category code (e.g., `cs.CL`, `cs.AI`, `cs.LG`)
- `--max` or `-m` (optional): Maximum papers to return (default: 10)
Examples
/arxiv-viewer:latest cs.CL # Latest NLP papers
/arxiv-viewer:latest cs.AI --max 20 # Latest 20 AI papers
/arxiv-viewer:latest stat.ML # Latest statistical ML papers
Workflow
Uses **Actionbook + agent-browser** to scrape arxiv.org:
1. `search_actions("arxiv list recent")` → get action ID 2. `get_action_by_id(action_id)` → get page selectors 3. `agent-browser open https://arxiv.org/list/{category}/recent` 4. `agent-browser get text <paper_list_selector>` 5. Parse and return paper list
Output Format
## Latest Papers in {category}
### Today's Submissions ({date})
1. **{Title}** (arXiv:{id})
Authors: {author list}
[Abstract](url) | [PDF](url) | [HTML](url)
2. **{Title}** (arXiv:{id})
Authors: {author list}
[Abstract](url) | [PDF](url) | [HTML](url)
...Common Categories
| Code | Field | |------|-------| | `cs.AI` | Artificial Intelligence | | `cs.CL` | Computation and Language (NLP) | | `cs.CV` | Computer Vision | | `cs.LG` | Machine Learning | | `cs.SE` | Software Engineering | | `stat.ML` | Statistical ML |
Read more
/arxiv-viewer:latest
Get the latest paper submissions for a specific arXiv category.
Usage
/arxiv-viewer:latest <category> [--max <n>]
Parameters
- `category` (required): arXiv category code (e.g., `cs.CL`, `cs.AI`, `cs.LG`)
- `--max` or `-m` (optional): Maximum papers to return (default: 10)
Examples
/arxiv-viewer:latest cs.CL # Latest NLP papers /arxiv-viewer:latest cs.AI --max 20 # Latest 20 AI papers /arxiv-viewer:latest stat.ML # Latest statistical ML papers
Workflow
Uses **Actionbook + agent-browser** to scrape arxiv.org:
1. `search_actions("arxiv list recent")` → get action ID 2. `get_action_by_id(action_id)` → get page selectors 3. `agent-browser open https://arxiv.org/list/{category}/recent` 4. `agent-browser get text <paper_list_selector>` 5. Parse and return paper list
Output Format
## Latest Papers in {category}
### Today's Submissions ({date})
1. **{Title}** (arXiv:{id})
Authors: {author list}
[Abstract](url) | [PDF](url) | [HTML](url)
2. **{Title}** (arXiv:{id})
Authors: {author list}
[Abstract](url) | [PDF](url) | [HTML](url)
...Common Categories
| Code | Field | |------|-------| | `cs.AI` | Artificial Intelligence | | `cs.CL` | Computation and Language (NLP) | | `cs.CV` | Computer Vision | | `cs.LG` | Machine Learning | | `cs.SE` | Software Engineering | | `stat.ML` | Statistical ML |
Actionbook turns the websites you work in every day into something your AI agent can actually operate. Direct API requests when possible, UI automation when not, with login handled. Fast and resilient.
Other commands on actionbook.
- /analyze
Analyze a webpage's structure using Actionbook's verified selectors and show available elements for scraping.
Open command - /generate
Generate web scraper scripts using Actionbook's verified selectors.
Open command - /list-sources
List all websites that have verified selector data in Actionbook.
Open command - /request-website
Request a new website to be indexed in Actionbook by submitting its URL through the request form.
Open command - /citations
Extract the bibliography/references from an arXiv paper (ar5iv.org).
Open command - /download
Download an arXiv paper PDF to local directory.
Open command

