What makes Payroll Data Audit notable?

1.8K downloads. Trust evidence available

How should Payroll Data Audit be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Payroll Data Audit

工资数据审核系统，基于确定性规则引擎 + Python 脚本执行。全量对齐《工资审核标准流程 SOP》6 步流程。v7.2 修复P0阻断bug：_get_pay_month() 支持中文格式（"2026年4月"/"2026年04月"/"202604"），RL-003/RL-007 排除逻辑完全生效。 v7.1... Skill: Payroll Data Audit Owner: tuobadaidai Summary: 工资数据审核系统，基于确定性规则引擎 + Python 脚本执行。全量对齐《工资审核标准流程 SOP》6 步流程。v7.2 修复P0阻断bug：_get_pay_month() 支持中文格式（"2026年4月"/"2026年04月"/"202604"），RL-003/RL-007 排除逻辑完全生效。 v7.1... Tags: latest:7.4.1 Version history: v6.2.3 | 2026-07-24T09:18:50.184Z | user Restore from backup - payroll data audit system v7.4.1 | 2026-06-05T09:02:37.485Z | user v7.4.1: SKILL.md 标题对齐版本号 + deliver_to_f

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.8k

Updated

Oct 10, 2026

Version

6.2.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.8K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.8K downloadsadoption · observed Oct 10, 2026
Latest release: 6.2.3release · observed Jul 24, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: medium.

clawhub skill install s171s30jbmhtrc2kxbr4hxmyn583gsk3:payroll-data-audit

Python environment detected. Create a strict virtual environment (`python -m venv .venv`) before installing dependencies to prevent system-level package conflicts.
Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-tuobadaidai-payroll-data-audit/snapshot"

Documentation

CLAWHUB

155,607 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: payroll-data-audit
version: 6.2.2
description: 工资数据审核系统，基于确定性规则引擎 + Python 脚本执行。
  全量对齐《工资审核标准流程 SOP》6 步流程。v6.2 新增总审核报告（Master Report）、
  规则判定过程详解（judgment）、黄线排除逻辑完善。v6.2.1 新增编排指南：单节点原则。
  Use when user asks to 工资数据审核、薪资校验、算薪逻辑验证、薪酬合规检查、
  工资单审核、月度薪资校验、发薪前数据检查、payroll audit、salary check、
  wage verification、payroll compliance.
  不适用于非薪酬类数据审核、纯算薪操作（非审核）、外部薪酬调研、个税/社保计算.
  此技能需手动触发.
---

# Payroll Data Audit v6.2

**架构原则**：确定性操作下沉到代码，模糊推理留给 LLM。AI 不做计算和判断，只做路由决策和报告翻译。

## 概述

工资数据审核系统，全量对齐《工资审核标准流程 SOP》6 步流程，对飞书/SAP/ADP 导出的工资表执行自动化合规校验。SOP 覆盖率 95%（41/43 项）。

### v6.2 新功能

- **总审核报告（Master Report）**：Phase 7/7，将数据扫描、审核结果、判定过程、问题清单、抽样校验聚合为一份完整的 HTML 总报告（`06_master_report.html`）
- **规则判定过程详解（judgment）**：每条规则输出 `judgment` 字段，包含规则逻辑、检查范围、排除人数及原因、实际检查人数、通过率、判定结论，让看报告的人能看到"怎么判的、排了谁、阈值是什么"
- **黄线排除逻辑完善**：YL-001~004、YL-006 新增实习生/日薪/保洁/当月入职/当月离职排除；YL-005（出勤天数超计薪天数）不排除任何人（数据质量问题全员检查）

### v6.0 新功能

- **表格化报告**：整体以表格形式呈现，信息密度高，替代 v5 的卡片+SVG 风格
- **动态交互看板**：支持筛选/排序/搜索/展开明细/导出CSV/深色模式（零依赖，纯内嵌JS）
- **数据支撑索引**：`data_index.json` 作为报告和看板的关联核心，保证数据一致性
- **三者联动**：报告 ↔ 看板 ↔ 数据索引，通过 rule_id 双向锚定

### 功能范围

- **SOP 第一步（强制）**：数据扫描确认（发薪月/公司主体/计薪项/特殊人员/工号重复检测）
- 字段完整性检查（30+ 列名容错映射）
- 公式校验（Decimal 精度，0.01 容差）
- 业务逻辑校验（出勤工资/天数/绩效系数/加班/最低工资）
- 红线校验（实发≤0、加班超36h、低于最低工资、社保未缴）
- 黄线校验（绩效异常、出勤超限、工资波动）
- 蓝线校验（跨月趋势，仅提示）
- 政策校验（道旅国际豁免、15号后入职、实习生/保洁豁免、离职当月社保）
- 人数对比分析（新入职/离职/波动>5%）
- 总额环比分析（12项计薪科目，±10%阈值自动标记）
- 分主体/分四级部门对比（按公司主体分组环比）
- 按人深入分析（连续在职筛选+排除逻辑+六类变化分类+核实标记）
- HTML/Markdown 审核报告生成
- **数据支撑**：每个审核结论必须有数据依据
- **审核清单看板**：完整条目清单（结果+数据依据+处理建议），HTML+Markdown 双格式
- **分段审核**：7阶段独立执行，避免上下文截断，支持断点续传
- **抽样校验**：随机抽样+独立重算+偏差检测，二次确认审核结果
- **超链接复核**：异常项可点击复核链接（支持 {emp_id}/{emp_name}/{row_index}）
- **端到端流水线**：`run_full_pipeline.py` 一键跑完不中断（数据扫描→审核→报告→看板→抽样→问题清单→总审核报告）

**不覆盖**：实际算薪操作、薪酬市场调研、个税计算、社保核算。

### SOP 流程映射

| SOP 步骤 | 本 Skill 对应 | 说明 |
|---------|-------------|------|
| 第一步：审核流程（强制） | `data_scan.py` + 用户确认 | **禁止跳步** |
| 第二步：数据逻辑验证 | `rules_engine.py` 公式+业务逻辑 | 公式校验+5项业务规则 |
| 第三步：异常数据扫描 | `rules_engine.py` 红/黄/蓝线 | 4红+6黄+4蓝 |
| 第四步：总额对比分析 | `rules_engine.py --prev` 总额环比 | ±10%阈值 |
| 第五步：按人深入分析 | `rules_engine.py --prev` 按人分析 | 排除+6类变化 |
| 第六步：汇总审核报告 | `generate_report.py` / `generate_report_v6.py` | 结构化报告（v5）/ 表格化报告（v6） |
| 第七步：审核清单看板 | `generate_kanban.py` / `generate_kanban_v6.py` | 静态看板（v5）/ 动态交互看板（v6） |
| 第八步：抽样校验 | `sampling_verify.py` | 二次确认审核结果 |
| 数据支撑索引 | `generate_data_index.py` | 三者关联核心（报告↔看板↔数据） |
|| 分段审核编排 | `run_audit.py` | 7阶段独立执行+断点续传 |
|| 端到端流水线 | `run_full_pipeline.py` | 一键跑完不中断，始终生成所有输出（含总报告） |
|| 总审核报告 | `generate_master_report.py` | 聚合所有输出为一份完整 HTML 总报告 |

## 使用

### 决策路由

先判断用户需求属于哪类场景，再执行对应流程：

| 用户说的 | 匹配场景 | 执行 |
|---------|---------|------|
| "帮我审核本月工资数据" | 完整审核 (Step 1→6) | 先 data_scan → 用户确认 → run_full_audit |
| "快速看看有没有问题" | 红线校验 | `--step red_lines` |
| "发薪前帮我理一下数据" | 字段检查 | `--step fields` |
| "帮我验一下公式对不对" | 公式校验 | `--step formulas` |
| "帮我出个审核报告" | 报告生成 | `generate_report.py` |
| "帮我出个表格版审核报告" | 报告生成 v6 | `generate_report_v6.py` |
| "帮我出个审核清单

_meta.json

{
  "ownerId": "kn70tx725606ywwb5gfj0vpxjx83admr",
  "slug": "payroll-data-audit",
  "version": "6.2.3",
  "publishedAt": 1784884730184
}

scripts/rules.json

{
  "version": "5.1.0",
  "metadata": {
    "lastUpdated": "2026-06-01",
    "updatedBy": "HRCOE",
    "description": "工资数据审核规则库，所有阈值和逻辑以本文件为准。全量对齐SOP v1.0",
    "changelog": "v5.1.0: 新增道旅国际社保/公积金豁免政策(POL-004/POL-005); 新增业务逻辑校验规则(BR-001~BR-004); 新增按人分析排除条件(person_analysis_exclusions); 新增请假>2天排除逻辑; 新增多主体发薪检测"
  },
  "thresholds": {
    "overtime_limit": 36,
    "overtime_unit": "hour",
    "overtime_breakdown": [
      "平时加班时数",
      "周末加班时数",
      "法定加班时数"
    ],
    "min_wage_default": 2360,
    "min_wage_shenzhen": 2360,
    "min_wage_guangzhou": 2300,
    "min_wage_dongguan": 1900,
    "perf_coefficient_max": 1.5,
    "perf_coefficient_min": 0.5,
    "perf_coefficient_swing": 0.5,
    "bonus_volatility_threshold": 0.5,
    "supply_volatility_threshold": 5000,
    "headcount_variance_threshold": 0.05,
    "supply_months_tolerance": 2
  },
  "red_lines": [
    {
      "id": "RL-001",
      "name": "实发≤0",
      "description": "实发金额合计≤0，必须立即核实",
      "condition": "sum(实发金额合计) <= 0",
      "field": "实发金额合计",
      "exclusions": [],
      "severity": "BLOCK",
      "action": "stop_and_alert"
    },
    {
      "id": "RL-002",
      "name": "加班超36h",
      "description": "月加班总时数>36小时，违反劳动法",
      "condition": "sum(平时加班时数 + 周末加班时数 + 法定加班时数) > 36",
      "field": "平时加班时数",
      "exclusions": [
        "当月入职",
        "当月离职",
        "实习生",
        "保洁",
        "请假超过15天"
      ],
      "severity": "BLOCK",
      "action": "stop_and_alert"
    },
    {
      "id": "RL-003",
      "name": "低于最低工资",
      "description": "应发合计低于当地最低工资标准",
      "condition": "应发合计 < 当地最低工资",
      "field": "应发合计",
      "exclusions": [
        "实习生",
        "保洁",
        "当月长时间请假",
        "当月入职",
        "当月离职"
      ],
      "severity": "BLOCK",
      "action": "stop_and_alert"
    },
    {
      "id": "RL-004",
      "name": "社保公积金应缴未缴",
      "description": "不符合豁免政策但个人社保/公积金扣款为0",
      "condition": "不符合豁免政策 AND 个人社保 == 0",
      "field": "个人社保",
      "exclusions": [
        "实习生",
        "日薪",
        "保洁"
      ],
      "severity": "BLOCK",
      "action": "stop_and_alert"
    }
  ],
  "yellow_lines": [
    {
      "id": "YL-001",
      "name": "绩效系数过高",
      "threshold": 1.5,
      "field": "绩效系数",
      "description": "绩效系数>1.5，需核实是否有特殊贡献依据",
      "action": "flag_and_explain",
      "exclusions": ["实习生", "日薪", "保洁", "当月入职", "当月离职"]
    },
    {
      "id": "YL-002",
      "name": "绩效系数过低",
      "threshold": 0.5,
      "field": "绩效系数",
      "description": "绩效系数<0.5，需核实绩效评估是否合理",
      "action": "flag_and_explain",
      "exclusions": ["实习生", "日薪", "保洁", "当月入职", "当月离职"]
    },
    {
      "id": "YL-003",
      "name": "绩效系数月度波动大",
      "threshold": 0.5,
      "field": "绩效系数",
      "description": "本月系数与上月系数差值>0.5，需核实评估依据",
      "action": "flag_and_explain",
      "exclusions": ["实习生", "日薪", "保洁", "当月入职", "当月离职"]
    },
    {
      "id": "YL-004",
      "name": "住宿扣款变化",
      "threshold": 0,
      "field": "住宿扣款",
      "description": "本月住宿扣款与上月不一致，需确认是

skill-card.md

## Description: <br>
Payroll Data Audit helps agents run deterministic payroll-data checks and produce audit reports for CSV or Excel payroll exports. <br>

This skill is ready for commercial/non-commercial use. <br>

## Publisher: <br>
[tuobadaidai](https://clawhub.ai/user/tuobadaidai) <br>

### License/Terms of Use: <br>
MIT-0 <br>


## Use Case: <br>
HR, payroll, and finance reviewers use this skill to audit monthly payroll exports before payroll release, validate formulas and policy rules, compare current and prior periods, and create data-backed issue reports. <br>

### Deployment Geography for Use: <br>
Global <br>

## Known Risks and Mitigations: <br>
Risk: Payroll inputs and generated reports can contain sensitive employee compensation data. <br>
Mitigation: Run the skill only on authorized payroll data, write outputs to restricted directories, and treat generated JSON, Markdown, HTML, and issue reports as sensitive files. <br>
Risk: Review-link URLs may expose raw employee identifiers if configured with employee fields. <br>
Mitigation: Use review links that avoid raw employee identifiers or route through an access-controlled internal system. <br>
Risk: Generated HTML reports may carry weak privacy and HTML-safety guardrails. <br>
Mitigation: Review, redact, or sanitize generated HTML before sharing outside the payroll review group. <br>
Risk: Payroll audit conclusions may be misleading if source data or red-line findings are not reviewed. <br>
Mitigation: Complete the data-scan confirmation step and have qualified payroll reviewers validate blocking findings before using outputs for payroll decisions. <br>


## Reference(s): <br>
- [ClawHub skill page](https://clawhub.ai/tuobadaidai/skills/payroll-data-audit) <br>
- [Publisher profile](https://clawhub.ai/user/tuobadaidai) <br>


## Skill Output: <br>
**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance] <br>
**Output Format:** [Markdown guidance with shell commands; generated audit artifacts may include JSON, Markdown, HTML, and CSV-style exports.] <br>
**Output Parameters:** [1D] <br>
**Other Properties Related to Output:** [Processes payroll CSV or Excel inputs and writes persistent audit outputs to caller-selected paths.] <br>

## Skill Version(s): <br>
6.2.3 (source: server release evidence; artifact frontmatter reports 6.2.2) <br>

## Ethical Considerations: <br>
Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>

requirements.txt

pandas>=2.0.0
numpy>=1.24.0
openpyxl>=3.1.0

Github ReposUpdated 9h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.