← Back to Skills Marketplace
jiwenbing

Sdbao

by Wenbing Ji · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
146
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install sdbao
Description
水滴保险经纪综合服务助手(sdbao)。支持查看精选保险产品推荐、登记用户购险线索给经纪人、产品咨询、理赔协助和保单管理。当用户询问水滴保险产品、想了解精选险种、需要经纪人联系、或需要水滴系保险服务时使用。
Usage Guidance
This skill appears to do what it claims (show insurance options and register leads) and does not install code or request secrets. Important considerations before installing/using: 1) It collects PII and health information — confirm you have the user's consent and limit what you collect to the minimum required. 2) Ask where lead data will be sent/stored and for how long (the skill text does not specify an endpoint or retention policy). 3) Do not supply highly sensitive identifiers (national ID, bank details) unless you verify secure transmission to an official, trusted endpoint. 4) Verify the broker identity and official contact channels if a user expects follow-up. 5) If you operate in a jurisdiction with data-protection rules, ensure the handling of personal/health data complies with those laws. Overall: functionally coherent, but treat data-handling and privacy procedures as the primary risk area.
Capability Analysis
Type: OpenClaw Skill Name: sdbao Version: 1.0.0 The skill bundle is a standard insurance service assistant designed to provide product recommendations and collect lead information (name, phone number, and insurance interests). It consists entirely of Markdown instructions and product data (SKILL.md, products.md) without any executable code, scripts, or hidden network calls. The data collection is transparently aligned with its stated purpose of connecting users with insurance brokers.
Capability Assessment
Purpose & Capability
Name, description, and included product list (products.md) align with an insurance-broker assistant. The skill requests no unrelated binaries, env vars, or config paths — everything requested is minimal and proportionate to the stated purpose.
Instruction Scope
Runtime instructions require collecting personal data (name, phone, age, health summary) and instruct the agent to produce a structured lead card. The SKILL.md does not specify where or how leads are transmitted, stored, or protected, which is a privacy/handling gap rather than a direct mismatch with purpose.
Install Mechanism
No install spec and no code files — instruction-only skill. This minimizes code-execution and supply-chain risk.
Credentials
The skill declares no required environment variables, credentials, or config paths. Requested user inputs (phone, name, etc.) are expected for a lead-capture skill; however, collecting health-related descriptions is sensitive and should be explicitly justified and protected.
Persistence & Privilege
always is false and the skill does not request persistent system privileges. There is no indication it modifies other skills or system configs.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install sdbao
  3. After installation, invoke the skill by name or use /sdbao
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release
Metadata
Slug sdbao
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Sdbao?

水滴保险经纪综合服务助手(sdbao)。支持查看精选保险产品推荐、登记用户购险线索给经纪人、产品咨询、理赔协助和保单管理。当用户询问水滴保险产品、想了解精选险种、需要经纪人联系、或需要水滴系保险服务时使用。 It is an AI Agent Skill for Claude Code / OpenClaw, with 146 downloads so far.

How do I install Sdbao?

Run "/install sdbao" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Sdbao free?

Yes, Sdbao is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Sdbao support?

Sdbao is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Sdbao?

It is built and maintained by Wenbing Ji (@jiwenbing); the current version is v1.0.0.

💬 Comments