agentleFS
leoleolroleoleolro/career-os/.claude/skills/offer-review/SKILL.md

offer-review

Skill0 starsChanged 56 days agoMITView on GitHub

Decode and benchmark a job offer (Australian employment specifics), compare against current role and other offers, and script the negotiation. Use when the candidate says "offer", "they offered", "should I accept", "negotiate", "review this contract", "/offer-review".

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. CaesiumY/claude-interview-agents★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository15 other files it gives its agents.

The file

Files
SKILL.md

/offer-review <file in inbox/ | pasted terms>

1. Extract the terms into a table

Base salary (ex/inc super — AU super guarantee is 12% from 1 July 2025; confirm which the letter means), bonus (target %, discretionary?), equity/RSUs (vesting, cliff), sign-on, relocation, allowances, leave (annual/personal/parental), probation, notice period (both directions), restraint of trade / non-compete / non-solicit (duration, geography — enforceability in AU is limited but still matters), IP/moonlighting clauses (matters if you have side projects or a business), remote/hybrid terms, start date, title/level, review cycle, training budget, visa/citizenship clauses (n/a — Australian citizen), any clawbacks. Flag anything missing or ambiguous as a question for the employer.

2. Benchmark

  • Compare to the candidate's current package (ask if not in profile/career-context.md) and any other live offers in data/pipeline.json.
  • Market: use WebSearch for AU salary guides (Hays, Robert Half, Michael Page, Glassdoor/Levels.fyi for AI roles) for the title + city + years; cite sources; give a range, not a point.
  • Total-comp view over 12 and 36 months (base + super + expected bonus + equity at conservative value − relocation costs).
  • Non-money: path fit (/career-path), learning, brand, manager quality, exit options.

3. Negotiation script

  • Decide the ask: base first (a specific number, anchored on the benchmark and a competing offer/current package), then sign-on/relocation, then start date/leave. One ask per message.
  • Draft the email/call script in the candidate's voice, polite and firm, with fallbacks. Note timing (respond within the stated window; ask for it in writing).
  • What not to say (don't invent competing offers; don't accept verbally before the letter).

4. Decision aid

A one-page reports/offer-<company>-<today>.md: terms table, benchmark, red flags, the ask, and a plain recommendation with the reasoning. the candidate decides; record the outcome with node tools/track.mjs move <id> offer|closed --note "…".

This is general information, not legal advice — for restraint or IP clauses that worry them, suggest a 30-minute employment-lawyer review (often free via union/professional association).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.