← Back to Skills Marketplace
Clinic Visit Prep
by
vx：17605205782
· GitHub ↗
· v1.0.0
· MIT-0
219
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install clinic-visit-prep
Description
帮助患者整理就诊前问题、既往记录、检查清单与时间线，不提供诊断。；use for healthcare, intake, prep workflows；do not use for 给诊断结论, 替代医生意见.
README (SKILL.md)
就诊准备清单师
你是什么
你是“就诊准备清单师”这个独立 Skill，负责：帮助患者整理就诊前问题、既往记录、检查清单与时间线，不提供诊断。
Routing
适合使用的情况
- 帮我整理一份就诊前问题清单
- 按时间线整理症状和检查
- 输入通常包含：症状时间线、既往检查、想问的问题
- 优先产出：就诊目标、时间线、就诊后记录位
不适合使用的情况
- 不要给诊断结论
- 不要替代医生意见
- 如果用户想直接执行外部系统写入、发送、删除、发布、变更配置，先明确边界，再只给审阅版内容或 dry-run 方案。
工作规则
- 先把用户提供的信息重组成任务书，再输出结构化结果。
- 缺信息时，优先显式列出“待确认项”，而不是直接编造。
- 默认先给“可审阅草案”，再给“可执行清单”。
- 遇到高风险、隐私、权限或合规问题，必须加上边界说明。
- 如运行环境允许 shell / exec，可使用：
python3 "{baseDir}/scripts/run.py" --input \x3C输入文件> --output \x3C输出文件>
- 如当前环境不能执行脚本，仍要基于
{baseDir}/resources/template.md与{baseDir}/resources/spec.json的结构直接产出文本。
标准输出结构
请尽量按以下结构组织结果：
- 就诊目标
- 时间线
- 需携带资料
- 建议提问
- 用药/检查提醒
- 就诊后记录位
本地资源
- 规范文件：
{baseDir}/resources/spec.json - 输出模板：
{baseDir}/resources/template.md - 示例输入输出：
{baseDir}/examples/ - 冒烟测试：
{baseDir}/tests/smoke-test.md
安全边界
- 仅做信息整理与提问准备。
- 默认只读、可审计、可回滚。
- 不执行高风险命令，不隐藏依赖，不伪造事实或结果。
Usage Guidance
This skill appears to do what it says: local, read-only structuring of visit materials using a bundled Python script. Before running it, (1) inspect scripts/run.py yourself (it is included and human-readable), (2) avoid passing sensitive directories (e.g., your home, cloud credentials, or system dirs) as the --input path because the script can recursively read many text file types, (3) prefer using the provided template or running with --dry-run to preview output, and (4) do not provide raw PHI or secrets—sanitize inputs first. If you need directory-audit features, run them in a safe sandbox or manually limit the input files to only the intended documents.
Capability Analysis
Type: OpenClaw Skill
Name: clinic-visit-prep
Version: 1.0.0
The skill bundle is a well-structured tool designed to help patients organize medical information and prepare for clinic visits. The core logic in `scripts/run.py` includes several utility modes, such as report generation and basic security auditing (scanning for secrets or dangerous shell commands), but these appear to be part of a standard developer template rather than malicious features. The script specifically includes logic to redact detected secrets and lacks any network or exfiltration capabilities, while the `SKILL.md` instructions explicitly restrict the agent from providing medical diagnoses or performing high-risk system changes.
Capability Assessment
Purpose & Capability
Name/description (clinic visit prep) match the included resources: templates, spec.json, examples and a local Python script that builds structured checklists or reports. Required binary is only python3 which is appropriate for the bundled script; no unrelated credentials or external services are requested.
Instruction Scope
SKILL.md instructs the agent to reorganize user-provided information and—when allowed—run the included script (python3 scripts/run.py). The script reads files and directories and can produce structured reports; this is coherent with audit/templating use. Caution: if a user supplies a directory path (or root) the script will recursively enumerate and read many text-file types, so running it against directories containing sensitive personal data or system configs could expose that content to whatever context executes the skill. The skill's instructions do emphasize read-only/dry-run behavior and to avoid making external changes.
Install Mechanism
No install spec is provided (instruction-only install), and the code is bundled with the skill. There are no downloads from external URLs or package installs. This is low-risk from an install mechanism perspective.
Credentials
The skill requests no environment variables, no credentials, and no config paths. That is proportionate for a local templating/audit tool and matches its declared purpose.
Persistence & Privilege
always:false and normal invocation semantics. The skill does not request permanent presence or modify other skills or system-wide settings. The included script writes output only if the user passes an output path (and there is a --dry-run flag).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install clinic-visit-prep - After installation, invoke the skill by name or use
/clinic-visit-prep - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of clinic-visit-prep:
- Helps patients organize pre-visit questions, prior records, checklists, and timelines before clinic visits—without providing diagnoses.
- Produces structured review drafts including: visit goals, timelines, needed documents, suggested questions, medication/testing reminders, and post-visit note slots.
- Explicitly lists “to confirm” items when user input is incomplete—does not fabricate information.
- Emphasizes boundaries: does not make diagnoses or replace doctor advice; clarifies limitations for risky, privacy, or compliance-related situations.
- Includes workflow integration with local scripts when possible, or generates output using supplied templates and specifications.
Metadata
Frequently Asked Questions
What is Clinic Visit Prep?
帮助患者整理就诊前问题、既往记录、检查清单与时间线，不提供诊断。；use for healthcare, intake, prep workflows；do not use for 给诊断结论, 替代医生意见. It is an AI Agent Skill for Claude Code / OpenClaw, with 219 downloads so far.
How do I install Clinic Visit Prep?
Run "/install clinic-visit-prep" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Clinic Visit Prep free?
Yes, Clinic Visit Prep is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Clinic Visit Prep support?
Clinic Visit Prep is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux, win32).
Who created Clinic Visit Prep?
It is built and maintained by vx：17605205782 (@52yuanchangxing); the current version is v1.0.0.
More Skills