Paper Claw
Fetch, classify and summarize arXiv papers into daily digests
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 24, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Jul 30, 2026 · b8d2bda
⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 24, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.
Ran the full pipeline live for one day against the arXiv API: it fetched 8 real speech/audio papers, deduplicated and keyword-classified them (ASR 2, TTS 2, Audio 3), and wrote a clean 21KB structured Markdown digest with real abstracts and readability notes. The headline 'AI-powered multi-language summaries' degrade to templated English when no LLM key is set (verified: the rule-based fallback fires and produces generic per-paper blurbs). Real friction: the skill/ dir alone doesn't run because its scripts assume the full repo as working directory, so you must clone the whole repo, pip install requirements, and supply SMTP creds for email plus an LLM key for translated summaries. All network calls hit only official arXiv and LLM-provider endpoints and configured SMTP recipients, with no exfiltration.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 4/5
What Paper Claw does
A multi-source paper digest pipeline that fetches recent papers from arXiv (170+ categories), deduplicates and keyword-classifies them, generates summaries with a multi-provider LLM fallback chain, and delivers HTML+Markdown digests by email. Triggers when you want to fetch, classify, or summarize research papers or set up an automated daily paper digest.
How to install Paper Claw
Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.
Commands — how to trigger Paper Claw
-
/paper-clawFetch, classify and summarize arXiv papers into daily digests
It also activates on plain-language prompts like these:
-
Set up a daily arXiv digest for my research categories -
Fetch and summarize recent papers on transformer efficiency -
Classify today's new cs.CL papers into a digest email
Frequently asked questions
- Is the Paper Claw skill free?
- Yes. The skill itself is free from PigeonDan1/paper_claw. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Paper Claw work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 24, 2026. Verdict: Works with setup. Ran the full pipeline live for one day against the arXiv API: it fetched 8 real speech/audio papers, deduplicated and keyword-classified them (ASR 2, TTS 2, Audio 3), and wrote a clean 21KB structured Markdown digest with real abstracts and readability notes. The headline 'AI-powered multi-language summaries' degrade to templated English when no LLM key is set (verified: the rule-based fallback fires and produces generic per-paper blurbs). Real friction: the skill/ dir alone doesn't run because its scripts assume the full repo as working directory, so you must clone the whole repo, pip install requirements, and supply SMTP creds for email plus an LLM key for translated summaries. All network calls hit only official arXiv and LLM-provider endpoints and configured SMTP recipients, with no exfiltration.
- What is the Paper Claw SkillProof Score?
- 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
- How do I install Paper Claw?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Paper Claw with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.