[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74MHV8YV7FE0436N338AG4W":3,"skill-same:01M74MHV8YV7FE0436N338AG4W":64},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":40,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M74MHV8YV7FE0436N338AG4W","deepxiv-cli",null,"Access academic papers (arXiv, PMC, and coming soon bioRxiv, medRxiv) via CLI with hybrid search and intelligent content extraction","pengqianhan\u002FAI-Human-Research-OS","pengqianhan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4286531?v=4","01M74M3DT9HNZ6HPAK8TX69EX9","PengqianHan","01M74M3DTVSN2GXW0JH2W396FK",3,"MIT","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fcollected-skills\u002Fdeepxiv-cli\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: deepxiv-cli\nversion: \"0.2.0\"\ndescription: Access academic papers (arXiv, PMC, and coming soon bioRxiv, medRxiv) via CLI with hybrid search and intelligent content extraction\nframeworks: [\"codex\", \"langchain\", \"claude-code\", \"custom-agents\"]\nuse_cases: [\"literature-search\", \"paper-analysis\", \"knowledge-synthesis\", \"research-assistant\"]\n---\n\n# DeepXiv CLI Skill\n\n## 🚀 30-Second Overview\n\n**What**: Access open access academic papers (arXiv, PMC, bioRxiv, medRxiv) through a powerful CLI tool.\n\n**What you can do**:\n- 🔍 Search papers with hybrid search (BM25 + Vector)\n- 📄 Read papers section-by-section (save tokens!)\n- 🧠 Use built-in AI agent for analysis\n- 📊 Access biomedical literature (PMC)\n\n**When to use**: User wants to search, read, or analyze academic papers\n\n---\n\n## 🎯 Command Selection Guide\n\n**I want to...** → **Use this command**\n\n| Goal | Command | Example |\n|------|---------|---------|\n| Find papers on a topic | `deepxiv search` | `deepxiv search \"agent memory\" --limit 5` |\n| Quickly understand a paper | `deepxiv paper \u003Cid> --brief` | `deepxiv paper 2409.05591 --brief` |\n| Read specific section | `deepxiv paper \u003Cid> --section` | `deepxiv paper 2409.05591 --section Introduction` |\n| See paper structure | `deepxiv paper \u003Cid> --head` | `deepxiv paper 2409.05591 --head` |\n| Preview first 10k chars | `deepxiv paper \u003Cid> --preview` | `deepxiv paper 2409.05591 --preview` |\n| Get full text | `deepxiv paper \u003Cid>` | `deepxiv paper 2409.05591` |\n| Access biomedical paper | `deepxiv pmc \u003Cid>` | `deepxiv pmc PMC544940` |\n| Intelligent analysis | `deepxiv agent query` | `deepxiv agent query \"analyze this paper\"` |\n\n---\n\n## 📚 Core Commands Reference\n\n### 1. Search Papers (`deepxiv search`)\n\n**When to use**: Finding relevant papers on a topic\n\n```bash\n# Basic search (quick)\ndeepxiv search \"agent memory\" --limit 5\n\n# Advanced search with filters\ndeepxiv search \"transformer\" --mode bm25 --format json\ndeepxiv search \"LLM\" --categories cs.AI,cs.CL --min-citations 100\n\n# Date range\ndeepxiv search \"vision models\" --date-from 2024-01-01 --date-to 2024-12-31\n```\n\n**Expected output**: List of papers with title, arxiv_id, score, citation count\n**Token cost**: ~500-1000 tokens per search\n**Tips**:\n- Use `--limit 3-5` for quick overview\n- Use `--format json` for downstream processing\n- Adjust `bm25_weight` and `vector_weight` for different search styles\n\n---\n\n### 2. Read arXiv Papers (`deepxiv paper`)\n\n**When to use**: Understanding specific papers (choose format by depth needed)\n\n#### Option A: Quick Summary (30 seconds)\n```bash\ndeepxiv paper 2409.05591 --brief\n# ✓ Best for: Quick understanding\n# → Title, TLDR, keywords, citation count\n# Token cost: ~500 tokens\n# Use when: \"What's this paper about?\"\n```\n\n#### Option B: Paper Structure (2 minutes)\n```bash\ndeepxiv paper 2409.05591 --head\n# ✓ Best for: Understanding paper organization\n# → Metadata, all sections with summaries\n# Token cost: ~1-2k tokens\n# Use when: \"What does this paper contain?\"\n```\n\n#### Option C: Quick Scan (3 minutes)\n```bash\ndeepxiv paper 2409.05591 --preview\n# ✓ Best for: Fast preview without full read\n# → First ~10k characters\n# Token cost: ~2k tokens\n# Use when: \"Let me scan the introduction\"\n```\n\n#### Option D: Specific Section (1 minute)\n```bash\ndeepxiv paper 2409.05591 --section Introduction\n# ✓ Best for: Reading one section in detail\n# → Full section content\n# Token cost: ~1-5k tokens (varies by section)\n# Use when: \"I only need the introduction\"\n```\n\n#### Option E: Complete Paper (for deep analysis)\n```bash\ndeepxiv paper 2409.05591\n# or explicitly: deepxiv paper 2409.05591 --raw\n# ✓ Best for: Full text analysis\n# → Complete paper in markdown\n# Token cost: ~10-50k tokens\n# Use when: \"I need to thoroughly analyze this\"\n```\n\n---\n\n### 3. Access Biomedical Literature (`deepxiv pmc`)\n\n**When to use**: Need medical, biology, or biomedical research\n\n```bash\n# Quick metadata\ndeepxiv pmc PMC544940 --head\n\n# Full paper\ndeepxiv pmc PMC544940\n```\n\n**Expected output**: Paper metadata or complete paper JSON\n**Token cost**: ~1-2k tokens (metadata), ~10-30k tokens (full)\n\n---\n\n### 4. Manage Token (`deepxiv token`)\n\n**When to use**: Check your API token status\n\n```bash\ndeepxiv token\n# Shows current token and daily limit info\n```\n\n**Note**: Token auto-registers on first use, saves to `~\u002F.env`\n\n---\n\n### 5. Intelligent Agent (`deepxiv agent`)\n\n**When to use**: Need analysis beyond simple retrieval\n\n```bash\n# One-time query\ndeepxiv agent query \"What are key innovations in this paper?\"\n\n# Multi-turn reasoning\ndeepxiv agent query \"Compare these two approaches\" --max-turn 10 --verbose\n\n# First time setup\ndeepxiv agent config\n# Configure your LLM (OpenAI, DeepSeek, OpenRouter, etc.)\n```\n\n**Token cost**: Varies by reasoning depth\n**Requirements**: Requires langgraph and langchain-core\n\n---\n\n## 🎬 Common Workflows\n\n### Workflow 1: Quick Paper Review (2 minutes)\n```bash\n# Step 1: Get brief info\ndeepxiv paper 2409.05591 --brief\n\n# Step 2: Read introduction\ndeepxiv paper 2409.05591 --section Introduction\n\n# Step 3: Check results (optional)\ndeepxiv paper 2409.05591 --section Results\n```\n**Total tokens**: ~2-3k | **Use case**: Quick assessment before deciding to read fully\n\n### Workflow 2: Deep Paper Analysis (15 minutes)\n```bash\n# Step 1: Understand structure\ndeepxiv paper 2409.05591 --head\n\n# Step 2: Read key sections\ndeepxiv paper 2409.05591 --section Introduction\ndeepxiv paper 2409.05591 --section Methods\ndeepxiv paper 2409.05591 --section Results\n\n# Step 3: AI analysis\ndeepxiv agent query \"Summarize the main contributions\"\n```\n**Total tokens**: ~10-15k | **Use case**: Thorough understanding\n\n### Workflow 3: Literature Search (5 minutes)\n```bash\n# Step 1: Find relevant papers\ndeepxiv search \"agent memory\" --limit 5\n\n# Step 2: Quick assess each\nfor id in results; do\n    deepxiv paper $id --brief\ndone\n\n# Step 3: Deep read top 2\ndeepxiv paper \u003Ctop_id_1>\ndeepxiv paper \u003Ctop_id_2>\n```\n**Total tokens**: ~5-10k | **Use case**: Literature review\n\n---\n\n## 💪 Capabilities & Limitations\n\n### What deepxiv Can Do ✅\n\n| Capability | Details |\n|-----------|---------|\n| **Hybrid Search** | BM25 + Vector search across 2M+ arXiv papers |\n| **Smart Summaries** | AI-generated TLDRs and keywords |\n| **Section Access** | Read specific sections without loading full text |\n| **Biomedical Access** | PubMed Central (PMC) papers |\n| **Open Access Only** | arXiv, PMC, bioRxiv (coming), medRxiv (coming) |\n| **Intelligent Analysis** | ReAct agent with multi-turn reasoning |\n| **Multiple LLMs** | Compatible with OpenAI, DeepSeek, OpenRouter, etc. |\n\n### What deepxiv Cannot Do ❌\n\n| Limitation | Note |\n|-----------|------|\n| **Subscription Journals** | Only open access papers (by design) |\n| **Real-time Updates** | arXiv has ~1-2 day delay |\n| **Paywalled Content** | Cannot access IEEE, ACM, etc. journals |\n| **Daily Limits** | 10,000 requests\u002Fday free (email for more) |\n| **Proprietary Data** | Only academic papers, not internal docs |\n\n---\n\n## 🔧 Troubleshooting\n\n### Problem: Paper Not Found\n```bash\ndeepxiv paper invalid_id\n# Error: NotFoundError: Paper not found\n```\n**Solution**:\n- Check arXiv ID format (should be like `2409.05591`)\n- Verify at https:\u002F\u002Farxiv.org\n\n### Problem: Daily Limit Exceeded\n```bash\ndeepxiv search \"topic\"\n# Error: RateLimitError: Daily limit reached\n```\n**Solution**:\n- Wait until tomorrow (limit resets daily)\n- OR email `tommy@chien.io` with name, email, phone for higher limit\n\n### Problem: Token Invalid\n```bash\ndeepxiv paper 2409.05591\n# Error: AuthenticationError: Invalid or expired token\n```\n**Solution**:\n- Run `deepxiv config --token YOUR_NEW_TOKEN`\n- Or delete `~\u002F.env` to auto-register new token\n\n### Problem: Agent Dependencies Missing\n```bash\ndeepxiv agent query \"analyze\"\n# Error: langgraph not installed\n```\n**Solution**:\n```bash\npip install deepxiv-sdk[agent]\n```\n\n### Problem: Timeout on Large Papers\n```bash\ndeepxiv paper \u003Clarge_paper_id>\n# Error: Request timed out\n```\n**Solution**:\n- Use `--brief` or `--head` instead of full paper\n- Or use `--section` to read specific parts\n- Increase timeout: Use Python API with `Reader(timeout=180)`\n\n---\n\n## 📊 Output Format Guide\n\n### For Search Results\n**Format**: Show title, arxiv_id, brief context\n```\n1. Title of Paper (2409.05591)\n   - Field: Computer Science \u002F AI\n   - Citations: 150\n   - Key idea: Brief 1-line summary of main contribution\n```\n\n### For Paper Reading\n**Always mention what command was used**:\n```\nFrom `deepxiv paper 2409.05591 --brief`:\n- Title: MemGPT: Towards LLMs as Operating Systems\n- TLDR: Introduces hierarchical memory management for extended context\n- Key concepts: agent memory, context management, LLM systems\n- (~500 tokens)\n```\n\n### For Structured Data\n**Use JSON format when**:\n- Processing results programmatically\n- Building pipelines\n- Storing for later analysis\n```bash\ndeepxiv search \"topic\" --format json  # Pipe to other tools\n```\n\n---\n\n## ⏱️ Token Budget Guide\n\nWhen planning queries, consider token costs:\n\n```\nQuick Summary:        500 tokens\nMetadata (--head):    1-2k tokens\nOne Section:          1-5k tokens (depends on section)\nFull Paper:           10-50k tokens\nSearch Query:         0.5-1k tokens\nAgent Analysis:       5-20k tokens (reasoning depth)\n```\n\n**Recommendation**: For general use, stick to `--brief` and `--section` to keep tokens under 5k per query.\n\n---\n\n## 🚀 Advanced Usage\n\n### Batch Processing (Multiple Papers)\n```bash\nfor id in 2409.05591 2504.21776 2503.04975; do\n    echo \"=== $id ===\"\n    deepxiv paper $id --brief\ndone\n```\n\n### Piping to Other Tools\n```bash\ndeepxiv search \"topic\" --format json | jq '.results[] | .arxiv_id'\n```\n\n### Custom Token Configuration\n```python\nfrom deepxiv_sdk import Reader\nreader = Reader(token=\"YOUR_TOKEN\", timeout=120, max_retries=5)\n```\n\n---\n\n## 🌐 Supported & Coming Soon\n\n### Current Support ✅\n- **arXiv** - Computer Science, Physics, Math, Economics\n- **PMC** - PubMed Central biomedical literature\n\n### Coming Soon 🔄\n- **bioRxiv** - Biology preprints\n- **medRxiv** - Medicine preprints\n- **Other OA** - Additional open access sources\n- **Full OA Ecosystem** - Unified cross-source search\n\n---\n\n## 📞 Getting Help\n\n**Command not working?**\n```bash\ndeepxiv \u003Ccommand> --help\n```\n\n**Need a higher daily limit?**\nEmail: `tommy@chien.io` with name, email, phone\n\n**Found a bug?**\n[GitHub Issues](https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fdeepxiv_sdk\u002Fissues)\n\n**Learn more?**\n[Full Documentation](https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fdeepxiv_sdk#readme)\n\n---\n\n## ✨ Tips & Best Practices\n\n1. **Start with `--brief`** - Always start with brief overview\n2. **Use sections** - Don't load full papers when sections suffice\n3. **Save tokens** - Stack operations to reduce API calls\n4. **Check limits** - Run `deepxiv token` before large batches\n5. **Use agent wisely** - For complex analysis that needs reasoning\n6. **Format choice** - Use `--format json` for piping, plain text for humans\n7. **Error handling** - Always handle \"Paper not found\" and \"Limit exceeded\" cases\n\n---\n\n**Last Updated**: 2024 | **Version**: 0.2.0 | **Status**: Production Ready\n","# DeepXiv CLI Skill\n\n## 🚀 30-Second Overview\n\n**What**: Access open access academic papers (arXiv, PMC, bioRxiv, medRxiv) through a powerful CLI tool.\n\n**What you can do**:\n- 🔍 Search papers with hybrid search (BM25 + Vector)\n- 📄 Read papers section-by-section (save tokens!)\n- 🧠 Use built-in AI agent for analysis\n- 📊 Access biomedical literature (PMC)\n\n**When to use**: User wants to search, read, or analyze academic papers\n\n---\n\n## 🎯 Command Selection Guide\n\n**I want to...** → **Use this command**\n\n| Goal | Command | Example |\n|------|---------|---------|\n| Find papers on a topic | `deepxiv search` | `deepxiv search \"agent memory\" --limit 5` |\n| Quickly understand a paper | `deepxiv paper \u003Cid> --brief` | `deepxiv paper 2409.05591 --brief` |\n| Read specific section | `deepxiv paper \u003Cid> --section` | `deepxiv paper 2409.05591 --section Introduction` |\n| See paper structure | `deepxiv paper \u003Cid> --head` | `deepxiv paper 2409.05591 --head` |\n| Preview first 10k chars | `deepxiv paper \u003Cid> --preview` | `deepxiv paper 2409.05591 --preview` |\n| Get full text | `deepxiv paper \u003Cid>` | `deepxiv paper 2409.05591` |\n| Access biomedical paper | `deepxiv pmc \u003Cid>` | `deepxiv pmc PMC544940` |\n| Intelligent analysis | `deepxiv agent query` | `deepxiv agent query \"analyze this paper\"` |\n\n---\n\n## 📚 Core Commands Reference\n\n### 1. Search Papers (`deepxiv search`)\n\n**When to use**: Finding relevant papers on a topic\n\n```bash\n# Basic search (quick)\ndeepxiv search \"agent memory\" --limit 5\n\n# Advanced search with filters\ndeepxiv search \"transformer\" --mode bm25 --format json\ndeepxiv search \"LLM\" --categories cs.AI,cs.CL --min-citations 100\n\n# Date range\ndeepxiv search \"vision models\" --date-from 2024-01-01 --date-to 2024-12-31\n```\n\n**Expected output**: List of papers with title, arxiv_id, score, citation count\n**Token cost**: ~500-1000 tokens per search\n**Tips**:\n- Use `--limit 3-5` for quick overview\n- Use `--format json` for downstream processing\n- Adjust `bm25_weight` and `vector_weight` for different search styles\n\n---\n\n### 2. Read arXiv Papers (`deepxiv paper`)\n\n**When to use**: Understanding specific papers (choose format by depth needed)\n\n#### Option A: Quick Summary (30 seconds)\n```bash\ndeepxiv paper 2409.05591 --brief\n# ✓ Best for: Quick understanding\n# → Title, TLDR, keywords, citation count\n# Token cost: ~500 tokens\n# Use when: \"What's this paper about?\"\n```\n\n#### Option B: Paper Structure (2 minutes)\n```bash\ndeepxiv paper 2409.05591 --head\n# ✓ Best for: Understanding paper organization\n# → Metadata, all sections with summaries\n# Token cost: ~1-2k tokens\n# Use when: \"What does this paper contain?\"\n```\n\n#### Option C: Quick Scan (3 minutes)\n```bash\ndeepxiv paper 2409.05591 --preview\n# ✓ Best for: Fast preview without full read\n# → First ~10k characters\n# Token cost: ~2k tokens\n# Use when: \"Let me scan the introduction\"\n```\n\n#### Option D: Specific Section (1 minute)\n```bash\ndeepxiv paper 2409.05591 --section Introduction\n# ✓ Best for: Reading one section in detail\n# → Full section content\n# Token cost: ~1-5k tokens (varies by section)\n# Use when: \"I only need the introduction\"\n```\n\n#### Option E: Complete Paper (for deep analysis)\n```bash\ndeepxiv paper 2409.05591\n# or explicitly: deepxiv paper 2409.05591 --raw\n# ✓ Best for: Full text analysis\n# → Complete paper in markdown\n# Token cost: ~10-50k tokens\n# Use when: \"I need to thoroughly analyze this\"\n```\n\n---\n\n### 3. Access Biomedical Literature (`deepxiv pmc`)\n\n**When to use**: Need medical, biology, or biomedical research\n\n```bash\n# Quick metadata\ndeepxiv pmc PMC544940 --head\n\n# Full paper\ndeepxiv pmc PMC544940\n```\n\n**Expected output**: Paper metadata or complete paper JSON\n**Token cost**: ~1-2k tokens (metadata), ~10-30k tokens (full)\n\n---\n\n### 4. Manage Token (`deepxiv token`)\n\n**When to use**: Check your API token status\n\n```bash\ndeepxiv token\n# Shows current token and daily limit info\n```\n\n**Note**: Token auto-registers on first use, saves to `~\u002F.env`\n\n---\n\n### 5. Intelligent Agent (`deepxiv agent`)\n\n**When to use**: Need analysis beyond simple retrieval\n\n```bash\n# One-time query\ndeepxiv agent query \"What are key innovations in this paper?\"\n\n# Multi-turn reasoning\ndeepxiv agent query \"Compare these two approaches\" --max-turn 10 --verbose\n\n# First time setup\ndeepxiv agent config\n# Configure your LLM (OpenAI, DeepSeek, OpenRouter, etc.)\n```\n\n**Token cost**: Varies by reasoning depth\n**Requirements**: Requires langgraph and langchain-core\n\n---\n\n## 🎬 Common Workflows\n\n### Workflow 1: Quick Paper Review (2 minutes)\n```bash\n# Step 1: Get brief info\ndeepxiv paper 2409.05591 --brief\n\n# Step 2: Read introduction\ndeepxiv paper 2409.05591 --section Introduction\n\n# Step 3: Check results (optional)\ndeepxiv paper 2409.05591 --section Results\n```\n**Total tokens**: ~2-3k | **Use case**: Quick assessment before deciding to read fully\n\n### Workflow 2: Deep Paper Analysis (15 minutes)\n```bash\n# Step 1: Understand structure\ndeepxiv paper 2409.05591 --head\n\n# Step 2: Read key sections\ndeepxiv paper 2409.05591 --section Introduction\ndeepxiv paper 2409.05591 --section Methods\ndeepxiv paper 2409.05591 --section Results\n\n# Step 3: AI analysis\ndeepxiv agent query \"Summarize the main contributions\"\n```\n**Total tokens**: ~10-15k | **Use case**: Thorough understanding\n\n### Workflow 3: Literature Search (5 minutes)\n```bash\n# Step 1: Find relevant papers\ndeepxiv search \"agent memory\" --limit 5\n\n# Step 2: Quick assess each\nfor id in results; do\n    deepxiv paper $id --brief\ndone\n\n# Step 3: Deep read top 2\ndeepxiv paper \u003Ctop_id_1>\ndeepxiv paper \u003Ctop_id_2>\n```\n**Total tokens**: ~5-10k | **Use case**: Literature review\n\n---\n\n## 💪 Capabilities & Limitations\n\n### What deepxiv Can Do ✅\n\n| Capability | Details |\n|-----------|---------|\n| **Hybrid Search** | BM25 + Vector search across 2M+ arXiv papers |\n| **Smart Summaries** | AI-generated TLDRs and keywords |\n| **Section Access** | Read specific sections without loading full text |\n| **Biomedical Access** | PubMed Central (PMC) papers |\n| **Open Access Only** | arXiv, PMC, bioRxiv (coming), medRxiv (coming) |\n| **Intelligent Analysis** | ReAct agent with multi-turn reasoning |\n| **Multiple LLMs** | Compatible with OpenAI, DeepSeek, OpenRouter, etc. |\n\n### What deepxiv Cannot Do ❌\n\n| Limitation | Note |\n|-----------|------|\n| **Subscription Journals** | Only open access papers (by design) |\n| **Real-time Updates** | arXiv has ~1-2 day delay |\n| **Paywalled Content** | Cannot access IEEE, ACM, etc. journals |\n| **Daily Limits** | 10,000 requests\u002Fday free (email for more) |\n| **Proprietary Data** | Only academic papers, not internal docs |\n\n---\n\n## 🔧 Troubleshooting\n\n### Problem: Paper Not Found\n```bash\ndeepxiv paper invalid_id\n# Error: NotFoundError: Paper not found\n```\n**Solution**:\n- Check arXiv ID format (should be like `2409.05591`)\n- Verify at https:\u002F\u002Farxiv.org\n\n### Problem: Daily Limit Exceeded\n```bash\ndeepxiv search \"topic\"\n# Error: RateLimitError: Daily limit reached\n```\n**Solution**:\n- Wait until tomorrow (limit resets daily)\n- OR email `tommy@chien.io` with name, email, phone for higher limit\n\n### Problem: Token Invalid\n```bash\ndeepxiv paper 2409.05591\n# Error: AuthenticationError: Invalid or expired token\n```\n**Solution**:\n- Run `deepxiv config --token YOUR_NEW_TOKEN`\n- Or delete `~\u002F.env` to auto-register new token\n\n### Problem: Agent Dependencies Missing\n```bash\ndeepxiv agent query \"analyze\"\n# Error: langgraph not installed\n```\n**Solution**:\n```bash\npip install deepxiv-sdk[agent]\n```\n\n### Problem: Timeout on Large Papers\n```bash\ndeepxiv paper \u003Clarge_paper_id>\n# Error: Request timed out\n```\n**Solution**:\n- Use `--brief` or `--head` instead of full paper\n- Or use `--section` to read specific parts\n- Increase timeout: Use Python API with `Reader(timeout=180)`\n\n---\n\n## 📊 Output Format Guide\n\n### For Search Results\n**Format**: Show title, arxiv_id, brief context\n```\n1. Title of Paper (2409.05591)\n   - Field: Computer Science \u002F AI\n   - Citations: 150\n   - Key idea: Brief 1-line summary of main contribution\n```\n\n### For Paper Reading\n**Always mention what command was used**:\n```\nFrom `deepxiv paper 2409.05591 --brief`:\n- Title: MemGPT: Towards LLMs as Operating Systems\n- TLDR: Introduces hierarchical memory management for extended context\n- Key concepts: agent memory, context management, LLM systems\n- (~500 tokens)\n```\n\n### For Structured Data\n**Use JSON format when**:\n- Processing results programmatically\n- Building pipelines\n- Storing for later analysis\n```bash\ndeepxiv search \"topic\" --format json  # Pipe to other tools\n```\n\n---\n\n## ⏱️ Token Budget Guide\n\nWhen planning queries, consider token costs:\n\n```\nQuick Summary:        500 tokens\nMetadata (--head):    1-2k tokens\nOne Section:          1-5k tokens (depends on section)\nFull Paper:           10-50k tokens\nSearch Query:         0.5-1k tokens\nAgent Analysis:       5-20k tokens (reasoning depth)\n```\n\n**Recommendation**: For general use, stick to `--brief` and `--section` to keep tokens under 5k per query.\n\n---\n\n## 🚀 Advanced Usage\n\n### Batch Processing (Multiple Papers)\n```bash\nfor id in 2409.05591 2504.21776 2503.04975; do\n    echo \"=== $id ===\"\n    deepxiv paper $id --brief\ndone\n```\n\n### Piping to Other Tools\n```bash\ndeepxiv search \"topic\" --format json | jq '.results[] | .arxiv_id'\n```\n\n### Custom Token Configuration\n```python\nfrom deepxiv_sdk import Reader\nreader = Reader(token=\"YOUR_TOKEN\", timeout=120, max_retries=5)\n```\n\n---\n\n## 🌐 Supported & Coming Soon\n\n### Current Support ✅\n- **arXiv** - Computer Science, Physics, Math, Economics\n- **PMC** - PubMed Central biomedical literature\n\n### Coming Soon 🔄\n- **bioRxiv** - Biology preprints\n- **medRxiv** - Medicine preprints\n- **Other OA** - Additional open access sources\n- **Full OA Ecosystem** - Unified cross-source search\n\n---\n\n## 📞 Getting Help\n\n**Command not working?**\n```bash\ndeepxiv \u003Ccommand> --help\n```\n\n**Need a higher daily limit?**\nEmail: `tommy@chien.io` with name, email, phone\n\n**Found a bug?**\n[GitHub Issues](https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fdeepxiv_sdk\u002Fissues)\n\n**Learn more?**\n[Full Documentation](https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fdeepxiv_sdk#readme)\n\n---\n\n## ✨ Tips & Best Practices\n\n1. **Start with `--brief`** - Always start with brief overview\n2. **Use sections** - Don't load full papers when sections suffice\n3. **Save tokens** - Stack operations to reduce API calls\n4. **Check limits** - Run `deepxiv token` before large batches\n5. **Use agent wisely** - For complex analysis that needs reasoning\n6. **Format choice** - Use `--format json` for piping, plain text for humans\n7. **Error handling** - Always handle \"Paper not found\" and \"Limit exceeded\" cases\n\n---\n\n**Last Updated**: 2024 | **Version**: 0.2.0 | **Status**: Production Ready\n",{"name":5,"version":24,"use_cases":25,"frameworks":30,"description":7},"0.2.0",[26,27,28,29],"literature-search","paper-analysis","knowledge-synthesis","research-assistant",[31,32,33,34],"codex","langchain","claude-code","custom-agents","main","e71245365df78e06cd166602744bf2491f79910e","research-skills-hub\u002Fcollected-skills\u002Fdeepxiv-cli",0,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS","https:\u002F\u002Fpengqianhan.github.io\u002FAI-Human-Research-OS\u002F","https:\u002F\u002Fgithub.com\u002Fpengqianhan","Ph.D. candidate of The University of Auckland, New Zealand","2026-11-14 18:08:16",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add pengqianhan\u002FAI-Human-Research-OS --skill deepxiv-cli",{"tool":50,"command":51},"bunx","bunx skills add pengqianhan\u002FAI-Human-Research-OS --skill deepxiv-cli",{"tool":53,"command":54},"pnpm","pnpm dlx skills add pengqianhan\u002FAI-Human-Research-OS --skill deepxiv-cli","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fcollected-skills\u002Fdeepxiv-cli\u002FSKILL.md",true,[58],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"agents\u002Fopenai.yaml","REFERENCE","参考文档",287,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fcollected-skills\u002Fdeepxiv-cli\u002Fagents\u002Fopenai.yaml",[65,72,79,86,93,100],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M74MWYTHT498SVMN823896T7","workflow-skill-creator","Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say \"make this a skill\", \"create a skill from what we just did\", \"package this workflow\" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fworkflow_skill_creator\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M74MWWVCFZ8HQS8840F1V1FT","uv","Checks whether the uv Python package manager is installed and installs it if missing. Ensures uv is on PATH. Use when another skill requires uv as a prerequisite.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fuv\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M74MWRH5BTSWZ2C5PCTD5FV9","uniprot-database","Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or retrieving functional annotations and publications. Don't use for sequence alignment, protein folding, or sequence similarity search (use specialized skills for those tasks).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Funiprot_database\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M74MWN1D3ER9F1FZPWH8HQC1","unibind-database","Queries the UniBind database for experimentally validated transcription factor (TF) binding sites. Use when retrieving direct TF-DNA interaction datasets, downloading binding site coordinates (BED\u002FFASTA) for local analysis, or listing available datasets by species, cell line, or TF name. Don't use to query specific intervals, locations, genes, motif models or expression data.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Funibind_database\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M74MWHHB5QZY3NR2FYA1EK4N","ucsc-conservation-and-tfbs","Fetch Evolutionary Conservation scores (phyloP, phastCons) and Transcription Factor Binding Sites (TFBS) from the UCSC Genome Browser. Use when analyzing whether genomic variants or regions are evolutionarily conserved, functionally important, or bounded by TF regulators across major projects (ENCODE, JASPAR, ReMap).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fucsc_conservation_and_tfbs\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M74MWERYHSY87P21FDMVE6BA","string-database","Query the STRING database for protein-protein interactions (PPIs), functional enrichment, and homology. Use when the user asks about interactions between specific proteins, interaction evidence, confidence scores, protein interaction partners, or pathway enrichments.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fstring_database\u002FSKILL.md",[],[]]