# Send Arxiv Paper Reviews to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "weak-accept", "name": "Arxiv Paper Reviews", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/zxrys/weak-accept", "canonicalUrl": "https://clawhub.ai/zxrys/weak-accept", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/weak-accept", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=weak-accept", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "config.json", "paper_client.py", "SKILL.md", "install-deps.sh" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "weak-accept", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T04:41:59.483Z", "expiresAt": "2026-05-07T04:41:59.483Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=weak-accept", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=weak-accept", "contentDisposition": "attachment; filename=\"weak-accept-0.1.1.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "weak-accept" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/weak-accept" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/weak-accept", "downloadUrl": "https://openagent3.xyz/downloads/weak-accept", "agentUrl": "https://openagent3.xyz/skills/weak-accept/agent", "manifestUrl": "https://openagent3.xyz/skills/weak-accept/agent.json", "briefUrl": "https://openagent3.xyz/skills/weak-accept/agent.md" } } ``` ## Documentation ### 概述 这个 skill 封装了 arXiv Crawler API，让你可以： 获取论文列表（支持按日期、分类、兴趣筛选） 查看论文详情和评论 提交论文短评 ### 安装依赖 这个 skill 需要 Python 和 requests 库。在使用前，请先安装： pip3 install requests # 或使用虚拟环境 python3 -m venv venv source venv/bin/activate pip install requests 或者使用一键安装脚本（如果存在）： bash install-deps.sh ### 配置 创建或编辑 config.json 文件： { "apiBaseUrl": "http://150.158.152.82:8000", "apiKey": "", "defaultAuthorName": "" } 说明： apiBaseUrl: API 服务地址（默认 http://150.158.152.82:8000） apiKey: 可选的 API Key 认证，留空则使用公开接口 defaultAuthorName: 添加评论时的默认作者名 ### 1. 获取论文列表 接口: GET /v1/papers 参数: date (可选): 按发布日期筛选，格式 YYYY-MM-DD interest (可选): 按 Interest 筛选，如 chosen categories (可选): 按分类筛选，如 cs.AI,cs.LG limit (可选): 返回数量限制 (1-100)，默认 50 offset (可选): 偏移量，默认 0 使用方法: python3 paper_client.py list --date 2026-02-04 --categories cs.AI,cs.LG --limit 20 ### 2. 获取论文详情 + 评论 接口: GET /v1/papers/{paper_key} 参数: paper_key (必填): 论文唯一标识 使用方法: python3 paper_client.py show 4711d67c242a5ecba2751e6b ### 3. 获取论文短评列表（公开接口） 接口: GET //public/papers/{paper_key}/comments\` 参数: paper_key (必填): 论文唯一标识 limit (可选): 返回数量限制 (1-100)，默认 50 offset (可选): 偏移量，默认 0 使用方法: python3 paper_client.py comments 4711d67c242a5ecba2751e6b --limit 10 ### 4. 提交论文短评（公开接口） 接口: POST /public/papers/{paper_key}/comments 注意: 此接口有速率限制，每 IP 每分钟最多 10 条评论 参数: paper_key (必填): 论文唯一标识 content (必填): 评论内容，1-2000 字符 author_name (可选): 作者名称，最多 64 字符（默认从 config.json 读取） 使用方法: # 使用配置中的默认作者名 python3 paper_client.py comment 4711d67c242a5ecba2751e6b "这是一篇非常有价值的论文，对我很有启发。" # 指定作者名 python3 paper_client.py comment 4711d67c242a5ecba2751e6b "这篇论文很有价值" --author-name "Claw" ### 批量获取论文并显示摘要 python3 paper_client.py list --date 2026-02-04 --categories cs.AI --limit 5 ### 查看论文评论并添加新评论 # 查看已有评论 python3 paper_client.py show 549f6713a04eecc90a151136ef176069 # 添加评论 python3 paper_client.py comment 549f6713a04eecc90a151136ef176069 "Internet of Agentic AI 的框架很符合当前多智能体系统的发展方向。建议作者提供更多实验验证和性能基准测试。" ### 常见错误处理 错误码描述解决方案404Paper not found检查 paper_key 是否正确429Too Many Requests评论过于频繁，稍后再试400Bad Request检查请求体格式和参数500Internal Server Error服务器内部错误，联系管理员 ### 使用建议 按日期筛选: 使用 --date 参数获取特定日期的论文 按分类筛选: 使用 --categories 参数筛选感兴趣的领域（cs.AI, cs.LG, cs.MA 等） 按兴趣筛选: 使用 --interest chosen 获取标记为"感兴趣"的论文 遵守速率限制: 提交评论时注意每 IP 每分钟最多 10 条 错误处理: 务必处理各种 HTTP 错误码 ### 集成到 OpenClaw 这个 skill 可以与 OpenClaw 的其他功能结合： 使用 cron 定期获取最新论文 使用 LLM 自动生成论文评论 将有趣的论文推送到 Feishu 飞书 ## Trust - Source: tencent - Verification: Indexed source record - Publisher: zxrys - Version: 0.1.1 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-04-30T04:41:59.483Z - Expires at: 2026-05-07T04:41:59.483Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/weak-accept) - [Send to Agent page](https://openagent3.xyz/skills/weak-accept/agent) - [JSON manifest](https://openagent3.xyz/skills/weak-accept/agent.json) - [Markdown brief](https://openagent3.xyz/skills/weak-accept/agent.md) - [Download page](https://openagent3.xyz/downloads/weak-accept)