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
- jeremykamber/jnk-skillstheir own version, first seen Oct 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- jeremykamber/jnk-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository210 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/ai-ml-code.mdcCursor rule
- .cursor/rules/code-translation.mdcCursor rule
- .cursor/rules/data-pipelines.mdcCursor rule
- .cursor/rules/documentation.mdcCursor rule
- .cursor/rules/dsge-code.mdcCursor rule
- .cursor/rules/econometrics-code.mdcCursor rule
- .cursor/rules/eviews-code.mdcCursor rule
- .cursor/rules/forecasts.mdcCursor rule
- .cursor/rules/gempack-code.mdcCursor rule
- .cursor/rules/lego-manifests.mdcCursor rule
- .cursor/rules/llm-code.mdcCursor rule
- .cursor/rules/model-code.mdcCursor rule
- .cursor/rules/notebooks-and-scripts.mdcCursor rule
- .cursor/rules/r-code.mdcCursor rule
- .cursor/rules/restricted-data.mdcCursor rule
- .cursor/rules/rl-code.mdcCursor rule
- .cursor/rules/sectoral-trade-climate-code.mdcCursor rule
- .cursor/rules/semi-structural-code.mdcCursor rule
- .cursor/rules/stata-code.mdcCursor rule
- .cursor/rules/tests.mdcCursor rule
- .cursor/rules/validation.mdcCursor rule
- adoptSkill
- ai-auditSkill
- backtestSkill
- build-abmSkill
- build-causal-mlSkill
- build-cgeSkill
- build-climate-macroSkill
- build-deep-forecasterSkill
- build-drl-policySkill
- build-dsgeSkill
- build-financial-programmingSkill
- build-fpasSkill
- build-game-modelSkill
- build-hankSkill
- build-io-samSkill
- build-llm-agentsSkill
- build-llm-pipelineSkill
- build-multicountrySkill
- build-neural-solverSkill
- build-rag-kbSkill
- build-semi-structuralSkill
- build-sfcSkill
- build-trade-modelSkill
- calibrate-modelSkill
- calibration-planSkill
- carbon-pricing-analysisSkill
- chart-packSkill
- climate-scenarioSkill
- code-inventorySkill
- code-reviewSkill
- country-typologySkill
- data-requirementsSkill
- debt-decompositionSkill
- debt-sustainabilitySkill
- design-trainingSkill
- distributional-analysisSkill
- equivalence-testSkill
- The first 60 shown.
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
- Very specific: line 26
If a required input is ABSENT, that part is NOT ASSESSED — NO DATA: do not estimate or invent it.
- Very specific: line 28
Collaboration: Follow .claude/docs/collaboration-protocol.md: ask questions first, present options, get approval before writing files, and …
- Distinctive: line 49
Write the facilitator guide and debrief questions
≈ “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.
Files
<!-- 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
- Check required inputs. For each input below record
FOUNDorABSENT(never 'assumed'):- Learning goal
- Audience
If a required input is
ABSENT, that part isNOT 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.
- 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. - Collaboration. Follow
.claude/docs/collaboration-protocol.md: ask questions first, present options, get approval before writing files, and updateproduction/session-state/active.mdafter each approved section.
Agents
policy-wargame-facilitator— primary agent; coordinates the work and integrates resultstraining-curriculum-designer— Designs training and capacity developmentllm-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)
| Decision | Typical options | What it changes |
| Format | lab exercise, case study, tabletop, wargame | Interaction level |
| Engine | validated model, lego set, LLM-agent role players, expert adjudication | Realism and cost |
| Audience | analysts, senior officials, mixed | Difficulty and focus |
| Duration | hours, days | Depth |
Workflow
- Define learning outcomes and the decision situation
- 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
- Write the facilitator guide and debrief questions
- 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
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
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.

