← Back to Skills Marketplace
ryanbihai

Agent News Briefing

by ryanbihai · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
59
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install agent-news-briefing
Description
保险代理人每日重点新闻(健康、财经类)的背景深度搜索和解读,可直接发给客户(或作为朋友圈文案、群发话术),帮助代理人提升与客户的触达。结合Customer Profile Management技能,更可针对特定客户的画像(如关注比特币/新能源的客户)进行个性化新闻解读。触发场景:(1)生成当日新闻简报;(2)生成...
README (SKILL.md)

Agent News Briefing

保险代理人新闻简报技能,支持个性化客户画像匹配。

工作流程

Step 0 — 判断是否有客户个性化需求

用户触发时,检查是否指定了具体客户:

  • 有指定客户:先调用 customer-profile-management 查询该客户的档案,了解其关注领域、已有保单、家庭状况
  • 无指定客户:直接进入 Step 1,按通用逻辑处理

查询客户档案的命令:

# 查询客户基本信息(关注领域、风险偏好、家庭状况)
ls 客户档案/ | grep -i "\x3C客户姓名>"
# 读取客户档案内容
cat 客户档案/\x3C客户姓名>.md

客户画像关键字段(从档案中提取):

  • 关注领域:crypto新能源房产股票
  • 风险偏好:保守型稳健型积极型
  • 家庭状况:是否有子女、配偶、老人
  • 已有保障:哪些保险产品已购
  • 职业/收入:影响新闻解读角度

Step 1 — 搜索当日新闻

使用 web_search 搜索健康+保险+财经领域当日新闻:

基础关键词:

医保 最新政策
健康保险 新闻 今天
商业健康险 动态

按需叠加(用户指定或从客户画像推断):

  • 客户关注crypto/比特币→ 加搜:比特币 政策 监管
  • 客户关注新能源→ 加搜:新能源汽车 政策 补贴
  • 客户关注养老→ 加搜:养老金融 政策 保险
  • 客户关注健康→ 加搜:医保 创新药 惠民保

Step 2 — 精选 1-2 条最值得关注的新闻

筛选标准:

  • 有政策来源(官方文件、监管部门)
  • 与普通人生活相关
  • 有可解读的"客户价值点"

个性化筛选(针对指定客户时):

  • 优先选与客户关注领域相关的新闻
  • 考虑客户风险偏好:保守型客户多选保障类新闻,积极型客户可加入理财类视角

每条新闻输出:

  • 新闻标题 + 原文链接
  • 一句话摘要:普通人能听懂的话
  • 对目标客户意味着什么:结合该客户的画像来解读

Step 3 — 生成可发送的文案

对每条精选新闻,生成三种文案:

A. 朋友圈文案(100-200字)

  • 风格:亲切、专业、有温度,像朋友聊天
  • 目的:吸引客户点赞/评论,引发互动
  • 如有客户画像:可提及"做XX投资的朋友注意了"

B. 群发话术(50-100字)

  • 风格:简短、直接、可群发
  • 开头有称呼,结尾有 CTA
  • 如有客户画像:称呼用客户真实姓名

C. 客户问答预判

  • 预判该客户看完文案后会问什么问题
  • 给出简短回答

Step 4 — 个性化附加段(仅当有指定客户时)

当指定了客户,在结尾额外输出一段:

━━━ 🎯 针对{客户姓名}的个性化建议 ━━━

基于您的客户画像({风险偏好}、关注{领域}):

【新闻如何影响他/她】
{结合客户情况的个性化分析,50-100字}

【建议切入点】
{如何用这条新闻与该客户开启对话,1-2句话}

输出格式模板

通用版(无指定客户):

📰 【{日期} 健康新闻简报】

━━━ 📌 今日头条 ━━━
{新闻标题}
来源:{来源} | 链接:{链接}

📝 一句话解读:
{30字以内大白话}

💡 对客户意味着:
{50字以内}

━━━ 📱 发给客户的文案 ━━━

【朋友圈文案】
{100-200字}

【群发话术】
{称呼}您好!{50-100字}\
\
——来自您的专属保险顾问

❓ 客户可能问:
Q: {问题1}
A: {回答1}

Q: {问题2}
A: {回答2}

📌 投递说明:以上内容已生成。如需调整,请告诉我。

个性化版(有指定客户): 在通用版基础上,增加 Step 4 个性化附加段。

新闻来源优先级

  1. 国家医保局 (https://www.nhsa.gov.cn) — 医保目录、谈判、支付政策
  2. 国家卫健委 (https://www.nhc.gov.cn) — 医疗服务、公立医院改革
  3. 国家金融监督管理总局 (https://www.cbirc.gov.cn) — 保险产品监管政策
  4. 中国银行保险报 (https://www.cbimc.cn) — 保险行业综合报道
  5. 八点健闻 (https://www.healthinsight.com.cn) — 医疗健康深度报道
  6. 澎湃新闻健康 (https://www.thepaper.cn) — 热点健康事件大众解读

写作风格规则

  • ✅ 亲切、专业、有温度,像朋友聊天
  • ✅ 用"您"或"咱们",不用"该用户"
  • ✅ 有立场有观点,不做新闻搬运工
  • ✅ 主动说"建议联系您的保险顾问"
  • ❌ 避免"据悉"、"数据显示"等记者腔
  • ❌ 不承诺具体赔付,不夸大保障范围
  • ❌ 不对比具体公司产品
Usage Guidance
This skill looks like it will do what it promises (generate news briefs), but the runtime instructions tell the agent to read customer profile files from a local folder using shell commands even though the skill metadata declares no file-access path or permissions. Before installing or enabling this skill: - Verify where '客户档案/' would be located and whether that folder contains sensitive personal data. - Prefer changing the skill to call a controlled Customer Profile Management API (with an explicit required config path/credential) instead of running 'ls'/'cat' on arbitrary files. - If you must allow filesystem access, require the skill to declare the exact config path and limit the fields it reads (e.g., only '关注领域' and '风险偏好'), and log/alert such accesses. - Consider using manual invocation (or restricting autonomous runs) while testing, and audit any outputs before they are sent externally. - Ensure compliance with data-protection policies (consent, retention, masking) before allowing the skill to read or transmit customer data. If the missing config-path declaration was an oversight and the author can update the skill to explicitly request only the minimal, auditable access needed, the coherence and privacy concerns would be largely addressed.
Capability Analysis
Type: OpenClaw Skill Name: agent-news-briefing Version: 1.0.0 The skill is designed to help insurance agents generate personalized news briefings by reading local customer profiles and performing web searches. While it uses shell commands like 'ls' and 'cat' to access files in the '客户档案/' directory (SKILL.md), this behavior is explicitly documented and aligned with its stated purpose of customer profile management. No evidence of data exfiltration to external domains, credential theft, or malicious prompt injection was found.
Capability Tags
crypto
Capability Assessment
Purpose & Capability
The stated goal (produce personalized insurance news briefings) aligns with the actions described (search web, summarize, craft messaging). However, the skill's instructions assume access to a local '客户档案/' directory and the 'customer-profile-management' integration for personalization, yet the skill metadata declares no required config paths or credentials for accessing customer data. That omission is an inconsistency.
Instruction Scope
SKILL.md explicitly tells the agent to run shell commands (ls, cat) against local paths (客户档案/<客户姓名>.md) to extract sensitive customer profile fields. This is beyond what the declared requirements indicate and could expose personal data to the model or external services during execution. The instructions also use a generic 'web_search' tool (expected) and produce outbound content, which is coherent, but the file-read steps are scope-creep and privacy-sensitive.
Install Mechanism
No install spec and no code files — instruction-only. This minimizes disk-write risk. There is nothing being fetched or installed by the skill itself.
Credentials
No environment variables or credentials are requested, which is appropriate for a news-briefing skill. However, the skill expects to access local customer data files without declaring required config paths or permissions. That mismatch (undeclared file access) is a proportionality and transparency problem: personal data access should be explicit and limited to the fields needed for personalization.
Persistence & Privilege
The skill is not set to always:true and does not request special platform-wide privileges. Autonomous invocation is allowed (default), which increases blast radius if the skill is given access to private files — consider requiring manual invocation when personal data is involved.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install agent-news-briefing
  3. After installation, invoke the skill by name or use /agent-news-briefing
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
agent-news-briefing 1.0.0 - 首次发布,面向保险代理人,支持每日健康、财经类重点新闻的深度搜索与解读 - 可生成适合朋友圈、群发和客户个性化的多种文案 - 支持结合客户画像,提供针对性新闻分析和建议 - 按新闻权威性与客户相关性智能筛选,兼顾政策解读与客户沟通 - 明确输出结构:新闻摘要、客户价值、可发文案、问答预判和专属建议
Metadata
Slug agent-news-briefing
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Agent News Briefing?

保险代理人每日重点新闻(健康、财经类)的背景深度搜索和解读,可直接发给客户(或作为朋友圈文案、群发话术),帮助代理人提升与客户的触达。结合Customer Profile Management技能,更可针对特定客户的画像(如关注比特币/新能源的客户)进行个性化新闻解读。触发场景:(1)生成当日新闻简报;(2)生成... It is an AI Agent Skill for Claude Code / OpenClaw, with 59 downloads so far.

How do I install Agent News Briefing?

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

Is Agent News Briefing free?

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

Which platforms does Agent News Briefing support?

Agent News Briefing is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Agent News Briefing?

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

💬 Comments