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

> CSV with task data including assignee, completion status, dates, and optionally effort/points

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: Jira export, Asana export, Linear export, project management tool exports.

Establish for the subtask:
- Output path: `./documents/tmp/manager-analysis-data.json`
- Column types to detect: assignee, status, created date, completed date, effort/points (optional)


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 Manager Analytics Session Data]: Read the file at `./documents/tmp/manager-analysis-data.json` and analyze its contents (Load the parsed and interpreted CSV data)

5. [Read Manager Diagnostics Guide]: Read the documentation in: `./skills/sauna/[skill_id]/references/manager.diagnostics.guide.md` (Reference workload analysis framework, validation rules, and output format)

6. **Validate the data before analysis.** Check for:

1. **Missing assignees:** Count tasks with empty or missing assignee. These can't be attributed in distribution analysis.
2. **Invalid effort values:** If story points/effort column exists, check for non-numeric or negative values.
3. **Date issues:** If dates are present, check for unparseable formats or dates in the far future.
4. **Sample size:** Count unique assignees and total tasks.

If issues found, report them clearly:
- "⚠️ X tasks have no assignee - excluded from distribution analysis"
- "⚠️ X tasks have invalid effort values - task counts used instead"

If < 3 team members, note that distribution comparison is limited per the Data Confidence section.
If someone has zero completed tasks, note this explicitly (might indicate data issue or blocked work).
If data is too incomplete to analyze (no assignee column detected), stop and ask user to verify the CSV structure.

Proceed with valid rows only.


7. Analyze workload distribution across the team:

**For each team member, calculate:**
1. Total tasks assigned
2. Tasks completed
3. Completion rate
4. Average completion time (if dates available)
5. Story points / effort (if available)

**Distribution analysis:**
- Mean and median load per person
- Standard deviation (how uneven is distribution?)
- Who is at >1.5x average? <0.5x average?

**Patterns to surface:**
- Single points of failure (one person owns critical area)
- Knowledge bottlenecks
- Unassigned or blocked work
- Overdue/aging tasks by owner

Present results following the Workload Analysis template from the guide.
Create a visual chart if possible (simple ASCII or describe the distribution).


8. Provide recommendations based on findings:

**If workload is imbalanced:**
- Who should take on more? (Consider capacity, growth goals)
- What can be redistributed?
- Are there training/enablement needs?

**If there are bottlenecks:**
- Knowledge sharing recommendations
- Cross-training priorities
- Documentation needs

**For team discussions:**
- Questions to raise in team meetings
- 1:1 conversation suggestions

Ask if they want deeper analysis on specific individuals or patterns.