← Back to Skills

arxiv-paper-search

v1.0.0 approved Knowledge updated today
USK v3 ✅ Verified ⚡ Auto-Convert
⬇ Download
Install Guide↓
🤖 Agent install commands (curl / MCP / Claude Desktop)
▸ curl one-liner
curl -L -o arxiv-paper-search.skill   "https://aiskillstore.io/v1/agent/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/download?platform=ClaudeCode"
▸ MCP tool call (after registering Skill Store MCP)
{
  "tool": "download_skill",
  "arguments": {
    "skill_id": "6e175fda-3f84-4688-bbcb-d577bf79be31",
    "platform": "ClaudeCode"
  }
}
▸ Claude Desktop / Cursor MCP config (one-time)
{
  "mcpServers": {
    "skill-store": {
      "url": "https://aiskillstore.io/mcp/"
    }
  }
}
📖 Full agent API guide: /llms.txt  ·  MCP server card

Search arXiv preprints (CS/AI/physics/math/economics) and return structured metadata — title, authors, abstract, DOI, categories, PDF URL — as JSON.

# arxiv # academic # research # preprint # paper-search # literature

Basic Info

Owner 👤 aiskillstore-team Category Knowledge Registered 2026-06-26 Last Updated 2026-06-26 Latest Version 1.0.0 Packaged At 2026-06-26 Vetting Status approved Downloads 0 Checksum (SHA256) 544f8f2715f54de21cd0622674695fd512708354155755054f4284ae687bf894

⚡ AGENT INFO USK v3

Capabilities
arxiv_search academic_literature paper_metadata research_discovery preprint_access
Permissions
✓ network
✗ filesystem
✗ subprocess
Interface
type: cli   entry_point: main.py   runtime: python3   call_pattern: stdin_stdout
Agent API
# 스킬 스키마 조회 (에이전트가 호출 방법을 파악) GET /v1/agent/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/schema # 플랫폼별 자동 변환 다운로드 GET /v1/agent/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/download?platform=OpenClaw GET /v1/agent/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/download?platform=ClaudeCode GET /v1/agent/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/download?platform=ClaudeCodeAgentSkill GET /v1/agent/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/download?platform=Cursor GET /v1/agent/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/download?platform=GeminiCLI GET /v1/agent/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/download?platform=CodexCLI GET /v1/agent/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/download?platform=CustomAgent

Installation

Compatible Platforms any

1
Install the skill using openclaw_skill_manager.py.
python openclaw_skill_manager.py --install arxiv-paper-search
2
Verify installation
python openclaw_skill_manager.py --list-installed
3
Install a specific version (optional)
python openclaw_skill_manager.py --install arxiv-paper-search --version 1.0.0
1
Download the skill package.
curl -O https://aiskillstore.io/v1/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/download
2
Place it in the Claude Code commands directory.
unzip arxiv-paper-search.skill -d ~/.claude/commands/arxiv-paper-search/
3
Use it as a slash command in Claude Code.
/arxiv-paper-search
1
Download the Agent Skills package.
curl -O https://aiskillstore.io/v1/agent/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/download?platform=ClaudeCodeAgentSkill
2
Unzip it into the Claude Code skills directory.
unzip arxiv-paper-search-agent-skill-*.skill -d ~/.claude/skills/arxiv-paper-search/
3
Restart Claude Code — the skill is auto-loaded at session start. No slash command needed.
1
Download the Cursor-converted package.
curl -O https://aiskillstore.io/v1/agent/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/download?platform=Cursor
2
Unzip and place it in a permanent location.
unzip arxiv-paper-search-cursor-*.skill -d ~/.cursor/skills/arxiv-paper-search/
3
Add the MCP server config to .cursor/mcp.json, then restart Cursor.
cat ~/.cursor/skills/arxiv-paper-search/cursor_mcp_config.json
1
Download the Gemini CLI-converted package.
curl -O https://aiskillstore.io/v1/agent/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/download?platform=GeminiCLI
2
Unzip and place it in a permanent location.
unzip arxiv-paper-search-geminicli-*.skill -d ~/.gemini/skills/arxiv-paper-search/
3
Add the MCP server config to ~/.gemini/settings.json, then restart Gemini CLI.
cat ~/.gemini/skills/arxiv-paper-search/gemini_settings_snippet.json
1
Download the Codex CLI-converted package.
curl -O https://aiskillstore.io/v1/agent/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/download?platform=CodexCLI
2
Unzip and place it in a permanent location.
unzip arxiv-paper-search-codexcli-*.skill -d ~/.codex/skills/arxiv-paper-search/
3
Add the MCP server config to ~/.codex/config.toml, then restart Codex CLI.
cat ~/.codex/skills/arxiv-paper-search/codex_config_snippet.toml
1
Download the skill package via REST API.
GET https://aiskillstore.io/v1/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/download
2
Place it in your agent platform's skills directory.
cp arxiv-paper-search.skill ./skills/
3
Fetch platform-specific details via the Install Guide API.
GET https://aiskillstore.io/v1/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/install-guide?platform=CustomAgent

Security Vetting Report

Vetting Result APPROVED

Findings: ["메타데이터 경고: 권장 필드 없음: 'requirements' (SKILL.md v2 권장)", "메타데이터 경고: 권장 필드 없음: 'changelog' (SKILL.md v2 권장)"]

✅ No security risks found.

AI Review Stage

Reviewer gemini Risk Level 🟢 Low Review Summary arXiv 논문 검색 스킬은 선언된 권한 내에서 arXiv API를 안전하게 호출하며, 악의적인 코드나 무단 데이터 수집 없이 안정적으로 동작합니다.
Reasoning

1. **선언된 permissions(network/filesystem/subprocess)과 실제 코드가 일치하는가?** - 메타데이터에 `network: true`가 선언되어 있으며, 코드(`main.py`)는 `arxiv` 라이브러리를 사용하여 arXiv API에 네트워크 요청을 보냅니다. 이는 선언된 권한과 일치합니다. - `filesystem: false`, `subprocess: false`로 선언되어 있으며, 코드 분석 결과 파일 시스템에 대한 쓰기 작업이나 외부 프로세스 실행은 발견되지 않았습니다. `os` 모듈은 스크립트 경로 확인 등 제한적인 용도로만 사용됩니다. 2. **악의적 목적의 코드가 있는가? (데이터 탈취, 시스템 파괴, 난독화 등)** - 코드는 사용자로부터 JSON 입력을 받아 arXiv API 쿼리를 구성하고, 그 결과를 JSON 형태로 표준 출력으로 반환하는 명확한 목적을 가집니다. - 데이터 탈취, 시스템 파괴, 난독화 등 악의적인 목적을 가진 코드는 발견되지 않았습니다. 사용되는 `arxiv` 라이브러리는 학술 API 접근을 위한 표준적이고 신뢰할 수 있는 패키지입니다. 3. **선언되지 않은 외부 통신이 있는가?** - `network: true` 권한이 선언되었고, 코드에서 `arxiv` 라이브러리를 통해 arXiv API로의 통신만 확인됩니다. 그 외의 다른 외부 서버로의 통신 시도는 발견되지 않았습니다. 4. **사용자 데이터를 무단으로 수집하거나 전송하는가?** - 스킬은 표준 입력으로 받은 사용자 쿼리 파라미터를 arXiv API 호출에만 사용하며, 이를 외부에 저장하거나 무단으로 제3자에게 전송하는 코드는 존재하지 않습니다. 5. **코드 품질이 스킬의 목적과 일치하는가?** - 입력 유효성 검사(쿼리 내용, `max_results` 범위, `sort_by` 값, 카테고리 형식, 날짜 형식)가 철저하게 구현되어 있습니다. - 오류 처리 로직(`err` 함수)이 명확하며, 발생 가능한 오류에 대해 상세한 메시지와 함께 구조화된 JSON 응답을 제공합니다. - `main.py`와 `lib/search.py`로 기능이 잘 분리되어 있어 코드 구조가 명확하고 가독성이 높습니다. - `arxiv` 라이브러리 의존성 확인 및 안내 메시지가 포함되어 있어 사용자 경험을 고려했습니다. - 정적 분석 결과에서도 어떠한 위험 요소나 난독화, 금지된 실행 파일이 발견되지 않아 코드의 안전성과 품질이 검증되었습니다.

Version History

Version USK v3 Vetting Status Packaged At Downloads Changelog
v1.0.0 approved 2026-06-26 ⬇ 0

Examples 6

Representative input/output examples for this skill. Agents can use these to understand how to invoke the skill and what output to expect.

LLM alignment — latest preprints
# cs.AI# cs.CL# alignment# sort-by-date

Search for recent papers on large language model alignment in cs.AI and cs.CL, sorted by submission date.

📥 Input
{
  "categories": [
    "cs.AI",
    "cs.CL"
  ],
  "max_results": 10,
  "query": "large language model alignment",
  "sort_by": "submittedDate"
}
📤 Output
{
  "papers": [
    {
      "abstract": "We present a scalable oversight framework for aligning large language models with human preferences...",
      "abstract_url": "https://arxiv.org/abs/2406.11111",
      "arxiv_id": "2406.11111",
      "authors": [
        "Alice Smith",
        "Bob Jones"
      ],
      "categories": [
        "cs.AI",
        "cs.CL"
      ],
      "doi": null,
      "pdf_url": "https://arxiv.org/pdf/2406.11111",
      "published": "2026-06-01T00:00:00Z",
      "title": "Scalable Oversight for Language Model Alignment",
      "updated": "2026-06-10T00:00:00Z"
    }
  ],
  "query_used": "(cat:cs.AI OR cat:cs.CL) AND large language model alignment AND submittedDate:[202601010000 TO 202612312359]",
  "total_found": 10
}
Attention Is All You Need — metadata lookup
# title-search# transformer# classic-paper

Retrieve metadata for the Transformer paper by title search.

📥 Input
{
  "max_results": 3,
  "query": "ti:Attention Is All You Need",
  "sort_by": "relevance"
}
📤 Output
{
  "papers": [
    {
      "abstract": "The dominant sequence transduction models are based on complex recurrent or convolutional neural networks...",
      "abstract_url": "https://arxiv.org/abs/1706.03762",
      "arxiv_id": "1706.03762",
      "authors": [
        "Ashish Vaswani",
        "Noam Shazeer",
        "Niki Parmar"
      ],
      "categories": [
        "cs.CL",
        "cs.LG"
      ],
      "doi": null,
      "pdf_url": "https://arxiv.org/pdf/1706.03762",
      "published": "2017-06-12T00:00:00Z",
      "title": "Attention Is All You Need",
      "updated": "2023-08-02T00:00:00Z"
    }
  ],
  "query_used": "ti:Attention Is All You Need",
  "total_found": 3
}
Reward hacking — papers since 2026
# date-filter# rlhf# safety

Find preprints on reward hacking submitted after January 2026.

📥 Input
{
  "date_from": "2026-01-01",
  "max_results": 10,
  "query": "reward hacking",
  "sort_by": "submittedDate"
}
📤 Output
{
  "papers": [
    {
      "abstract": "Reward hacking remains a key challenge in reinforcement learning from human feedback...",
      "abstract_url": "https://arxiv.org/abs/2602.09999",
      "arxiv_id": "2602.09999",
      "authors": [
        "Carol Lee"
      ],
      "categories": [
        "cs.LG",
        "cs.AI"
      ],
      "doi": null,
      "pdf_url": "https://arxiv.org/pdf/2602.09999",
      "published": "2026-02-15T00:00:00Z",
      "title": "Reward Hacking in RLHF: An Empirical Study",
      "updated": "2026-02-15T00:00:00Z"
    }
  ],
  "query_used": "reward hacking AND submittedDate:[202601010000 TO 99991231235959]",
  "total_found": 8
}
Causal inference — statistics and ML
# statistics# causal# multi-category

Search causal inference papers across math.ST and stat.ML, returning up to 20 results.

📥 Input
{
  "categories": [
    "math.ST",
    "stat.ML"
  ],
  "max_results": 20,
  "query": "causal inference",
  "sort_by": "relevance"
}
📤 Output
{
  "papers": [
    {
      "abstract": "We study causal identification and estimation under covariate shift using nonparametric models...",
      "abstract_url": "https://arxiv.org/abs/2405.00123",
      "arxiv_id": "2405.00123",
      "authors": [
        "Diana Park",
        "Ethan Wu"
      ],
      "categories": [
        "stat.ML",
        "math.ST"
      ],
      "doi": null,
      "pdf_url": "https://arxiv.org/pdf/2405.00123",
      "published": "2024-05-01T00:00:00Z",
      "title": "Nonparametric Causal Inference under Distribution Shift",
      "updated": "2024-05-01T00:00:00Z"
    }
  ],
  "query_used": "(cat:math.ST OR cat:stat.ML) AND causal inference",
  "total_found": 20
}
Author search — Yann LeCun recent papers
# author-search# deep-learning# lecun

Find recent papers authored by Yann LeCun using the au: field prefix.

📥 Input
{
  "max_results": 5,
  "query": "au:LeCun_Y",
  "sort_by": "submittedDate"
}
📤 Output
{
  "papers": [
    {
      "abstract": "We introduce an improved joint embedding predictive architecture for learning visual representations...",
      "abstract_url": "https://arxiv.org/abs/2405.07777",
      "arxiv_id": "2405.07777",
      "authors": [
        "Yann LeCun",
        "Ishan Misra"
      ],
      "categories": [
        "cs.CV",
        "cs.LG"
      ],
      "doi": null,
      "pdf_url": "https://arxiv.org/pdf/2405.07777",
      "published": "2024-05-10T00:00:00Z",
      "title": "Joint Embedding Predictive Architecture for Self-Supervised Vision",
      "updated": "2024-05-12T00:00:00Z"
    }
  ],
  "query_used": "au:LeCun_Y",
  "total_found": 5
}
Invalid date format — error handling
# error-case# validation

Providing an incorrectly formatted date triggers INVALID_DATE_FORMAT error.

📥 Input
{
  "date_from": "2026/01/01",
  "query": "graph neural network"
}
📤 Output
{
  "error": {
    "code": "INVALID_DATE_FORMAT",
    "message": "Invalid date format: \u00272026/01/01\u0027. Expected YYYY-MM-DD."
  }
}

All examples are also available via the agent API: /v1/agent/skills/6e175fda-3f84-4688-bbcb-d577bf79be31/schema

Reviews & Ratings

No reviews yet. Be the first to leave one!

✍️ Write a Review