Agent Skillsmohitagw15856/pm-claude-skills › pay-stub-decoder

pay-stub-decoder

GitHub

逐行解析工资单,解释扣款明细与净薪构成。提供收支瀑布图、常见错误检查清单(如预扣税、加班费、福利匹配)及薪资部门沟通话术,帮助用户发现并纠正工资计算错误。

exports/openclaw/pay-stub-decoder/SKILL.md mohitagw15856/pm-claude-skills

Trigger Scenarios

解释工资单 为什么工资比预期少 这些扣款是什么 检查工资单是否有误

Install

npx skills add mohitagw15856/pm-claude-skills --skill pay-stub-decoder -g -y
More Options

Non-standard path

npx skills add https://github.com/mohitagw15856/pm-claude-skills/tree/main/exports/openclaw/pay-stub-decoder -g -y

Use without installing

npx skills use mohitagw15856/pm-claude-skills@pay-stub-decoder

指定 Agent (Claude Code)

npx skills add mohitagw15856/pm-claude-skills --skill pay-stub-decoder -a claude-code -g -y

安装 repo 全部 skill

npx skills add mohitagw15856/pm-claude-skills --all -g -y

预览 repo 内 skill

npx skills add mohitagw15856/pm-claude-skills --list

SKILL.md

Frontmatter
{
    "name": "pay-stub-decoder",
    "homepage": "https:\/\/mohitagw15856.github.io\/pm-claude-skills\/skill\/pay-stub-decoder.html",
    "metadata": {
        "openclaw": {
            "emoji": "🧠"
        }
    },
    "description": "Decode a pay stub line by line — every deduction explained, the gross-to-net story, and the errors worth catching. Use when asked to explain my pay stub, why is my paycheck smaller than expected, what are all these deductions, or check my paycheck for mistakes. Produces a line-by-line decode, the gross-to-net waterfall, the error checklist (withholding, benefits, overtime), and the fixes to raise with payroll."
}

Pay Stub Decoder Skill

Most people can't explain a third of the lines on their own pay stub — which is exactly how errors survive for years. This skill decodes every line, shows the gross-to-net waterfall, and runs the error checklist: wrong withholding status, benefit deductions that don't match elections, missing overtime, and the retirement match that quietly isn't there.

What This Skill Produces

  • Line-by-line decode — every earning, tax, and deduction in plain English
  • The waterfall — gross → taxes → pre-tax deductions → post-tax → net, with percentages
  • The error checklist — run against the user's stated situation, discrepancies flagged
  • Payroll fixes — what to raise, with the wording

Required Inputs

Ask for these only if not provided:

  • The stub — lines and amounts (redact identifiers freely; the codes and numbers are what matter)
  • The expectations: stated salary/rate, hours if hourly, benefit elections (retirement %, insurance tier), filing status
  • Jurisdiction — tax lines and mandatory deductions vary by country/state; never guess
  • What prompted this — "smaller than expected" gets a targeted diff, not just a tour

Framework

  1. Codes to English: payroll abbreviations (the cryptic 6-character kind) decoded by pattern and context; anything genuinely ambiguous gets flagged ask payroll what this code means rather than guessed.
  2. Pre-tax vs post-tax matters: the waterfall shows where each deduction lands, because a pre-tax dollar costs less than a post-tax one — and misclassified deductions are a real error class.
  3. The five common errors: withholding status not matching filing reality · benefit deduction ≠ elected amount · missing/mis-multiplied overtime · retirement contribution or employer match absent or mismatched · state/locality taxes for the wrong place (remote-work classic).
  4. Annualize the surprises: a $38 mystery deduction is $988/year — every finding shows both numbers.
  5. Year-to-date is the audit trail: YTD columns catch errors the single stub hides (a match that stopped in March shows here first).

Output Format

Pay Stub Decode: [period]

The waterfall: Gross $[n] → taxes −$[n] ([n]%) → pre-tax −$[n] → post-tax −$[n] → Net $[n] ([n]% of gross)

Line decode | Line/code | Plain English | Amount | /year | Check | ⚠ Findings — each: the line, expected vs actual, the annualized gap, likely cause For payroll: [the message: specific lines, specific asks — payroll fixes line items, not feelings] Looks right: [the lines verified clean — decoded confidence, not just alarms]

End verbatim: "This is a plain-language reading, not tax or legal advice — payroll rules vary by jurisdiction; confirm anything load-bearing with payroll or a tax professional."

Quality Checks

  • Every line is decoded or explicitly flagged ask-payroll — none skipped
  • The waterfall reconciles to the stated net to the cent
  • Findings show single-period and annualized amounts
  • The error checklist ran against the user's stated elections
  • Clean lines are affirmed, not just silent
  • The disclaimer appears verbatim

Anti-Patterns

  • Do not guess ambiguous codes — a wrong decode plants a wrong grievance
  • Do not treat all deductions as losses — the waterfall distinguishes taxes, savings, and benefits
  • Do not skip YTD — the single stub hides what the year reveals
  • Do not draft an angry payroll email — line numbers and expected-vs-actual get fixes; tone gets ticket queues
  • Do not give tax advice — decode what IS withheld; what SHOULD be is a professional's call

Version History

  • 54fad50 Current 2026-07-19 12:27

Same Skill Collection

exports/openclaw/360-feedback-template/SKILL.md
exports/openclaw/401k-plan-decoder/SKILL.md
exports/openclaw/ab-test-planner/SKILL.md
exports/openclaw/ab-test-readout/SKILL.md
exports/openclaw/accessibility-audit/SKILL.md
exports/openclaw/account-plan/SKILL.md
exports/openclaw/acquirer-red-team/SKILL.md
exports/openclaw/ad-copy/SKILL.md
exports/openclaw/aeo-optimizer/SKILL.md
exports/openclaw/agenda-or-cancel/SKILL.md
exports/openclaw/agent-design-review/SKILL.md
exports/openclaw/agent-observability-spec/SKILL.md
exports/openclaw/agent-spec/SKILL.md
exports/openclaw/ai-ethics-review/SKILL.md
exports/openclaw/ai-eval-plan/SKILL.md
exports/openclaw/ai-feature-prd/SKILL.md
exports/openclaw/ai-product-canvas/SKILL.md
exports/openclaw/air-quality/SKILL.md
exports/openclaw/altitude-shifter/SKILL.md
exports/openclaw/ambiguity-resolver/SKILL.md
exports/openclaw/analyst-relations-brief/SKILL.md
exports/openclaw/announcement-card/SKILL.md
exports/openclaw/api-docs-writer/SKILL.md
exports/openclaw/api-test-plan/SKILL.md
exports/openclaw/api-versioning-strategy/SKILL.md
exports/openclaw/apology-letter/SKILL.md
exports/openclaw/architecture-decision-record/SKILL.md
exports/openclaw/architecture-diagram/SKILL.md
exports/openclaw/archive-strategy/SKILL.md
exports/openclaw/assumption-bounty/SKILL.md
exports/openclaw/assumption-mapper/SKILL.md
exports/openclaw/async-update-format/SKILL.md
exports/openclaw/auto-repair-estimate-decoder/SKILL.md
exports/openclaw/autopilot-charter/SKILL.md
exports/openclaw/benefits-decoder/SKILL.md
exports/openclaw/bid-tender-review/SKILL.md
exports/openclaw/board-deck-narrative/SKILL.md
exports/openclaw/board-minutes/SKILL.md
exports/openclaw/board-pre-read/SKILL.md
exports/openclaw/bom-cost-review/SKILL.md
exports/openclaw/bookkeeping-categorization/SKILL.md
exports/openclaw/boolean-search-builder/SKILL.md
exports/openclaw/brag-doc/SKILL.md
exports/openclaw/brainstorming/SKILL.md
exports/openclaw/brief-builder/SKILL.md
exports/openclaw/briefing-note/SKILL.md
exports/openclaw/budget-builder/SKILL.md
exports/openclaw/budget-variance-analysis/SKILL.md
exports/openclaw/bug-diagnosis/SKILL.md
exports/openclaw/bug-report/SKILL.md

Metadata

Files
0
Version
471c606
Hash
1178472b
Indexed
2026-07-19 12:27

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-30 23:47
浙ICP备14020137号-1 $방문자$