AR
Design armored CAR-T cells with cytokine payloads and resistance mechanisms.
FreedomIntelligence/OpenClaw-Medical-Skills查看
数据与复现
TO
tooluniverse-literature-deep-research
维护者 FreedomIntelligence · 最近更新 2026年4月1日
Conduct comprehensive literature research with target disambiguation, evidence grading, and structured theme extraction. Creates a detailed report with mandatory completeness checklist, biological model synthesis, and testable hypotheses. For biological targets, resolves official IDs (Ensembl/UniProt), synonyms, naming collisions, and gathers expression/pathway context before literature search. Default deliverable i….
原始来源
FreedomIntelligence/OpenClaw-Medical-Skills
https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/tooluniverse-literature-deep-research
- 维护者
- FreedomIntelligence
- 许可
- MIT
- 最近更新
- 2026年4月1日
技能摘要
来自 SKILL.md 的关键信息
核心说明
- systematic approach to comprehensive literature research that starts ，支持 target disambiguation to prevent missing details，uses evidence grading to separate signal ，面向 noise，、 produces content-focused report ，支持 mandatory completeness sections。
- KEY PRINCIPLES：1. Target disambiguation FIRST - Resolve IDs，synonyms，naming collisions before literature search 2. Right-size deliverable - Use Factoid、Verification Mode ，用于 single，answerable questions；use full report mode ，用于 “deep research” 3. Report-first output - Default deliverable is report file；inline answer is allowed (、 recommended) ，用于 Factoid、Verification Mode 4. Evidence grading - Grade every claim by evidence strength (mechanistic paper vs screen hit vs review vs text-mined) 5. Mandatory completeness - All checklist sections must exist，even if "unknown/limited evidence" 6. Source attribution - Every piece of information traceable to database/tool 7. English-first queries - Always use English terms ，用于 literature searches 、 tool calls，even if user writes in another language. Only try original-language terms as fallback if English returns no results. Respond in user's language。
- Generated：[Date] Evidence cutoff：[Date]。
原始文档
SKILL.md 摘录
Mandatory Questions
- Target type: Is this a biological target (gene/protein), a general topic, or a disease?
- Scope: Is this a single factoid to verify (“Which antibiotic?”, “Which strain?”, “Which year?”) or a comprehensive/deep review?
- Known aliases: Any specific gene symbols or protein names you use?
- Constraints: Open access only? Include preprints? Specific organisms?
- Methods appendix: Do you want methodology details in a separate file?
Mode Selection (CRITICAL)
Pick exactly one mode based on the user’s intent and the question structure:
- Factoid / Verification Mode (single concrete question; answer should be a short phrase/sentence)
- Mini-review Mode (narrow topic; 1–3 pages of synthesis)
- Full Deep-Research Mode (use the full template + completeness checklist)
Heuristic:
- If the user asks “X has been evolved to be resistant to which antibiotic?” → Factoid / Verification Mode
- If the user asks “What does the literature say about X?” → Full Deep-Research Mode
Factoid / Verification Mode (Fast Path)
Goal: Provide a correct, source-verified single answer, with minimal but explicit evidence attribution.
Deliverables (still file-backed):
[topic]_factcheck_report.md(≤ 1 page)[topic]_bibliography.json(+ CSV) containing the key paper(s)
Fact-check report template:
适用场景
- 适合在users need thorough literature reviews，target profiles，或 to verify specific claims ，面向 literature时使用。
不适用场景
- Do not rely on this catalog entry alone ，用于 installation 或 maintenance details。
相关技能
相关技能
AR
数据与复现
arxiv-search
Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic sea…
FreedomIntelligence/OpenClaw-Medical-Skills查看
AU
Autonomous oncology research agent: literature mining, trial matching, biomarker analysis, and treatment hypothesis gene…
FreedomIntelligence/OpenClaw-Medical-Skills查看
BI
Preprocesses cell-free DNA sequencing data including adapter trimming, alignment optimized for short fragments, and UMI-…
FreedomIntelligence/OpenClaw-Medical-Skills查看