# SkillSimm Simulation Report

Fill in every section — bullet points are fine. When you're done, paste the
whole report into an AI agent connected to the SkillSimm template server
(`https://mcp.skillsimm.com/mcp`) with the submission prompt at the bottom.

## 0. Basics

- Working title:
- Who is this for (audience):
- What skill or judgment should it train (objective):
- Roles involved (e.g., support agent, manager):
- Solo or team simulation? Ideal team size:

## 1. What the workflow looks like

Narrate the scenario and the steps in order, in plain language.

- What kicks the workflow off?
- Who does what, step by step? (aim for 5–12 steps)
- What does "done" look like?

## 2. Materials needed

List every document, dataset, or image a participant must read to do the work.

- For each material: what is it, and what does it contain?
- Can you provide it, or does a realistic version need to be created?

## 3. Human decision boundaries & standard operating procedure

For each step from section 1:

- Must a human decide, or can the AI act? (The human-only decisions are what
  the simulation exists to practice.)
- If AI is involved, what may it do — suggest options, critique a draft,
  grade an answer, or decide outright?
- What is the standard operating procedure a competent employee follows?
  Thresholds, approval limits, escalation criteria, required checks.

## 4. Edge cases

- What tricky inputs or ambiguities make this workflow genuinely hard?
- What do strong performers catch that weak performers miss?
- Any deliberately planted traps participants should detect?

## 5. Grading (optional — the interview will help you refine this)

- How would you know a participant did well?
- Are there objectively right answers, or is quality judged by a rubric?
- What would an excellent answer vs. a weak answer look like?

---

## Submission prompt (copy along with your report)

> Here is my structured report for a new SkillSimm simulation. Please:
> 1. Interview me about anything missing or ambiguous — one question at a time.
> 2. Build the full template package (steps, human/AI modes, materials, grading).
> 3. Show me a preview and let me revise it.
> 4. When I approve, validate it and submit it for review.