offer-decode — Claude Code skill: offer analysis
The offer-decode Claude Code skill breaks down a job offer and estimates take-home pay. It runs on an offer letter, a CTC breakdown, or a request to compare terms and draft a negotiation reply.
MIT ★ 345 updated 2026-11-14
/plugin marketplace add nishant-Tiwari24/cracked
/plugin install cracked@crackedWhat offer-decode does
The skill separates fixed and variable pay, one-time compensation, equity, and benefits. For multiple offers, it compares recurring and first-year cash, estimated take-home pay, and terms such as bonds or notice periods. It can also draft a negotiation message.
For salary estimates in India, it needs INDIA-CTC.md and Python 3; scripts/ctc.py calculates tax and pay using stated assumptions. The agent also calls the cracked-profile skill for the country and city. It saves the analysis to $CRACKED_DIR/offers/<company>-<date>.md.
What it helps with
- separate take-home cash from deferred compensation
- estimate monthly pay after tax
- spot bonds, bonus clawbacks, or restrictive terms
- compare offers by cash and employment terms
- draft a request for higher fixed pay
Example prompts for the agent
- Break down this offer letter and estimate my monthly take-home pay.
- Compare these two offers by recurring pay, bonuses, and terms.
- Draft a polite reply asking for a higher fixed salary.
How to install offer-decode
1Plugin marketplace
/plugin marketplace add nishant-Tiwari24/cracked/plugin install cracked@crackedThis installs the whole cracked plugin with all its skills
2Skills CLI (Vercel)
npx skills add nishant-Tiwari24/cracked --skill offer-decode -a claude-code3Manually: put the files in place
~/.claude/skills/offer-decode/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/offer-decode/
1Skills CLI (Vercel)
npx skills add nishant-Tiwari24/cracked --skill offer-decode -a codex2Manually: put the files in place
.agents/skills/offer-decode/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add nishant-Tiwari24/cracked --skill offer-decode -a cursor2Manually: put the files in place
.cursor/skills/offer-decode/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install nishant-Tiwari24/cracked skills/strategy/offer-decode2Manually: put the files in place
.github/skills/offer-decode/SKILL.md1Skills CLI (Vercel)
npx skills add nishant-Tiwari24/cracked --skill offer-decode -a gemini-cli2Platform CLI
gemini skills install https://github.com/nishant-Tiwari24/cracked --path skills/strategy/offer-decodeManually: put the files in place
.devin/skills/offer-decode/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about offer-decode
How do I install offer-decode in Claude Code?
Add the marketplace with /plugin marketplace add nishant-Tiwari24/cracked, then install the skill with /plugin install cracked@cracked.
What does offer-decode do?
It breaks down compensation, estimates monthly take-home pay, flags terms such as bonds, and compares offers. It can also draft a negotiation message.
What does offer-decode need to work?
For salary estimates in India, it needs Python 3 and INDIA-CTC.md; the calculation uses scripts/ctc.py. The agent also calls the cracked-profile skill for country and city details.
Source text
SKILL.md · MIT
---
name: offer-decode
description: Decode a tech job offer or CTC breakup into what the candidate actually takes home. It separates fixed, variable, one-time and deferred pay (ESOPs/RSUs), estimates monthly in-hand salary with stated assumptions, flags red flags (bonds, clawbacks, inflated CTC, notice period, non-competes), compares multiple offers side by side, and drafts a negotiation reply. Use when the user has an offer letter, a CTC breakup, wants to compare offers, asks "what is my in-hand salary", or wants to negotiate an offer.
---
# Offer decode
"₹18 LPA" can mean ₹1.05 lakh a month in hand, or ₹80,000 with a ₹2 lakh bond. Candidates routinely pick the worse offer because of how the CTC was written. Decode it properly.
## 0. Inputs
1. Call the Skill tool with "cracked-profile" (country; current location and city matter for rent and professional tax).
2. Get the offer(s): offer letter PDF, CTC annexure, a screenshot, or typed numbers. Read every page. Bonds, clawbacks and notice periods hide in annexures and the fine print.
3. If you're comparing offers, collect all of them before analysing.
## 1. Break it down
For each offer, build this table (annual and monthly):
| Component | Annual | Monthly | Category |
|---|---|---|---|
Categories:
- **Fixed cash**: basic, HRA, special allowance, other fixed allowances
- **Variable**: performance bonus. Note the *target* % and whether it's guaranteed. Ask the user for the company's historical payout. If it's unknown, show 0%, 70% and 100% payout side by side and label it an assumption (the calculator does this).
- **One-time**: joining/sign-on bonus, relocation. Check for clawbacks ("repayable if you leave within 12 months").
- **Deferred / equity**: ESOPs, RSUs. Note the vesting schedule, cliff, strike price (ESOPs), and liquidity (private company ESOPs may never be sellable).
- **Benefits counted in CTC**: employer PF, gratuity, insurance premiums, meal cards, NPS. These are real money but **not in-hand cash**.
**Year-1 cash** = fixed + expected variable + one-time.
**Recurring cash** = fixed + expected variable.
Show both. The headline CTC is neither.
## 2. Estimate in-hand
For India, use [INDIA-CTC.md](INDIA-CTC.md) and run the calculator rather than doing the maths yourself: `python3 scripts/ctc.py --fixed <annual fixed> --variable <annual bonus> --regime both [--rent <annual rent> --metro] [--pt <professional tax>] [--pf capped|full] [--wage-rule basic|labour-code]`. Paste its table. If you change an assumption, rerun it. For other countries, estimate with the main tax and social-security components (e.g. US: federal + state + FICA, 401k if stated), and say which ones you included.
Rules:
- **Tax rules change every year.** If you have a web tool, verify the current slabs for the relevant financial year before computing. If not, use the reference values, name the year they're from, and say so clearly.
- Show the calculation step by step, and state every assumption (tax regime, PF on full basic vs capped, professional-tax state, rent).
- Run arithmetic with the calculator or the shell, never in your head, and show the result.
- End with a **monthly in-hand estimate as a range** (e.g. ₹1.02–1.06 L), not false precision.
## 3. Red flags and fine print
Check and report each one:
- **Service bond / training bond**: amount, duration, enforceability concerns. State the facts and suggest they ask HR to clarify. You're not a lawyer.
- **Clawbacks** on joining bonus or relocation.
- **Variable %** that's high relative to fixed, or with vague payout conditions.
- **Notice period** (60–90 days hurts the next switch), **probation** terms, **non-compete / non-solicit**.
- **Inflated CTC**: insurance, gratuity, or one-time items padding the headline.
- **Joining date and location** flexibility; **relocation** support; **work mode**.
- ESOPs at early startups: high strike, short exercise window, or a 4-year vest with a 1-year cliff. Treat them as a lottery ticket, not salary.
## 4. Compare (if more than one offer)
Side-by-side table: recurring cash, year-1 cash, monthly in-hand, equity (with a "realistic value" note), bond, notice period, role/team, learning, location and cost of living (adjust in-hand for rent differences between cities), and brand/growth. Then a recommendation **with reasoning**, and the one factor that would flip it.
## 5. Negotiate (if they want to)
Draft a short, polite email or message: appreciation → a specific ask (a fixed-pay increase, joining bonus, waived bond, relocation, joining date) → justification (competing offer, market data the user provides, or their unique fit) → flexibility. Note that campus placement offers are usually non-negotiable; off-campus and lateral offers usually are.
## 6. Output
Save the analysis to `$CRACKED_DIR/offers/<company>-<date>.md`. No scorecard for this skill.
End with: "Estimates for planning only, not tax or legal advice. Confirm the final numbers with HR."
---
*Skill calls:* if your agent has no Skill tool, open the named skill's `SKILL.md` in the cracked skills folder (`core/`, `interview/`, `profile/`, `strategy/`) and follow it instead.
© Nishant Tiwari · MIT · nishant-Tiwari24/cracked