dispute-identification

dispute-identification is a skill for Claude Code from vivy-yi/finance-skills. It costs 87 tokens per session (2,254 once invoked), scanned A, a copy of luban, MIT.

A process for finding repeated or connected irregularities in employee expense claims and supplier payments. It combines signals such as invoice problems, policy violations, approval differences, and rejected claims.

In plain words
What is it for?
Use it after invoice checks, policy checks, or three-way matching to identify high-frequency exceptions, claims near approval limits, repeated supplier activity, and cases that need escalation.
Why use it?
A single review may miss patterns spread across many claims or people. Looking across records can reveal repeated anomalies, possible split purchases, or supplier concentration risks.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md.

Good fit Use it after invoice checks, policy checks, or three-way matching to identify high-frequency exceptions, claims near approval limits, repeated supplier activity, and cases that need escalation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vivy-yi/finance-skills/dispute-identification
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 vivy-yi/finance-skills --skill dispute-identification
Clone the repo
git clone --depth 1 https://github.com/vivy-yi/finance-skills

Made for: Claude Code.

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 dispute-identification

README.md
[![agentmods](https://agentmods.dev/badge/skills/vivy-yi/finance-skills/dispute-identification/github.svg)](https://agentmods.dev/skills/vivy-yi/finance-skills/dispute-identification)
Your own site
<a href="https://agentmods.dev/skills/vivy-yi/finance-skills/dispute-identification"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/dispute-identification/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 dispute-identification

Your own site · 80×15
<a href="https://agentmods.dev/skills/vivy-yi/finance-skills/dispute-identification"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/dispute-identification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,254 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 80% copy Near-identical to another mod 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 $0.00087 $0.02254
Opus 5 $0.00044 $0.01127
Sonnet 5 $0.00017 $0.00451
Haiku 4.5 $0.00009 $0.00225

Measured 12d ago against content hash c992b8fefb9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dispute-identification 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 12d 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.

Origin

This is a copy

80% identical to luban — 595 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

finance-skills/skills/expense-review/skills/dispute-identification/SKILL.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

加载上下文

首次使用时: 读取 ../../CLAUDE.md 获取场景级配置(升级门槛/异常定义)。


/dispute-identification — 报销异常识别

Examples

→ 示例:用户说"供应商发票有争议,金额和合同不一致,帮我怎么处理",系统应调用本技能,执行发票争议识别和分类。

→ 示例:用户说"帮我们分析一下最近有哪些发票争议,是价格问题还是质量问题",系统应调用本技能,分析发票争议模式和频率。

→ 示例:用户说"有个供应商发了三次催款函了,说我们一直不处理争议",系统应调用本技能,评估争议处理延迟的信用风险。

与其他 Skill 的关系

前置 Skill: 通常在其他原子 Skill 执行后,对综合结果进行二次风险扫描。

不是:

  • 替代发票验真(invoice-verification)
  • 替代标准检查(policy-compliance-check)
  • 替代三单匹配(triple-match-automation)

是:

  • 跨节点模式识别(员工历史行为/跨维度异常)
  • 风险等级重评估(基于模式识别提升风险等级)
  • 升级决策触发(超出单节点判断能力的复杂异常)

异常模式识别

模式一:高频异常员工识别

识别逻辑:

统计维度:同一员工,同一自然月内
计数项:
  - 发票异常次数
  - 标准超标次数
  - 三单差异次数
  - 被驳回次数

触发阈值:
  - 任一单项 ≥ 2 次
  - 或异常总次数 ≥ 3 次

→ 🔴 升级至财务专员
→ 记录为"高频异常关注对象"

模式二:金额临界规避识别

识别逻辑:

识别特征:
  - 报销金额紧贴审批权限边界(如 4999 元 / 9999 元)
  - 同一供应商的连续报销金额均在某一审批权限以下
  - 同一费用类型(如"办公用品")反复小额报销

触发阈值:
  - 同一员工同一供应商 30 天内 ≥ 3 笔,金额均在 5000 元以下
  - 或金额分布呈现明显的"分档聚集"特征(如 4900-4999 区间异常集中)

→ ⚠️ 标记"疑似分拆报销"
→ 要求提供完整采购记录
→ 如无法证明拆分合理性 → 升级至财务经理

模式三:供应商集中风险

识别逻辑:

统计维度:同一供应商,所有员工报销汇总
计数项:
  - 30 天内对该供应商的报销笔数
  - 30 天内对该供应商的报销总额
  - 该供应商的发票异常记录

触发阈值:
  - 30 天内报销笔数 ≥ 5 笔
  - 且总金额 ≥ [填空:如 20 万元]
  - 或发票异常 ≥ 1 次

→ 🔴 升级至财务专员
→ 核查该供应商是否在白名单内
→ 必要时触发供应商重新资质审查

模式四:时间集中异常

识别逻辑:

识别特征:
  - 同一员工在报销截止日前 3 天内集中提交大量报销
  - 季末/年最后 1-2 个工作日集中提交(可能是突击花钱)
  - 跨年后 5 个工作日内集中提交上年费用(跨期报销高峰)

触发阈值:
  - 截止日前 3 天内提交笔数 ≥ 5 笔
  - 或单日提交金额 ≥ [填空:如 10 万元]

→ ⚠️ 标注"集中报销,核查真实性"
→ 必要时要求抽查原始凭证

模式五:关联关系异常

识别逻辑:

识别特征:
  - 报销员工为供应商的关联方(查询[GOV]供应商股东穿透)
  - 审批人与报销人存在上下级/亲属关系
  - 报销金额与员工职级明显不匹配(普通员工报销高管级标准)

触发阈值:
  - 任一关联关系被识别

→ 🔴 直接升级至财务经理
→ 不自行判断,记录为高风险案例

模式六:跨期异常模式

识别逻辑:

识别特征:
  - 连续 3 个月以上在月末最后 5 天提交报销
  - 费用发生时间与报销提交时间间隔规律性超 60 天
  - 每年固定时间(如 12 月)集中报销大量上一年度费用

触发阈值:
  - 规律性月末集中提交 ≥ 3 次
  - 或规律性跨期 ≥ 60 天 ≥ 3 次

→ ⚠️ 标注"跨期规律异常"
→ 要求说明情况
→ 如无合理解释 → 🔴 升级财务专员

风险等级重评估

当上述任一模式被触发时,重新评估风险等级

初始风险等级(由其他 Skill 输出)

初始结论 初始风险
全部原子 Skill 均通过
部分 Skill 有 ⚠️ 提示
任一 Skill 有 ❌ 驳回
任一 Skill 有 🔴 升级

Read the full file on GitHub · 271 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. 12d ago First seen · 271 lines · 87 tokens per session scan A c992b8fefb9d

Subscribe to this mod's changes

dispute-identification is a skill published in the GitHub repository vivy-yi/finance-skills (29 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 2,254 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 80% identical to luban, differing in 595 lines, and is treated as a copy.

Related

Other skills, from other repositories

wealth-structure

A framework for thinking about wealth through ownership, responsibility, leverage, and avoiding risks that could end your progress.

kangarooking/cangjie-skill · 141 tokens

alpha-vantage

Access real-time and historical stock market data, forex rates, cryptocurrency prices, commodities, economic indicators, and 50+ technical indicators via the Alpha Vantage API. Use when fetching stock prices (OHLCV), company fundamentals (income statement, balance sheet, cash flow), earnings, options data, market…

foryourhealth111-pixel/Vibe-Skills · 126 tokens

hedgefundmonitor

Query the OFR (Office of Financial Research) Hedge Fund Monitor API for hedge fund data including SEC Form PF aggregated statistics, CFTC Traders in Financial Futures, FICC Sponsored Repo volumes, and FRB SCOOS dealer financing terms. Access time series data on hedge fund size, leverage, counterparties, liquidity…

foryourhealth111-pixel/Vibe-Skills · 123 tokens

edgartools

Python library for accessing, analyzing, and extracting data from SEC EDGAR filings. Use when working with SEC filings, financial statements (income statement, balance sheet, cash flow), XBRL financial data, insider trading (Form 4), institutional holdings (13F), company financials, annual/quarterly reports (10-K…

foryourhealth111-pixel/Vibe-Skills · 110 tokens

asc-ppp-pricing

Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands. Use when adjusting prices by country or implementing localized PPP strategies.

rorkai/app-store-connect-cli-skills · 45 tokens

fred-economic-data

Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources. Access GDP, unemployment, inflation, interest rates, exchange rates, housing, and regional data. Use for macroeconomic analysis, financial research, policy studies, economic forecasting, and academic research requiring…

foryourhealth111-pixel/Vibe-Skills · 75 tokens