To run this task you must have the following required information:

> CSV file with compensation data including salaries, roles/levels, and optionally demographics

If you don't have all of this information, exit here and respond asking for any extra information you require, and instructions to run this task again with ALL required information.

---

You MUST use a todo list to complete these steps in order. Never move on to one step if you haven't completed the previous step. If you have multiple read steps in a row, read them all at once (in parallel).

Add all steps to your todo list now and begin executing.

## Steps

1. If the CSV path was not already provided, ask the user for it.
Common sources: HRIS exports, compensation planning spreadsheets, payroll exports.

Establish for the subtask:
- Output path: `./documents/tmp/hr-data.json`
- Column types to detect: salary/compensation, role/title, level, department, gender, tenure


2. [Gather Requirements for Parse and Interpret CSV] The next step has the following requirements: "CSV file path to parse. Column type hints (e.g., "scores, customers, dates, categories"). Output file path for the interpreted data.". Search the user's data for this information or ask them directly if needed. Do not proceed until you have this information.

3. [Execute Parse and Interpret CSV Task]: Spawn a subagent and provide it with the requirements gathered above and instructions to read `./skills/sauna/[skill_id]/references/recipes/stdlib.csv.interpret.md` for its task list

4. [Read Session HR Data]: Read the file at `./documents/tmp/hr-data.json` and analyze its contents (Load the parsed and interpreted CSV data)

5. [Read HR Analytics Guide]: Read the documentation in: `./skills/sauna/[skill_id]/references/hr.analytics.guide.md` (Compensation benchmarking analysis output format)

6. Analyze the compensation data:

1. Calculate summary statistics: average, median, distribution percentiles
2. Break down by role and level:
   - Average and median salary per role/level combination
   - Identify outliers (significantly above or below peers)
3. Pay equity analysis (if demographic data available):
   - Compare average/median by gender
   - Flag statistically significant gaps
   - Control for role/level when comparing
4. Identify compression issues:
   - Where junior and senior pay is too close
   - New hire vs. tenured employee gaps
5. If market benchmark data is included, calculate gaps to market

Present results following the Compensation Benchmarking Analysis template.
Include actual salary figures, percentages, and gaps.

IMPORTANT: Handle compensation data with appropriate confidentiality. Aggregate small
groups (< 5 people) to avoid identifying individuals.


7. Provide 2-3 actionable recommendations based on the findings.
Focus on: specific adjustments needed, equity corrections, process improvements.
Quantify the cost of recommended adjustments if possible.