{"skill":{"slug":"semantic-paper-radar","displayName":"Semantic Paper Radar","summary":"Semantic literature discovery and synthesis across arXiv/OpenAlex/PubMed (and optional Google Scholar adapters). Use when users ask for domain must-read pape...","description":"---\nname: semantic-paper-radar\ndescription: Semantic literature discovery and synthesis across arXiv/OpenAlex/PubMed (and optional Google Scholar adapters). Use when users ask for domain must-read papers, research trend mapping, paper recommendations, reading lists, or academic lineage/context for a topic in natural science, AI, engineering, medicine, or interdisciplinary research.\n---\n\n# Semantic Paper Radar\n\nBuild a domain reading list from natural-language intent, then output a concise research map.\n\n## Workflow\n\n1. Clarify query intent in one line:\n   - topic + scope + time window + priority (`foundational` / `frontier` / `balanced`).\n2. Run aggregated retrieval:\n   - General: `python3 scripts/paper_radar.py search --query \"<topic>\" --max 40 --years 8`\n   - Biomedical force-on: `python3 scripts/paper_radar.py search --query \"<topic>\" --max 40 --years 8 --biomed`\n3. Generate synthesis report:\n   - `python3 scripts/paper_radar.py report --query \"<topic>\" --max 40 --years 8 --top 12 --mode balanced`\n   - Biomedical force-on: add `--biomed`\n   - Export clickable HTML: add `--export-html` (optional `--html-out <path>`)\n\n4. Present results in Chinese unless user asked otherwise:\n   - 必读文献（分层）\n   - 学术脉络（时间线）\n   - 阅读顺序（先读3篇）\n   - 可选下一步（细分子方向）\n\n## Output Rules\n\n- Prefer OpenAlex entries with DOI/citation metadata for \"经典\" judgement.\n- Keep arXiv entries for \"最新前沿\" and unreviewed but high-momentum work.\n- If the query is biomedical/clinical, explicitly include a caution that arXiv papers may be preprint.\n- If retrieval is sparse, broaden query with synonyms and rerun once.\n\n## Recommended Prompt Pattern\n\nUse this framing when user asks for recommendations:\n\n- \"按 `经典奠基(3-5)` + `方法跃迁(3-5)` + `近两年新进展(3-5)` 输出\"\n- \"每篇给：一句贡献、为什么必读、适合第几步读\"\n- \"最后给该领域 3 条学术脉络主线\"\n\n## Optional Scholar Integration\n\nIf the environment already has a Scholar-capable tool/skill (e.g., serper-scholar), call it after `report` and use it only for:\n- citation cross-check\n- venue/author authority补充\n\nDo not block core workflow if Scholar integration is unavailable.\n","topics":["Arxiv"],"tags":{"latest":"0.1.0"},"stats":{"comments":0,"downloads":1814,"installsAllTime":69,"installsCurrent":7,"stars":1,"versions":1},"createdAt":1772539204056,"updatedAt":1778994820271},"latestVersion":{"version":"0.1.0","createdAt":1772539204056,"changelog":"Initial open-source release: arXiv/OpenAlex/PubMed semantic search, clickable links, milestones, HTML export.","license":null},"metadata":null,"owner":{"handle":"rogerrrr18","userId":"s17etrbtda050n9s21fmgge5xx86a1w2","displayName":"Roger Yang","image":"https://avatars.githubusercontent.com/u/198148965?v=4"},"moderation":null}