arxiv_id: bare ID like 2305.11206 or full https://arxiv.org/abs/2305.11206 (Normalise: strip the URL prefix, extract bare ID.)Try HTML first: web.fetch https://arxiv.org/html/
paper_text.If the paper_text is retrieved then write the summary to ~/.openclaw/workspace/papers/.
Note: DO NOT DO THIS STEP INSIDE sub-agents
Within the main agent and from paper_text, identify at most 5 citations the paper most directly builds on. Prioritize:
For each citation, extract either the arXiv ID or the title. Then resolve to an arXiv URL:
https://arxiv.org/html/https://arxiv.org/search/?query=&searchtype=all</code> and take the first match.</li></ul><h2>Step 3 — Spawn sub-agents for citations</h2><hr><p>For each resolved citation:</p><ul><li>Check if the file for citation exists: <code>~/.openclaw/workspace/papers/<arxiv-id>.md</code>, if it does then skip and consider the sub-agent concluded.</li><li>If the previous step fails then spawn a sub-agent with this EXACT instruction in VERBATIM: </li><li>Fetch https://arxiv.org/html/<citation_id> (or add v1 at the end, and try again: web.fetch https://arxiv.org/html/<arxiv_id>v1). If unavailable, SKIP. If retrieved then Write the summary to <code>~/.openclaw/workspace/papers/<arxiv-id>.md</code>.</li></ul><h2>Step 4 — Write the executive summary</h2><p>Check the citation summaries within <code>~/.openclaw/workspace/papers/</code> then utilize the main paper we are summarising with citation summaries and write a single <strong>markdown document in flowing prose</strong> (no bullet lists) to <code>~/.openclaw/workspace/digest/report_<arxiv-id></code>. Use this structure:</p><pre><code># <Title>
<What problem this solves and why it matters. Context and related references summary>
<What prior work missed and how this paper addresses that gap. Cite inline as [Author et al., YEAR](<arxiv_link>).
<Core method in plain terms>
<Headline result. How it differs from previous work.
<One limitation and one future direction>
<Detailed Ablations, benchmarks if present in this paper or cited references>
</code></pre><h2>Rules</h2><ul><li>Every citation must be a markdown link: <code><a href="<arxiv_or_url>" target="_blank" rel="noopener">Author et al., YEAR</a></code></li><li>No bullet lists in the output — <strong>prose only</strong>.</li><li>If a section is absent from the paper (e.g., no ablations), skip it silently.</li><li>Do not fabricate results, metrics, or author claims.</li><li><strong>Citation resolution retry</strong>: If a citation URL cannot be resolved after one retry, write the citation as plain text without a link: <code>[Author et al., YEAR]</code>.</li></ul></div>
</div>
</div>
<div id="tab-versions" class="detail-content">
<div class="detail-section">
<h2>版本历史</h2>
<p style="margin-bottom:12px;font-size:14px;color:#94a3b8;">共 1 个版本</p>
<ul class="version-list">
<li>
<div>
<span class="version-tag">v0.0.2</span>
<span style="font-size:11px;color:#5b6abf;margin-left:8px;background:#eef0ff;padding:1px 8px;border-radius:10px;">当前</span> </div>
<div style="font-size:12px;color:#94a3b8;">
2026-03-29 23:59 安全 安全 </div>
</li>
</ul>
</div>
</div>
<div id="tab-security" class="detail-content">
<div class="detail-section">
<h2>安全检测</h2>
<div class="sec-grid"> <div class="sec-card">
<h4>腾讯云安全 (Keen)</h4>
<div class="sec-status sec-safe">
安全，无风险 </div>
<a href="https://tix.qq.com/search/skill?keyword=9a4fe9aac7dca4e6f11d7803ffdb1701" target="_blank">查看报告</a> </div>
<div class="sec-card">
<h4>腾讯云安全 (Sanbu)</h4>
<div class="sec-status sec-safe">
安全，无风险 </div>
<a href="https://static.cloudsec.tencent.com/html-report-v2/2026/05/25/404181_84cec804bd654550bf92b36c825bdf00.html?q-sign-algorithm=sha1&q-ak=AKID8JMG1bzBC1dz96qNhssfFftujT1NCoFi&q-sign-time=1781393519%3B1812929519&q-key-time=1781393519%3B1812929519&q-header-list=host&q-url-param-list=&q-signature=60ff157f465f8d104339484bd8ccbaf4af820610" target="_blank">查看报告</a> </div>
</div>
</div>
</div>
<!-- Recommended Skills -->
<div style="margin-top:24px;">
<h2 style="font-size:18px;font-weight:600;margin-bottom:16px;">🔗 相关推荐</h2>
<div class="rec-grid">
<div class="rec-card">
<span class="badge-cat" style="margin-bottom:8px;display:inline-block;">content-creation</span>
<h3><a href="/s/humanizer">Humanizer</a></h3>
<div class="rec-owner">biostartechnology</div> <div class="rec-desc">消除AI写作痕迹，使文本更自然真实。基于维基百科"AI写作特征"指南，识别并修正夸张象征、宣传用语、肤浅-ing分析、模糊归因、破折号滥用、三项排比、AI词汇、负面平行结构及冗长连接词等模式。</div>
<div class="rec-stats">
<span style="color:#f39c12;">★ 862</span>
<span style="color:#5b6abf;">📥 200,230</span>
</div>
</div>
<div class="rec-card">
<span class="badge-cat" style="margin-bottom:8px;display:inline-block;">content-creation</span>
<h3><a href="/s/ai-ppt-generator">Baidu Wenku AIPPT</a></h3>
<div class="rec-owner">ide-rea</div> <div class="rec-desc">使用百度文库 AI 智能生成 PPT，自动根据内容选择模板。</div>
<div class="rec-stats">
<span style="color:#f39c12;">★ 66</span>
<span style="color:#5b6abf;">📥 46,247</span>
</div>
</div>
<div class="rec-card">
<span class="badge-cat" style="margin-bottom:8px;display:inline-block;">content-creation</span>
<h3><a href="/s/admapix">AdMapix</a></h3>
<div class="rec-owner">fly0pants</div> <div class="rec-desc">广告情报与应用数据分析助手，支持搜索广告素材、分析应用排名、下载量、收入及市场洞察，用于广告素材和竞品分析。</div>
<div class="rec-stats">
<span style="color:#f39c12;">★ 295</span>
<span style="color:#5b6abf;">📥 136,553</span>
</div>
</div>
</div>
</div>
</div>
<script>
document.addEventListener('DOMContentLoaded',function(){
document.querySelectorAll('.detail-tab').forEach(function(btn){
btn.addEventListener('click',function(e){
var tab = this.getAttribute('data-tab');
document.querySelectorAll('.detail-tab').forEach(function(b){b.classList.remove('active')});
document.querySelectorAll('.detail-content').forEach(function(c){c.classList.remove('active')});
this.classList.add('active');
var el = document.getElementById('tab-'+tab);
if(el) el.classList.add('active');
});
});
});
</script>
<div class="footer">
<p>Skill工具集 © 2026</p>
</div></body>
</html>