mcpField
C
compensation-benchmarking

compensation-benchmarking

github.com/anthropicsData & databases33.6k99 installsUpdated 1d ago
Repository

About compensation-benchmarking

A skill for benchmarking compensation for hiring, retention, and equity planning. It frames comparisons by role, level, location, company stage, and industry, and calls for percentile bands with source freshness and limitations noted.

Key features

  1. 01Break down total compensation components
  2. 02Compare roles, levels, and locations
  3. 03Account for company stage and industry
  4. 04Use verified or public salary data
  5. 05Report percentile bands and data limits

Use cases

  1. 01Set compensation ranges for hiring
  2. 02Review pay for retention planning
  3. 03Compare equity and cash compensation
  4. 04Adjust benchmarks by location and company stage

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/anthropics/knowledge-work-plugins --skill compensation-benchmarking

After installing, type/compensation-benchmarkingin Claude Code to confirm it loaded.

Details

From the project README

Compensation Benchmarking

Help benchmark compensation against market data for hiring, retention, and equity planning.

Framework

Components of Total Compensation
  • Base salary: Cash compensation
  • Equity: RSUs, stock options, or other equity
  • Bonus: Annual target bonus, signing bonus
  • Benefits: Health, retirement, perks (harder to quantify)
Key Variables
  • Role: Function and specialization
  • Level: IC levels, management levels
  • Location: Geographic pay adjustments
  • Company stage: Startup vs. growth vs. public
  • Industry: Tech vs. finance vs. healthcare

Data Sources

  • With ~~compensation data: Pull verified benchmarks
  • Without: Use web research, public salary data, and user-provided context
  • Always note data freshness and source limitations

Output

Provide percentile bands (25th, 50th, 75th, 90th) for base, equity, and total comp. Include location adjustments and company-stage context.

Comments

Markdown supported