game-design-expert
Skill5 starsChanged 22 days agoMITView on GitHub
Use when designing or improving a game's controls, mechanics, surprise, progression, character identity, or art direction, especially when a working game feels repetitive, generic, or unrewarding.
In this repository47 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agents-md-fixerSkill
- arch-docsSkill
- book-to-markdownSkill
- docset-updaterSkill
- humanizerSkill
- news-release-docsSkill
- pdf-guideSkill
- readme-docsSkill
- screenshot-docsSkill
- see-also-docsSkill
- setup-install-usage-docsSkill
- bptools-writer-expertSkill
- color-accessibility-expertSkill
- css-creative-expertSkill
- geometry-expertSkill
- glass-expertSkill
- hic-human-interact-expertSkill
- openscad-3d-printing-expertSkill
- podman-expertSkill
- postgresql-expertSkill
- pyside6-engineerSkill
- rust-code-expertSkill
- solid-js-expertSkill
- svg-creator-expertSkill
- typescript-engineerSkill
- ui-ux-engineerSkill
- vision-expertSkill
- wasm-rust-expertSkill
- webwork-writer-expertSkill
- delegate-manager-to-subagentsSkill
- gas-town-workflowSkill
- hang-checkSkill
- html-game-parallel-builderSkill
- parallel-planSkill
- stay-busySkill
- repo-rules-readerSkill
- blueprint-plan-drafterSkill
- ideonomy-plainSkill
- ideonomy-richSkill
- make-goalSkill
- modest-plan-drafterSkill
- audit-code-reviewerSkill
- old-python-code-reviewSkill
- prune-testsSkill
- unit-test-starterSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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
- Distinctive: line 16
Expect the unexpected = fun: Keep players curious about what happens next through fresh situations, helpful chaos, discoveries, and payoffs.
- Distinctive: line 20
Finish independently: If the human goes to sleep, the manager and subagents still have a complete path through every milestone.
- Distinctive: line 31
Read the relevant cases in references/case_studies.md.
- Distinctive: line 44
Use references/topic_index.md for focused lookup.
- Very specific: line 52
Use html-game-parallel-builder when a modular TypeScript game needs parallel implementation.
- Very specific: line 55
Use typescript-engineer for type design and svg-creator-expert for editable SVG production.
- Distinctive: line 62
Keep routine code maintenance in the normal engineering workflow.
- Distinctive: line 70
Use behavior tests for correctness and proportionate agent assessment for experience quality.
≈ “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.
Files
Game design expert
Turn an intended player experience into a playable, distinctive game. Use the six successful games in the references as evidence for decisions, with books providing supporting principles. Adapt their strengths to the current game.
Governing design principles
- Fun first, teaching when relevant. Make the main action satisfying and let relevant understanding emerge through play.
- Expect the unexpected = fun. Keep players curious about what happens next through fresh situations, helpful chaos, discoveries, and payoffs.
- Create a world worth exploring, characters worth recognizing, and consequences worth seeing. Connect expressive art to the experience.
- Finish independently. If the human goes to sleep, the manager and subagents still have a complete path through every milestone.
Workflow and reference routing
- Select the design problem with references/task_selection.md. Use the user's request and project evidence to resolve routine choices.
- Detect a new versus existing project before edits. Follow references/project_workflow.md to establish the shared brief or inspect the current experience and preserve its strengths.
- Read the relevant cases in references/case_studies.md. Turn each borrowed lesson into a decision for this game's audience, genre, and controls.
- Shape actions, choices, surprise, progression, and recovery using references/design_principles.md. Prototype the greatest uncertainty, then complete the requested scope.
- For characters, environments, or visual consequences, use references/art_direction.md. Carry artistic intent into gameplay and asset assignments, then inspect the integrated view.
- Implement or coordinate the requested improvements. Follow references/testing_and_oracles.md for proportional evidence, independent assessment, correction, and completion.
Use references/topic_index.md for focused lookup. For deeper book evidence, consult references/reference_survey.md and references/local_books.md. The committed guidance works when the optional books and example repositories are absent.
Boundaries and specialist handoffs
- Use
html-game-parallel-builderwhen a modular TypeScript game needs parallel implementation. It owns dispatch, contracts, integration, serving, and delivery; this skill supplies the shared creative brief and experience assessment. - Use
typescript-engineerfor type design andsvg-creator-expertfor editable SVG production. Use available image tools for other requested asset formats. Choose specialists for the actual task rather than assembling a default team. - Consult the target's
docs/FUN_VIBES_DESIGN_STYLE.mdanddocs/PLAYFUL_TRAINING_GAME_STYLE.mdwhen available. Their canonical sources live instarter-repo-template/templates/typescript/docs/; keep guide copies out of skills. The focused references here remain sufficient without them. - Keep routine code maintenance in the normal engineering workflow. Activate this skill when a decision about the player experience needs design judgment.
Completion and evidence
For implementation requests, finish the integrated improvement and its checks; for design-only requests, deliver actionable decisions and an executable path to acceptance. State what changed, why, evidence inspected, and remaining limits. Use behavior tests for correctness and proportionate agent assessment for experience quality. Keep claims about human enjoyment or learning tied to actual human evidence. Optional feedback never becomes a milestone dependency.
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.

