agentleFS
WilliamEbongWilliamEbong/CourseForge/.claude/skills/scenario-design/SKILL.md

scenario-design

Skill0 starsChanged 57 days agoMITView on GitHub

Designing realistic, neutral workplace scenarios and branching decision activities that exercise learning objectives safely. Used by CourseForge STORYBOARD authoring and instructional reviewers.

2 other projects use 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, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No invented statistics or measurements presented as fact.

    line 29
  2. Distinctive:

    Avoid stereotypes and blame.

    line 30
  3. Distinctive:

    Keep hazards at awareness level: the learner decides what to notice, stop, ask or escalate, never how to perform a hazardous procedure.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Scenario design

What a scenario is for

A scenario lets learners practise a decision they will face, with enough context to reason and feedback that teaches the principle. It is not a story for its own sake. Every scenario maps to an objective whose verb is about applying, distinguishing, evaluating, selecting, documenting or escalating.

Anatomy

  1. Situation: who the learner is (a role, not a named real person), where, what is happening, and what they know. Two to five sentences.
  2. Relevant facts: the information a competent person would have at that moment. Include the facts that matter and one or two that do not, so the learner must judge relevance.
  3. Decision point: a clear question: what do you do, what is missing, which option is best supported, who must be involved.
  4. Options: realistic choices, including the tempting wrong ones that people actually make (acting on incomplete information, over-relying on PPE, treating a label as a risk assessment, fixing the symptom instead of the cause).
  5. Consequences and feedback: for each option, what would plausibly follow and which principle applies, with citations.
  6. Debrief: one or two sentences connecting the decision back to the model taught.

Continuing cases

A case introduced in the first topic module and revisited later builds transfer: the learner applies new knowledge to a familiar situation. Keep facts consistent across modules (names of roles, the setting, what has already happened). Escalate complexity gradually: early visits identify, later visits decide and justify.

Neutrality and honesty

  • Invent roles and settings, never real organisations, incidents, people or outcomes. Use generic descriptions ("a university research laboratory", "a mid-sized clinic").
  • No invented statistics or measurements presented as fact. If a number is needed for reasoning, make it clearly hypothetical and keep it inside a plausible, sourced range.
  • Avoid stereotypes and blame. Workers who make mistakes are shown as people in systems with pressures, not as careless.
  • Keep hazards at awareness level: the learner decides what to notice, stop, ask or escalate, never how to perform a hazardous procedure.

"Not enough information" as a correct answer

Where the evidence supports it, the best decision is to stop and gather information or escalate. Build scenarios where the learner must recognise that the facts given are insufficient, and reward that recognition. This teaches professional judgement and prevents false confidence.

Branching without complexity

The storyboard models scenarios as sequences of blocks with single-choice or multiple-response items; true branching is a screen graph built later. Keep branches shallow: a decision, its consequence, and a return to the main path. Each branch must still teach, and every path must end in the debrief.

Accessibility

Scenario text is fully readable without images. Choices are standard, keyboard-operable controls. Nothing depends on timing. Consequences are described in words, not only shown.

Quality checks

  • The decision cannot be answered without applying the taught principle.
  • Wrong options are tempting for a real reason and have feedback explaining the specific error.
  • The correct option is supported by cited evidence.
  • The scenario is safe to act on: its correct path never models unsafe or unlawful behaviour.
  • The debrief states the transferable principle in one or two sentences.

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.