domains / families / general / family-health-analyzer

family-health-analyzer

combined

分析家族病史、评估遗传风险、识别家庭健康模式、提供个性化预防建议 整理家族病史和已知健康记录，识别需要医生或遗传咨询师评估的线索，不计算未经验证的个体发病概率

When to use

• 需要分析家族病史、遗传风险或家庭层面的健康模式时使用。
• 任务涉及家庭健康报告、家族聚集性疾病识别或预防建议生成。
• 需要把多个家庭成员的健康数据汇总后做趋势或风险评估。

When not to use

• 中文是原始受众语言，不是缺陷；按用户指定语言交互。原文已包含明确医学免责声明，必须保留。
• data/*.json 和 /family 命令属于外部应用约定，AAS未分发这些数据、运行时或算法；先定位用户明确授权的真实数据源，不伪造成功命令。
• 家庭/遗传信息高度敏感，仅收集获得同意的最小字段，匿名化亲属记录并私有保存；不得因亲属关联推定某人诊断。
• [CDC家族健康史说明](https://www.cdc.gov/family-health-history/about/index.html)强调与医疗专业人员讨论；此技能不提供医学诊断、治疗或自行更改筛查方案。
• Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
• Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

Skill page

Conflict

The two copies share the same eight-step workflow, data sources, and safety boundaries, but they disagree on the core analytical step. The FreedomIntelligence copy prescribes a specific weighted risk-scoring formula (0.4/0.3/0.3 weights, 70% high-risk threshold) and a fixed 'early onset <50' rule. The sickn33 copy explicitly forbids that uncalibrated formula, replaces it with descriptive recording of known history, and defers risk judgment to a clinician or genetic counselor. Because one copy's central step is the negation of the other's, crowning one would hide a real, safety-relevant alternative.