game-concept
Skill4 starsChanged 46 days agoMITView on GitHub
Authors a web-game concept — pitch, core loop, MDA, mechanics, progression and economy, content scope, visual/audio direction, feasibility (engine, frame/memory/load budgets on mobile web, networking), accessibility, metrics, prototype plan — into docs/specs/game-concept.md; `gate` records the prototype go/no-go. Use when starting a game, for 'game idea', 'core loop', 'is the prototype fun'.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- zenstory-ai/novel-to-gametheir own version, first seen Nov 8, 2026
- openaigames/OpenAIGamesDesignertheir own version, first seen Oct 15, 2026
- AVANT-ICONIC/gpt-webui-skillstheir own version, first seen Oct 13, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- zenstory-ai/novel-to-game★ 981same name
- openaigames/OpenAIGamesDesigner★ 24same name
- AVANT-ICONIC/gpt-webui-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 repository52 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- testing/CLAUDE.mdCLAUDE.md
- a11y-auditSkill
- adoptSkill
- api-contractSkill
- architecture-decisionSkill
- architecture-reviewSkill
- backlogSkill
- brainstormSkill
- changelogSkill
- code-reviewSkill
- collaboration-protocolSkill
- create-storiesSkill
- data-modelSkill
- dependency-auditSkill
- deploySkill
- design-systemSkill
- dev-storySkill
- docsSkill
- feature-specSkill
- hardenSkill
- helpSkill
- hotfixSkill
- impactSkill
- incidentSkill
- initSkill
- migrateSkill
- pentestSkill
- perf-auditSkill
- product-specSkill
- qa-planSkill
- refactorSkill
- release-checklistSkill
- retrospectiveSkill
- security-auditSkill
- setup-stackSkill
- skill-improveSkill
- skill-testSkill
- sprint-planSkill
- sprint-statusSkill
- stack-updateSkill
- startSkill
- story-doneSkill
- team-featureSkill
- team-gameSkill
- team-releaseSkill
- team-securitySkill
- tech-debtSkill
- test-setupSkill
- threat-modelSkill
- updateSkill
- ux-specSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 30
Read §11 of docs/specs/game-concept.md (the measurable "fun" criterion).
- Distinctive: line 31
Ask for the measured result against it (playtest notes, numbers).
- Very specific: line 33
After the write, the Phase 6 commit gate (docs: prototype gate <GO|NO-GO|PIVOT>, staging production/releases/gate-prototype.md and …
- Distinctive: line 42
When HEAD is a story branch, name it and offer: switch to the default branch and commit there (Recommended — a pipeline-wide document) · …
≈ “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 Concept
Reply in the project conversation language (CLAUDE.md → Language); code, identifiers, paths and commit messages stay in English.
Template .claude/docs/templates/game-concept.md. Reference threejs-webgames.md. In the commands below, <hooks> is .claude/hooks/ in copy mode and ${CLAUDE_PLUGIN_ROOT}/hooks/ in plugin mode.
Phase 1: Pitch and loop
Questions: genre, the player's "verb", session (minutes), platform (mobile web first?), single/multiplayer, references. Three core-loop variants with "why it is fun to repeat".
Phase 2: Mechanics, progression, content
Rules with parameters (mark which live in data, not code); a difficulty-curve table; MVP volume vs full version.
Phase 3: Feasibility
Engine with justification (3D → three.js, WebGPU with WebGL2 fallback; 2D → PixiJS/Phaser; versions from threejs-webgames.md); budget: 16.6 ms frame, draw calls, memory, first load on 4G; networking (multiplayer → server-authoritative on Go, tick rate); saves; spikes to test risks (e.g. "1000 instances on a mid-range phone").
threejs-engineer/web-game-engineer via Task — risk assessment for their part (in parallel).
Phase 4: Accessibility, metrics, prototype
Accessibility settings; retention metrics; prototype plan: what playability validates first, timeline, the "fun" criterion — measurable (sessions, minutes, a question to N testers), so gate can record a result, not an opinion.
Phase 4b: gate — the prototype go/no-go
/game-concept gate runs only this phase, after the first playable slice and before backend/multiplayer investment. The catalog step prototype-gate and /help look for its artefact.
- Read §11 of
docs/specs/game-concept.md(the measurable "fun" criterion). - Ask for the measured result against it (playtest notes, numbers).
- Record
GO | NO-GO | PIVOT (what changes)with the evidence inproduction/releases/gate-prototype.mdand as a "Result" block under §11, after "May I write?" — oneAskUserQuestion: write (Recommended) · show the draft/diff first · not now. After the "write" answer:touch .claude/.write-consent. - After the write, the Phase 6 commit gate (
docs: prototype gate <GO|NO-GO|PIVOT>, stagingproduction/releases/gate-prototype.mdanddocs/specs/game-concept.md). - Hand-off — one
AskUserQuestion.GO→/create-storiesfor the vertical slice's feature (Recommended when no stories exist) ·/dev-story S-NNN(Recommended when the stories exist — name the first Ready one) · stop here.NO-GO/PIVOT→ the next step is a concept revision, not the next feature:/game-conceptagain for the sections the result names (Recommended) ·/brainstormwhen the loop itself failed · stop here.
Phase 5: Write
"May I write docs/specs/game-concept.md?" — one AskUserQuestion: write (Recommended) · show the draft/diff first · not now. Propose an engine ADR (/architecture-decision). After the "write" answer: touch .claude/.write-consent (rule 7 — the consent-guard hook checks the marker).
Phase 6: Commit (documents lane)
Right after the write, one commit gate (rule 7 (4), .claude/docs/git-workflow.md § Documents): one AskUserQuestion offering docs: game concept, staging exactly the written files — docs/specs/game-concept.md (for gate: the message and files Phase 4b step 4 names). Record the gate before asking — <hooks>session-state.sh set Gate "/game-concept Phase 6: commit?" — and clear it after the answer (<hooks>session-state.sh set Gate "—").
- On the default branch when no story work is in progress.
- When HEAD is a story branch, name it and offer: switch to the default branch and commit there (Recommended — a pipeline-wide document) · commit here (the document belongs to this story) · leave uncommitted.
- Code, configs, workflows and scripts never ride the
docs:commit.
Nothing is committed without the answer.
Verdict: APPROVED | NEEDS REVISION | GO | NO-GO | PIVOT. Next step — one AskUserQuestion: /product-spec (light) (Recommended) · /architecture-decision (engine) · prototype via /dev-story. After gate, the hand-off of Phase 4b step 5 instead.
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.

