agentleFS
smileynetsmileynet/game-spice/skills/scenario-walkthrough/SKILL.md

scenario-walkthrough

Skill0 starsChanged 9 months agoMITView on GitHub

MLP scenario walkthrough and player experience narration. Use when visualizing the player experience before building, writing gameplay storyboards, narrating a play session, mapping player inputs to feedback, or validating that a plan feels concrete and playable. Covers 5-beat walkthrough, input/feedback mapping, experience narration.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Rule: If you can't fill in all 5 columns for a core action, the design isn't concrete enough to build.

    line 37

≈ “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

MLP Scenario Walkthrough

Narrate the player's experience before writing code. If you can't describe it, you can't build it.

Quick Reference

What Is a Scenario Walkthrough?

A moment-by-moment narration of a complete play session through your MLP. Not a feature list — a story of what the player sees, does, and feels from launch to session end.

Write one when: Core loop + 3 features are defined, BEFORE implementation begins (see scoping → The 3-Feature Rule).

The 5-Beat Structure

BeatQuestion It AnswersDuration
1. First ContactWhat does the player see on launch?First 10 seconds
2. Learning the VerbHow do they discover the core mechanic?First 1-2 minutes
3. Core Loop in MotionWhat does a full loop cycle feel like?2-3 cycles
4. Rising StakesHow does challenge emerge?First failure
5. Session EndWhy would they play again?Last moment

Input & Feedback Mapping

For each key moment, fill in this template:

Player IntentInputVisual FeedbackAudio FeedbackState Change
"I want to jump"Space barCharacter rises, squash & stretchWhoosh soundPosition changes, airborne state
"I want to attack"ClickSword swing animation, hit flashSlash + impact soundEnemy HP decreases

Rule: If you can't fill in all 5 columns for a core action, the design isn't concrete enough to build.

MLP Scenario Checklist

  • First 30 seconds described — what does the player see and do first?
  • First failure described — how does the player lose/fail and what happens?
  • Complete core loop cycle narrated — action → reward → reinvestment
  • Every input method used in MLP is mentioned at least once
  • A reason to replay or continue is present at session end
  • No beat says "the player has fun" — describe what they DO, not how they feel

Deep Dives

  • (see scenario-walkthrough/template.md for all 5 beat walkthroughs, Visual Snapshot Prompts, Walkthrough Anti-Patterns)

See Also

  • design-frameworks — Onboarding (Beat 2), core loop design (Beat 3), game feel (feedback mapping) (see design-frameworks → Core Loop Design)
  • scoping — Tracer bullet as the technical equivalent of a walkthrough (see scoping)
  • playtesting — Use the walkthrough as a testable artifact (see playtesting → The 3-Question Framework)
  • antipatterns — Design in Isolation and GDD Tome — walkthroughs help avoid both (see antipatterns)
  • economy-design — Narrate economy decisions within the walkthrough (see economy-design)
  • difficulty-design — Flow and difficulty for Beat 4 (Rising Stakes) (see difficulty-design → Flow State & Difficulty)
  • content-planning — Narrate content pacing and level progression before building (see content-planning)

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.