agentleFS
tatashbartatashbar/Economic-Modeling-Studio/.agents/skills/create-exercise/SKILL.md

create-exercise

Skill4 starsChanged 6 days agoMITView on GitHub

Creates a hands-on exercise, case study, or policy wargame with scenario, roles, materials, facilitator guide and debrief.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If a required input is ABSENT, that part is NOT ASSESSED — NO DATA: do not estimate or invent it.

    line 26
  2. Very specific:

    Collaboration: Follow .claude/docs/collaboration-protocol.md: ask questions first, present options, get approval before writing files, and …

    line 28
  3. Distinctive:

    Write the facilitator guide and debrief questions

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Generated from .claude/skills/create-exercise/SKILL.md by tools/sync_agents.py. Edit the source, then run the script. -->

/create-exercise — Create Exercise

Category: Capacity Development · Primary agent: policy-wargame-facilitator

Creates a hands-on exercise, case study, or policy wargame with scenario, roles, materials, facilitator guide and debrief.

Arguments: whatever the user wrote after the command name.

Purpose

Create a hands-on exercise, case study or policy wargame in which participants make decisions with a model: a realistic scenario, roles, information injects, scoring, a facilitator guide and debrief questions. The output is a piloted exercise that teaches through decisions and their consequences, built on a validated model and free of confidential data.

Use it when training analysts or policymakers, preparing for crises, or testing coordination and playbooks.

Do not use it when a full curriculum is needed (/design-training).

Before you start

  1. Check required inputs. For each input below record FOUND or ABSENT (never 'assumed'):
    • Learning goal
    • Audience If a required input is ABSENT, that part is NOT ASSESSED — NO DATA: do not estimate or invent it; name what is missing and which skill produces it. If all required inputs are absent, stop and say so.
  2. Check confidentiality. Identify the data classification level of the inputs (.claude/docs/confidentiality-and-ai-use.md). Do not proceed with restricted or confidential data in a way the policy does not allow.
  3. Collaboration. Follow .claude/docs/collaboration-protocol.md: ask questions first, present options, get approval before writing files, and update production/session-state/active.md after each approved section.

Agents

  • policy-wargame-facilitator — primary agent; coordinates the work and integrates results
  • training-curriculum-designer — Designs training and capacity development
  • llm-agent-simulation-specialist — Builds LLM-based economic agents and simulations

Each agent is defined in .claude/agents/<name>.md. If your tool runs subagents, run these agents as subagents, in parallel where the steps are independent; otherwise read each agent's file and apply its instructions in turn. Subagents only write to the paths named in your instructions.

Key design decisions (present options, let the user choose)

DecisionTypical optionsWhat it changes
Formatlab exercise, case study, tabletop, wargameInteraction level
Enginevalidated model, lego set, LLM-agent role players, expert adjudicationRealism and cost
Audienceanalysts, senior officials, mixedDifficulty and focus
Durationhours, daysDepth

Workflow

  1. Define learning outcomes and the decision situation
  2. Design scenario, roles, information injects and scoring; optionally use an LLM-agent or model engine
    • Build injects from a validated scenario; lego exercises can ask participants to attach, swap and validate bricks
  3. Write the facilitator guide and debrief questions
  4. Pilot with a small group; revise

Checkpoints with the user

  • After learning outcomes
  • After the pilot

Common pitfalls

  • Inconsistent injects
  • Too many injects for the time
  • Outcomes treated as forecasts
  • Debriefs that skip failures

Output

docs/training/exercises/<name>/

The exercise folder holds the scenario, roles, injects, scoring, participant materials, facilitator guide, debrief questions and pilot notes.

Gate / verdict

  • Scenario is consistent with a validated model; confidential information is excluded
  • Learning outcomes are assessed in the debrief

Suggested next steps

  • /design-training

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.