alphaXiv
Looks up a single arXiv paper and returns an LLM-optimized summary.
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 12, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 7a4c062
Verbatim single-skill install parses clean (strict-YAML frontmatter, no API key); the skill ran live against alphaxiv.org (curl overview/{id}.md, HTTP 200) and returned a genuine LLM-optimized summary. One harmless gap: SKILL.md links ../shared-references/integration-contract.md, not copied by the card's single-skill cp, but it is only referenced by the optional research-wiki ingest step, which self-guards on a missing research-wiki/ dir and exits silently. A/B on arXiv 1706.03762 was a wash: alphaxiv's endpoint supplied richer community-layer detail, but because the paper is canonical the base plain-arXiv arm produced an equally accurate, well-structured summary, so the skill's edge was masked on this well-known target.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 4/5
- Triggers reliably 4/5
- Output vs. baseline 5/10
- Docs & honesty 4/5
What alphaXiv does
Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.
How to install alphaXiv
git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep
cd Auto-claude-code-research-in-sleep
mkdir -p ~/.claude/skills
cp -r skills/alphaxiv ~/.claude/skills/alphaxiv
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger alphaXiv
-
/alphaxivLooks up a single arXiv paper and returns an LLM-optimized summary.
It also activates on plain-language prompts like these:
-
Explain this arXiv paper in plain terms -
Summarize this AlphaXiv paper for me -
What does this arXiv ID's paper actually claim
Frequently asked questions
- Is the alphaXiv skill free?
- Yes. The skill itself is free from wanshuiyin/Auto-claude-code-research-in-sleep. SkillProof publishes the install command and an independent test verdict at no cost.
- Does alphaXiv work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 12, 2026. Verdict: Works with setup. Verbatim single-skill install parses clean (strict-YAML frontmatter, no API key); the skill ran live against alphaxiv.org (curl overview/{id}.md, HTTP 200) and returned a genuine LLM-optimized summary. One harmless gap: SKILL.md links ../shared-references/integration-contract.md, not copied by the card's single-skill cp, but it is only referenced by the optional research-wiki ingest step, which self-guards on a missing research-wiki/ dir and exits silently. A/B on arXiv 1706.03762 was a wash: alphaxiv's endpoint supplied richer community-layer detail, but because the paper is canonical the base plain-arXiv arm produced an equally accurate, well-structured summary, so the skill's edge was masked on this well-known target.
- What is the alphaXiv SkillProof Score?
- 6.8/10 — installs cleanly 4/5, triggers reliably 4/5, output vs. baseline 5/10, docs & honesty 4/5.
- How do I install alphaXiv?
- 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 alphaXiv 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.