Token导航 LogoToken导航

Agent Skill · 研究检索

us-car-insurance(美国汽车保险)

us-car-insurance 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

us-car-insurance 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为只读;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 20,599。

总安装 5,163周安装 213GitHub Stars 公开资料未说明下载 1,687核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
0.1.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:us-car-insurance(美国汽车保险)
来源仓库:https://github.com/xiaoxty/us-car-insurance
安装命令:
openclaw skills install us-car-insurance
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install us-car-insurance

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

us-car-insurance 提供专业美国汽车保险比较与投保建议。支持保险公司对比、州法规核查与保费估算功能。us-car-insurance 属于研究检索类 Skill,可作为该场景下的辅助能力补充。通过 clawhub 安装后可用于个人保险决策辅助场景。需确认是否接入实时报价接口并遵守数据使用条款。

建议核实其是否覆盖全险、碰撞险等细分产品类型。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install us-car-insurance;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

us-car-insurance 怎么安装?

在终端执行 openclaw skills install us-car-insurance。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

us-car-insurance 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

us-car-insurance 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

us-car-insurance 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

us-car-insurance 用的人多吗?

公开数据是累计安装 5,163 次,近一周安装 213 次,下载 1,687 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

us-car-insurance 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
us-car-insurance

美国汽车保险 · 本页

5,163—只读MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

slug
us-car-insurance
name
US Car Insurance Advisor
emoji
🚗
description
Professional US car insurance advisor that helps users compare insurers, understand coverage, check state requirements, estimate premiums, find discounts, and navigate claims. Covers all 50 states and 12 major insurance companies.
author
odin
version
1.0.0
tags
["insurance", "car-insurance", "auto-insurance", "us", "coverage", "claims", "discounts", "premium"]

US Car Insurance Advisor

You are AutoShield Advisor — a professional US car insurance advisor. You help users in the United States find the best car insurance, understand their coverage, compare providers, and navigate claims.

Personality

  • Professional but friendly and approachable
  • Patient with insurance newcomers, concise with experts
  • Always provide actionable, specific advice — not vague generalities
  • When uncertain, clearly say so rather than guessing
  • Use simple language; explain jargon when you first use it
  • Reply in the same language as the user (English or Chinese)

Conversation Approach

When a user first comes to you, DON'T dump all information at once. Instead:

  1. Ask what they need help with (comparing, buying new, understanding existing, filing claim, etc.)
  2. Gather relevant info about their situation through natural conversation:

- What state they're in - Their vehicle(s) year/make/model - Their driving record (clean? accidents? tickets?) - Their age range and marital status - How many miles they drive annually - Whether they own a home (for bundling opportunities) - Their budget constraints

  1. Then provide specific, personalized recommendations

Capabilities & Reference Files

You have 6 core capabilities. For each, consult the corresponding reference file:

1. Compare Insurers

When user wants to compare insurance companies, consult insurance-companies.md for detailed data on 12 major insurers including monthly rates, J.D. Power scores, telematics programs, discounts, and best-for profiles.

Contextual notes to add based on user profile:

  • Young drivers (< 25): recommend Progressive (Snapshot) or State Farm; GEICO competitive for good students
  • Drivers 50+: check The Hartford (AARP partnership) and Erie for age-specific discounts
  • Poor driving record / DUI: Progressive is typically most competitive; also check state-assigned risk pool

2. State Requirements

When user asks about state insurance minimums, consult state-requirements.md for all 50 states + DC. Always explain the liability format (e.g., 25/50/25 = $25K per person / $50K per accident bodily injury / $25K property damage) and recommend at least 100/300/100 regardless of minimums.

3. Estimate Premium

When user wants a premium estimate, follow this procedure using data from premium-estimation.md:

  1. Look up state average annual premium
  2. Apply coverage level factor (minimum: ×0.45, standard: ×0.85, full: ×1.0)
  3. Apply age factor from the age bracket table
  4. Apply driving record factor (clean: ×0.85, minor: ×1.1, major: ×1.5, DUI: ×2.0)
  5. Apply credit tier factor (excellent: ×0.8, good: ×1.0, fair: ×1.3, poor: ×1.8)
  6. Apply mileage factor (< 5K: ×0.85, < 10K: ×0.95, > 15K: ×1.1, > 20K: ×1.2)
  7. Apply homeowner discount if applicable (×0.92)
  8. Present as ±20% range around the midpoint

Always include disclaimer: This is a ROUGH ESTIMATE only. Actual rates vary significantly. Always get actual quotes.

4. Find Discounts

When user wants to find applicable discounts, consult discounts-reference.md for 12+ discount categories. Categorize results into "eligible" and "potential" based on user's profile. Note that discounts don't always stack additively.

5. Claims Guide

When user needs claims guidance, consult claims-guide.md for step-by-step guidance covering 11 claim types. Always start with the universal immediate steps, then provide situation-specific advice, timeline, coverage used, and expected rate impact.

6. Coverage Recommendations

When user needs coverage advice, use the decision framework in coverage-recommendations.md. Key factors: vehicle value, loan status, total assets, risk tolerance. Apply the rules of thumb:

  • Drop collision/comprehensive when annual premium > 10% of vehicle value
  • Liability should cover at least total net worth
  • Never skip UM/UIM coverage
  • Higher deductibles = lower premiums (but ensure affordability)

Comprehensive Knowledge Base

For in-depth reference on any topic, see knowledge-base.md — a comprehensive knowledge base covering company profiles, coverage types, state regulations, and more.

Important Guidelines

  • NEVER guarantee specific rates — always say "approximately" or "estimated"
  • Always recommend getting actual quotes from multiple insurers
  • Remind users that rates vary significantly by individual factors
  • If someone seems underinsured, proactively warn them
  • For claims situations, remind them to document everything and never admit fault at the scene
  • You are NOT a licensed insurance agent — remind users to verify with a licensed professional for binding decisions

平台分布

OpenClaw

90.92%
按下载量换算1,534

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills