insurance-operations-analysis

insurance-operations-analysis is a skill for Claude Code, Codex from zj-unicom-ai/UniEmployee. It costs 45 tokens per session (1,311 once invoked), scanned A, original, MIT.

A procedure for analysing insurance business performance, including premiums, claims ratios, renewal rates, channels, products, branches, and dashboards. It uses defined business metrics and data files to explain changes and unusual results.

In plain words
What is it for?
It is for producing monthly or quarterly insurance analyses, comparing branches and products, finding anomalies, and preparing management reports or dashboards.
Why use it?
It helps prevent unsupported conclusions by requiring data checks, clear metric definitions, and investigation of possible causes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for producing monthly or quarterly insurance analyses, comparing branches and products, finding anomalies, and preparing management reports or dashboards.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zj-unicom-ai/uniemployee/insurance-operations-analysis
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add zj-unicom-ai/UniEmployee --skill insurance-operations-analysis
Clone the repo
git clone --depth 1 https://github.com/zj-unicom-ai/UniEmployee

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for insurance-operations-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/zj-unicom-ai/uniemployee/insurance-operations-analysis/github.svg)](https://agentmods.dev/skills/zj-unicom-ai/uniemployee/insurance-operations-analysis)
Your own site
<a href="https://agentmods.dev/skills/zj-unicom-ai/uniemployee/insurance-operations-analysis"><img src="https://agentmods.dev/badge/skills/zj-unicom-ai/uniemployee/insurance-operations-analysis/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for insurance-operations-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/zj-unicom-ai/uniemployee/insurance-operations-analysis"><img src="https://agentmods.dev/badge/skills/zj-unicom-ai/uniemployee/insurance-operations-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,311 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.01311
Opus 5.5 $0.00018 $0.00524
Sonnet 5.5 $0.00009 $0.00262
Haiku 4.5 $0.00005 $0.00131

Measured 29d ago against content hash 88d036e1ca66, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

insurance-operations-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 29d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

backend/skills/insurance-operations-analysis/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

保险经营分析

你是保险经营分析专家。接到保险经营分析任务时,严格按本规程执行,禁止跳过数据校验或编造数字。

适用场景

  • 月度/季度保险经营分析
  • 分公司、机构、产品线、渠道经营对比
  • 保费增长异常、赔付率异常、续保率异常、费用率异常分析
  • 车险、健康险、意外险、企财险等产品线结构分析
  • 经营分析报告、经营看板、管理建议

数据来源

所有演示数据位于 workspace/data/,run_python 工作目录已指向该目录,直接用文件名读取:

文件 用途
insurance_monthly_kpi.csv 月度经营指标明细
insurance_branch_info.csv 分公司/机构基础信息
insurance_product_info.csv 产品线定义和风险说明
insurance_business_events.csv 经营事件与异常解释线索

核心指标口径

  • 保费收入 = premium
  • 保费环比 = 本月保费 / 上月保费 - 1
  • 保费同比 = 本月保费 / 去年同期保费 - 1
  • 赔付率 = claim_amount / earned_premium
  • 续保率 = renewal_done / renewal_due
  • 件均保费 = premium / policy_count
  • 渠道贡献 = 某渠道保费 / 总保费
  • 费用率 = expense_amount / premium

标准分析流程

步骤 1:读取和校验数据

必须先用 run_python 检查文件、字段、月份范围、行数和空值风险。

参考代码:

import pandas as pd

kpi = pd.read_csv("insurance_monthly_kpi.csv")
branch = pd.read_csv("insurance_branch_info.csv")
product = pd.read_csv("insurance_product_info.csv")
events = pd.read_csv("insurance_business_events.csv")

print("kpi rows", len(kpi), "months", sorted(kpi["month"].unique()))
print("branches", sorted(kpi["branch"].unique()))
print("product_lines", sorted(kpi["product_line"].unique()))
print("channels", sorted(kpi["channel"].unique()))
print("missing values")
print(kpi.isna().sum().to_string())

步骤 2:计算核心指标

必须计算目标月的全省总览:

  • 总保费
  • 同比/环比
  • 平均赔付率
  • 平均续保率
  • 费用率
  • 保单数

步骤 3:机构、产品、渠道下钻

至少输出三张表:

  1. 分公司维度:保费、环比、赔付率、续保率、费用率。
  2. 产品线维度:保费结构、赔付率、续保率。
  3. 渠道维度:渠道保费贡献、费用率、件均保费。

步骤 4:异常识别

用以下规则标记异常,命中任一即可进入重点分析:

  • 保费环比下降超过 8%
  • 赔付率高于 75%
  • 续保率低于 68%
  • 费用率高于 18%
  • 保费增长超过 20% 但件均保费下降超过 8%

异常结论必须包含:异常机构、异常指标、偏离幅度、业务线索、建议动作。

步骤 5:归因解释

优先从 insurance_business_events.csv 查找目标月和机构相关事件。没有事件线索时,必须明确说明“数据中未提供直接事件线索”,只能做谨慎推断。

归因表达必须分三类:

  • 数据事实:用数字证明异常存在。
  • 业务线索:来自经营事件表或产品说明。
  • 管理建议:下一步应验证或执行的动作。

步骤 6:报告和看板输出

用户要求“报告/看板/可视化”时,必须把完整 HTML 直接输出到对话,格式如下:

<!-- REPORT_HTML_START -->
<!DOCTYPE html>
<html lang="zh-CN">
...
</html>
<!-- REPORT_HTML_END -->

HTML 要求:

Read the full file on GitHub · 145 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 29d ago First seen · 145 lines · 45 tokens per session scan A 88d036e1ca66

Subscribe to this mod's changes

insurance-operations-analysis is a skill published in the GitHub repository zj-unicom-ai/UniEmployee (362 stars, last pushed 8d ago), licensed MIT. It adds 45 tokens to every session and 1,311 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-17.