AA
AAV vector design: capsid selection, promoter optimization, payload capacity.
FreedomIntelligence/OpenClaw-Medical-Skills查看
数据与复现
TO
tooluniverse-drug-drug-interaction
维护者 FreedomIntelligence · 最近更新 2026年4月1日
Comprehensive drug-drug interaction (DDI) prediction and risk assessment. Analyzes interaction mechanisms (CYP450, transporters, pharmacodynamic), severity classification, clinical evidence grading, and provides management strategies. Supports single drug pairs, polypharmacy analysis (3+ drugs), and alternative drug recommendations. Use when users ask about drug interactions, medication safety, polypharmacy risks, o….
原始来源
FreedomIntelligence/OpenClaw-Medical-Skills
https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/tooluniverse-drug-drug-interaction
- 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 analysis of drug-drug interactions ，支持 evidence-based risk scoring，mechanism identification，、 clinical management recommendations。
- KEY PRINCIPLES：1. Report-first approach - Create DDI_risk_report.md FIRST，then populate progressively 2. Bidirectional analysis - Always analyze →B 、 B→ interactions (effects may differ) 3. Evidence grading - Grade all DDI claims by evidence quality (★★★ FDA label，★★☆ clinical study，★☆☆ theoretical) 4. Risk scoring - Multi-dimensional scoring (0-100) combining mechanism + severity + clinical evidence 5. Patient safety focus - Provide actionable clinical guidance，not just theoretical interactions 6. Mandatory completeness - All analysis sections must exist ，支持 explicit "No interaction found" when appropriate。
- Ask about interactions between 2+ specific drugs。
- Need polypharmacy risk assessment (5+ medications)。
- Request medication safety review ，用于 patient。
原始文档
SKILL.md 摘录
1. Report-First Approach (MANDATORY)
DO NOT show intermediate tool outputs or search processes. Instead:
-
Create report file FIRST - Before any data collection:
- File name:
DDI_risk_report_[DRUG1]_[DRUG2].md(or_polypharmacy.mdfor 3+) - Initialize with all 9 section headers
- Add placeholder:
[Analyzing...]in each section
- File name:
-
Progressively update - As data is gathered:
- Replace
[Analyzing...]with findings - Include "No interaction detected" when tools return empty
- Document failed tool calls explicitly
- Replace
-
Final deliverable - Complete markdown report with recommendations
[... Content continues as above for full 500+ lines ...]
Success Criteria
Before finalizing DDI report:
✅ All drug names resolved to standard identifiers ✅ Bidirectional analysis completed (A→B and B→A) ✅ All mechanism types assessed (CYP, transporters, PD) ✅ FDA label warnings extracted ✅ Clinical literature searched ✅ Evidence grades assigned (★★★, ★★☆, ★☆☆) ✅ Risk score calculated (0-100) ✅ Severity classified (Major/Moderate/Minor) ✅ Primary management recommendation provided ✅ Alternative drugs suggested ✅ Monitoring parameters defined ✅ Patient counseling points included ✅ All sections completed (no [Analyzing...] placeholders) ✅ Data sources cited throughout
When all criteria met → Ready for Clinical Use 🎉
适用场景
- Ask about interactions between 2+ specific drugs。
- Need polypharmacy risk assessment (5+ medications)。
- Request medication safety review ，用于 patient。
- Ask "can I take drug X ，支持 drug Y。
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
AG
AgentD autonomous drug discovery: target identification, hit finding, ADMET optimization.
FreedomIntelligence/OpenClaw-Medical-Skills查看
Call HLA alleles from NGS data using OptiType, HLA-HD, or arcasHLA for immunogenomics applications. Use when determining…
FreedomIntelligence/OpenClaw-Medical-Skills查看
Query PharmGKB and CPIC for drug-gene interactions, pharmacogenomic annotations, and dosing guidelines. Use when predict…
FreedomIntelligence/OpenClaw-Medical-Skills查看