// CLI tool (arxivterminal) for fetching, searching, and managing arXiv papers locally. Use when working with arXiv papers using the arxivterminal command - fetching new papers by category, searching the local database, viewing papers from specific dates, or managing the local paper database.
Fetch arXiv papers by date range and topics, rank them for research value, and produce introduction digests. Use when the user wants a literature sweep, daily or weekly paper triage, or a written overview of the best papers in a niche — without relying on the arxivterminal local database.
Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.
AI paper reviewer. Use when the user says 'review my paper', 'help me review this paper', '审稿', 'give me feedback on my paper', 'check my manuscript', 'evaluate this paper for NeurIPS/ICLR/EuroSys'. Accepts PDF files and produces structured narrative reviews with venue-specific dimensional scores and Accept/Reject recommendation.
Convert a local paper PDF to structured Markdown and export all figures as PNG + SVG + drawio. Attempts editable figure reconstruction via the built-in autofigure pipeline (SAM3 → RMBG-2.0 → VLM → SVG), falling back to a layered-SVG wrapper when API keys are unavailable. Use when the user wants to parse a paper PDF, extract its text as Markdown, or get editable/exportable figure assets.
Convert raster figure images into editable DrawIO files using SAM3 segmentation, RMBG-2.0 background removal, and multimodal LLM drawio generation.
Autonomous ML research loop — modify train.py, run 5-min GPU experiments, track val_bpb, iterate overnight. Invoke when the user wants to run self-directed architecture search on the autoresearch repo.
| name | arxivterminal |
| description | CLI tool (arxivterminal) for fetching, searching, and managing arXiv papers locally. Use when working with arXiv papers using the arxivterminal command - fetching new papers by category, searching the local database, viewing papers from specific dates, or managing the local paper database. |
| metadata | {"clawphd":{"emoji":"📚","requires":{"bins":["arxiv"]},"install":["pip install arxivterminal && pip install 'arxiv>=2.0' 'pydantic>=2.0'"]}} |
CLI tool for managing arXiv papers with local database storage.
Dependency note:
arxivterminalpinsarxiv<2.0.0andpydantic<2.0.0, but both must be overridden. Install with:pip install arxivterminal && pip install 'arxiv>=2.0' 'pydantic>=2.0'
arxiv fetch --num-days N --categories CATEGORIES
This is non-interactive and safe to call directly. See arxivterminal-fetch.md for details.
Use the bundled non-interactive search script (the arxiv search CLI is interactive and will hang):
python SKILL_DIR/scripts/arxiv_search.py "QUERY" -l 10
Replace SKILL_DIR with the directory containing this SKILL.md (derive from the <location> field).
arxiv stats
arxiv delete-all — clear all papersPaths are platform-dependent (uses appdirs):
~/.local/share/arxivterminal/papers.db~/Library/Application Support/arxivterminal/papers.dbFor programmatic date-range + topic fetch, scoring, and digests inside ClawPhD, use the three tools documented in the paper-scout skill:
arxiv_fetch_range — Atom API, optional keyword OR-query + categories + submittedDate windowarxiv_rank_papers — enhanced metadata heuristic + Semantic Scholar/OpenAlex enrichment + optional batch LLM refinementarxiv_paper_digest — introduction report for the selected papers using ranking rationale when availableUse arxivterminal when you need a persistent SQLite corpus (arxiv fetch, arxiv_search.py). Use paper-scout tools when you want a one-shot pipeline without populating the DB.
arxiv fetch --num-days 1 --categories cs.AI,cs.CL
python SKILL_DIR/scripts/arxiv_search.py "large language models" -l 20
arxiv fetch --num-days 7 --categories cs.AI,cs.LG,cs.CV
arxiv stats