agentleFS
MRCalderon3DMRCalderon3D/everything-game-dev-code/skills/design/core-loop-design/SKILL.md

core-loop-design

Skill105 starsChanged 8 months agoMITView on GitHub

Define the primary player activity loop and the support loops that sustain mastery, variety, and progression.

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:

    test whether the loop fits the intended session length and mastery curve

    line 28
  2. Distinctive:

    Keep this skill aligned with the relevant rules layer and current project documentation.

    line 60
  3. Distinctive:

    If engine-specific constraints materially change the workflow, hand off to the matching engine skill or engine-specific reviewer.

    line 61

≈ “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

Core Loop Design

Purpose

Define the primary player activity loop and the support loops that sustain mastery, variety, and progression.

Use When

  • a concept needs gameplay structure
  • the current loop feels unfocused
  • new systems risk diluting the core fantasy

Inputs

  • product pillars
  • target audience
  • competitive references
  • session and progression goals

Process

  1. state what the player repeatedly does and why it is satisfying
  2. map supporting loops that reinforce the core loop
  3. identify inputs, feedback, rewards, and failure points
  4. test whether the loop fits the intended session length and mastery curve
  5. cut systems that do not serve the loop

Outputs

  • core loop definition
  • support loop map
  • design constraints
  • candidate tutorial beats

Quality Bar

  • the loop is expressible as a closed cycle of player actions, rewards, and re-entry motivation
  • each loop step names the player verb, the feedback, and a duration target
  • supporting loops (session, progression, economy) are explicitly connected to the core loop
  • the loop is testable in a gray-box build without final art

Common Failure Modes

  • loops that depend on content volume instead of repeatable mechanics
  • reward steps without a defined re-entry hook back into the loop
  • a core loop tuned only on paper, never validated in a playable slice
  • conflating the core loop with the meta progression that wraps it

Related Agents

  • systems-designer
  • gdd-designer
  • level-designer

Related Commands

  • gdd
  • plan
  • onboarding

Notes

  • Keep this skill aligned with the relevant rules layer and current project documentation.
  • If engine-specific constraints materially change the workflow, hand off to the matching engine skill or engine-specific reviewer.

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.