AD hipaa-guard
HIPAA 美国医疗健康护栏 (hipaa-guard) v1.0.0。 在面向美国市场的医疗健康产品（远程医疗 / 医疗 SaaS / 健康 App / 患者门户） 的文案、隐私政策、产品描述发布前，实时检测触发 HIPAA 适用的表述与医疗隐私 违规用语，按风险分级输出命中与整改建议，供 Agent 主动调用。区别于事后深度审计，这是事前拦截。 Use when: 需要在发布医疗健康产品的文案 / 隐私政策 / 产品描述前， 实时拦截"处理受保护健康信息(PHI)"触发 HIPAA 适用的表述，以及缺少商业伙伴 协议(BAA)、PHI 未加密、第三方披露 PHI、缺失泄露通知、限制个人访问权等 高频违规表达；防止触碰 HIPAA 隐私规则 / 安全规则 / 泄露通知规则红线； 为中国出海企业/医疗科技团队加装一道轻量实时医疗隐私合规护栏。 核心能力： - 🛡️ 实时检测 6 类医疗隐私触发/违规：处理 PHI / 缺少 BAA / PHI 未加密 / 第三方披露 PHI / 缺失泄露通知 / 限制个人访问权 - 📊 风险分级（high / medium / low）与逐条整改建议 - 🔍 重叠命中智能去重（保留高 severity / 更长匹配），降低误报 - 📋 结构化 JSON 输出，便于 Agent 程序化调用与批量扫描 - 🧱 内核与规则分离：规则集中在 scripts/rules/terms.py，追加词即可扩展 触发关键词：HIPAA、医疗隐私、受保护健康信息、PHI、商业伙伴协议、BAA、 医疗 SaaS、远程医疗、患者数据、泄露通知、hipaa-guard 适用范围：面向美国市场的医疗健康产品文案 / 隐私政策 / 产品描述的发布前实时检测 运行模式：纯本地，零网络请求，零动态执行 外部依赖：Python 标准库（无需额外安装） 本产品为免费护栏，纯本地运行，零网络请求，文本输入即可评估。
HIPAA 美国医疗健康护栏 (hipaa-guard) v1.0.0。 在面向美国市场的医疗健康产品（远程医疗 / 医疗 SaaS / 健康 App / 患者门户） 的文案、隐私政策、产品描述发布前，实时检测触发 HIPAA 适用的表述与医疗隐私 违规用语，按风险分级输出命中与整改建议，供 Agent…
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 46/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 933 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 829: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 15 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (1 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.