Agent skill

Pay Stub Decoder

by mohitagw15856 in mohitagw15856/pm-claude-skills

Decode a pay stub line by line — every deduction explained, the gross-to-net story, and the errors worth catching.

MITAuto-check passed

Install Pay Stub Decoder

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill pay-stub-decoder -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills pay-stub-decoder --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/pay-stub-decoder .claude/skills/pay-stub-decoder && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pay-stub-decoder
GitHub stars
1.4k
Token cost
~1.1k tokens
SKILL.md length
533 words
Files
2 (incl. references)
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Decode a pay stub line by line — every deduction explained, the gross-to-net story, and the errors worth catching.

  • Works in 5 steps: Codes to English: payroll abbreviations… → Pre-tax vs post-tax matters: the… → The five common errors: withholding… → …
  • Asked to explain my pay stub
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework and Output Format, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pay Stub Decoder is an agent skill from mohitagw15856/pm-claude-skills. 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.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/worked-example.md`).

The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked to explain my pay stub
  • Why is my paycheck smaller than expected
  • What are all these deductions
  • Check my paycheck for mistakes

Example prompts

  • “/pay-stub-decoder”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Codes to English: payroll abbreviations (the cryptic 6-character kind) decoded by pattern and context; anything genuinely ambiguous gets…
  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…
  3. The five common errors: withholding status not matching filing reality · benefit deduction ≠ elected amount · missing/mis-multiplied…
  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).

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pay Stub Decoder loads about 1.1k tokens when it runs, and up to ~2.5k if it reads all its reference files. Until then it costs about 108 tokens; SKILL.md has 533 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~108
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 533 words, ~1,075 tokens.

Download SKILL.mdSave it as .claude/skills/pay-stub-decoder/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
pay-stub-decoder
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

Show full SKILL.md (235 more words)Show less
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

Example Trigger Phrases

  • "Explain my pay stub."
  • "Why is my paycheck smaller than expected?"
  • "What are all these deductions?"
  • "Check my paycheck for mistakes."

© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/pay-stub-decoder of mohitagw15856/pm-claude-skills.

  • SKILL.md
  • references/worked-example.md

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Pay Stub Decoder next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pay Stub Decoder compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pay Stub Decoder this skillmohitagw15856/pm-claude-skills1.4k—~1.1kAutomated safety check: PassMIT
Speculative DecodingOrchestra-Research/AI-Research-SKILLs13k2 repos~3.5kAutomated safety check: PassMIT
Explain Usageasgeirtj/system_prompts_leaks69k—~345Automated safety check: PassCC0-1.0
Logic Explainsickn33/agentic-awesome-skills47k1 repos~894Automated safety check: PassMIT
Faceless Explainer Videoheygen-com/hyperframes59k3 repos~7.7kAutomated safety check: NotesApache-2.0
PR Explainermastra-ai/mastra29k—~1.4kAutomated safety check: PassCustom licence

Similar skills

  • Speculative Decoding

    Orchestra-Research/AI-Research-SKILLs

    Explains three ways to speed up LLM inference: draft-model speculative decoding, Medusa heads and lookahead decoding with Jacobi iteration, and when each one fits.

    13k GitHub starsUsed in 2 repos~3.5k tokens
    AI & LLM EngineeringAuto-check passed
  • Explain Usage

    asgeirtj/system_prompts_leaks

    Explain where this session's tokens went, with one simple chart in plain language.

    69k GitHub stars~345 tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Logic Explain

    sickn33/agentic-awesome-skills

    Explain what a specific piece of code actually does for a given input by producing a step-by-step execution trace (interprocedural, with name resolution and type transitions).

    47k GitHub starsUsed in 1 repo~894 tokens
    Auto-check passed
  • Faceless Explainer Video

    heygen-com/hyperframes

    Turns an article, notes or a topic brief into an explainer video whose visuals are invented per scene, built frame by frame in HyperFrames with no footage.

    59k GitHub starsUsed in 3 repos~7.7k tokens
    Media & CreativeAuto-check: notes
  • PR Explainer

    mastra-ai/mastra

    A skill your agent uses when creating an approachable, self-contained HTML review aid for a pull request; explaining what changed, why it matters, how it works, and how it fits into the broader…

    29k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Understand Explain

    Egonex-AI/Understand-Anything

    Gives an in-depth explanation of one file, function or module by reading the project's knowledge graph and checking that the graph is still fresh.

    86k GitHub stars~1.3k tokensUpdated today
    DevelopmentAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Pay Stub Decoder

What does Pay Stub Decoder do?

Decode a pay stub line by line — every deduction explained, the gross-to-net story, and the errors worth catching. Pay Stub Decoder is an agent skill from mohitagw15856/pm-claude-skills. Decode a pay stub line by line — every deduction explained, the gross-to-net story, and the errors worth catching.

When should I use Pay Stub Decoder?

Pay Stub Decoder fits situations like: asked to explain my pay stub; why is my paycheck smaller than expected; what are all these deductions; check my paycheck for mistakes.

How do I install Pay Stub Decoder in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill pay-stub-decoder -a claude-code`. Or copy the skill folder (skills/pay-stub-decoder in mohitagw15856/pm-claude-skills) into .claude/skills/pay-stub-decoder in your project. Claude Code loads it when a task matches its description.

How do I install Pay Stub Decoder in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill pay-stub-decoder -a codex`. Or copy the skill folder (skills/pay-stub-decoder in mohitagw15856/pm-claude-skills) into .agents/skills/pay-stub-decoder in your project. Codex loads it when a task matches its description.

Can I use Pay Stub Decoder in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill pay-stub-decoder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pay-stub-decoder, .gemini/skills/pay-stub-decoder, .github/skills/pay-stub-decoder and .opencode/skills/pay-stub-decoder in your project.

What does Pay Stub Decoder need to run?

SKILL.md names no scripts, command-line tools or credentials: Pay Stub Decoder is instructions for the agent only.

Does Pay Stub Decoder access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Pay Stub Decoder safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Pay Stub Decoder use?

Pay Stub Decoder is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pay Stub Decoder use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.4k tokens, read only when the agent opens those files.

What are the alternatives to Pay Stub Decoder?

Skills that share tags, products or a category with Pay Stub Decoder: Speculative Decoding (Orchestra-Research/AI-Research-SKILLs, 13k stars), Explain Usage (asgeirtj/system_prompts_leaks, 69k stars), Logic Explain (sickn33/agentic-awesome-skills, 47k stars) and Faceless Explainer Video (heygen-com/hyperframes, 59k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pay Stub Decoder?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,433 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 8, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.