shiphrahx/ai-for-engineering-leaders/compensation-review
Claude Code and agent skill by shiphrahx/ai-for-engineering-leaders
- community
Checking that the SKILL.md file is still in the repository.
Produces a defensible compensation review for a direct report — the proposed increase, the new salary positioned against the band, the compa ratio, and any approval flags. Use when the user says "review [name]'s comp", "model this raise", "what does an X% increase look like", or pastes a current salary, a proposed increase, and the level band. Use this for the band-and-compa math behind a single person's raise — use promotion-case to argue a level change and offer-justification for a new-hire p…
Install
npx vskill@latest install shiphrahx/ai-for-engineering-leaders/compensation-reviewSKILL.md
Compensation Review
Position a proposed pay increase against the level band and compa ratio so the recommendation is defensible — not a number picked in isolation. Surface band breaches and high compa ratios before they reach an approver.
Inputs to gather
Gather these before calculating. If any are missing, ask in a single batched question — never invent salaries, increases, or band figures. Mark anything genuinely unavailable as Unknown.
- Person — name, current level
- Current salary — base, in the band's currency
- Proposed increase — as a fraction (e.g. 0.08 for 8%)
- Level band — minimum and maximum for the current level
Steps
- Confirm the band matches the person's current level — comparing against the wrong band invalidates the compa ratio.
- Run the calculator (below) to get the new salary, band position, and compa ratio. Use the printed figures verbatim.
- Write a one-paragraph recommendation — the increase, the new salary, where it sits in the band, and the rationale tied to performance or market, not tenure.
- If the calculator prints FLAGS (above ceiling, below floor, compa > 1.15), surface each explicitly and state the approval or correction needed before the increase can proceed.
- Run the calculator with the gathered inputs:
`` python scripts/calculate.py --current <value> --increase <value> --band-min <value> --band-max <value> `` Use the printed figures verbatim — do not recalculate manually. If FLAGS are printed, surface them explicitly to the user before proceeding.
Run the script. Fix every failure. Do not return output until the script passes.
Output format
Boundaries
- Never invent current salaries, increases, or band figures — mark unknowns as Unknown and ask.
- Never recommend an above-band increase without flagging it for approval — above-band without justification erodes comp integrity.
- Argue the increase from performance, scope, and market — never from tenure alone.
- This is a confidential people document — keep it private until shared through the proper channel.
Chaining
- If the review surfaces a level change rather than a within-band raise, offer promotion-case to argue the move on evidence.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/people-management/compensation-review/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/shiphrahx/ai-for-engineering-leaders/compensation-review)