Works with the AI Agents you already use
compensation structure and pay band analyzer
Compensation modeling is often prone to calculation errors, inconsistent rounding, and accidental privacy leaks when handling small groups.
$2.99
compensation structure and pay band analyzer
Example session with this skill installed
Review these pay bands for the Engineering job family in USD. Ensure midpoint progression is between 8% and 12%. Check if our midpoints match the provided 2024 Tech Survey medians.
- Read your context and instructions
- Compiled the compensation structure
Processed the pay band structure for Engineering. Calculated spreads, progressions, and market deltas using the deterministic analyzer.
Compensation Structure and Pay Band Analysis — Engineering, 2024-10-24
1. Scope, sources and assumptions
- Sources: E1 (Internal Pay Structure), E2 (2024 Tech Survey).
- Purpose: Band consistency and market alignment audit.
- Approved by: Total Rewards Director.
- Jurisdiction: US-CA.
- Min Group Size: 5.
2. Band structure
| Grade | Min | Mid | Max | Spread |
|---|---|---|---|---|
| E1 | 80,000 | 90,000 | 100,000 | 0.2500 |
| E2 | 92,000 | 105,800 | 119,600 | 0.3000 |
| E3 | 110,000 | 126,500 | 143,000 | 0.3000 |
| Pair | Midpoint progression | Overlap | Overlap share |
|---|---|---|---|
| E1-E2 | 0.1755 | 8,000 | 0.4000 |
| E2-E3 | 0.1956 | 9,600 | 0.3243 |
3. Findings
| Code | Grade or pair | Severity | Detail |
|---|---|---|---|
| PROG_HIGH | E1-E2 | Warning | Progression 17.55% exceeds policy limit of 12%. |
| PROG_HIGH | E2-E3 | Warning | Progression 19.56% exceeds policy limit of 12%. |
4. Market comparison
| Grade | Midpoint | Market Median | Variance | Source |
|---|---|---|---|---|
| E1 | 90,000 | 92,000 | -0.0217 | E2 (2024-01-15) |
| E2 | 105,800 | 104,000 | 0.0173 | E2 (2024-01-15) |
5. Positioning and privacy suppression
| Grade | n | Mean compa | Median compa | Mean penetration | counts |
|---|---|---|---|---|---|
| E1 | 12 | 0.9820 | 0.9750 | 0.4600 | Q1:3, Q2:5, Q3:4 |
| E2 | [n/a] | [n/a] | [n/a] | [n/a] | Suppressed (n<5) |
6. Exclusions and proposed actions
- 2 records excluded (missing data_use_permitted).
- Proposed Action: Review E1-E2 progression to align with 12% policy limit. Management decision required.
7. Items for human review
Information gap — organizational validation required: Verify if the E2-E3 progression was intentional for senior technical roles.
- This analysis supports, and does not replace, professional judgment and management's decision.
Next steps
- Validate the progression variances in Section 3 against recruitment difficulty data.
- Address the data permissions for the 2 excluded records to include them in the next run.
- Review the suppressed E2 positioning data with authorized HRBP access.
Connects securely to your tools. The creator never sees your data.
About this skill
Compensation modeling is often prone to calculation errors, inconsistent rounding, and accidental privacy leaks when handling small groups. This skill provides a deterministic environment for auditing pay structures and employee positioning. It enforces data minimisation and mathematical precision through a dedicated execution script.
What it does
- Structure Audit identifies inconsistencies in pay-band spreads, midpoint progressions, and grade overlaps or inversions.
- Market Benchmarking compares internal midpoints against user-provided market medians to flag competitive gaps.
- Positioning Analytics calculates compa-ratios and range penetration for authorised employee records.
- Privacy Enforcement applies group-size suppression to prevent the identification of individuals in small cohorts.
- Action Drafting generates management-ready proposals for band adjustments based on policy limits.
How it works
- The developer provides a JSON payload containing pay band definitions, pseudonymous employee records, and policy limits.
- The skill validates the
access_scopeand ensures all required authorisations and data permissions are present. - It executes a local Python script to perform exact decimal calculations for all compensation metrics.
- It generates a structured Markdown report that separates observed facts, computed results, and items requiring human review.
Frameworks & tools
The skill relies on a self-contained Python execution environment (scripts/run.py) and JSON schema validation for input/output integrity.
Why this beats prompting it yourself
Standard LLM prompting often results in "hallucinated" math or inconsistent rounding across large tables. This skill uses a deterministic script to ensure every compa-ratio and spread calculation is mathematically perfect while strictly enforcing privacy suppression rules that a raw prompt might overlook.
Use cases
- Audit a new salary structure for internal equity and logical progression.
- Identify employees falling outside their assigned pay bands or quartiles.
- Compare internal salary grades against external market surveys.
- Draft budget estimates for proposed pay-band adjustments.
Known limitations
Requires annual base pay only. It does not perform pay equity diagnostics, payroll reconciliation, or diversity metrics. Market data must be supplied by the user.
Annual pay only. No pay equity or diversity diagnostics. Market data must be user-provided. Minimum group size defaults to 5. No legal or compliance opinions.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 days ago