Game Prototype

Runs hypothesis-driven prototyping: one question per prototype, a falsifiable hypothesis, the cheapest fidelity that answers it (paper, simulation, agent-built throwaway), a time box, observed playtests and a kill-or-promote call. Use for "prototype", "proof of concept", "test this mechanic", "is this fun". Not for building a small shippable game (use game-vibe-code).

57 stars 6 forksProductivity & Notes Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add AlterLab-IEU/AlterLab_GameForge

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add AlterLab-IEU/AlterLab_GameForge --skill game-prototype
Manual install
git clone --depth 1 https://github.com/AlterLab-IEU/AlterLab_GameForge.git /tmp/AlterLab_GameForge
mkdir -p ~/.claude/skills
cp -r /tmp/AlterLab_GameForge/skills/workflows/game-prototype ~/.claude/skills/game-prototype

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# AlterLab GameForge -- Hypothesis-Driven Prototyping

A prototype is an experiment, not a demo. Every prototype exists to answer one question, usually
"is this worth building?", and the moment you start polishing it you have stopped prototyping and
started building, possibly the wrong thing. This workflow enforces the discipline: name the question,
write a hypothesis that can fail, build the cheapest thing that tests it, watch real players, and
make a binary kill-or-promote call on the evidence.

Coding agents changed the cost of the build step, not the discipline. An agent can produce a playable
throwaway in an hour, which makes it tempting to skip the question and "just build it." Cheap builds
make a clear question more important, not less: without one you get ten prototypes and no answers.

**Continuity through files.** Read `.gameforge/project.json` (pillars, phase), `design/concept.md`,
earlier reports in `design/prototypes/`, and `production/session-state/active.md`. Each prototype
lives in `prototypes/<name>/` with a `QUESTION.md`; the report goes to
`design/prototypes/<name>-report.md`; `active.md` gets the decision and the next step. If the
project's phase is still `concept` or `pre-production`, offer to set it to `prototype`.

## When NOT to use me

| The user wants... | Route to |
|---|---|
| A small, complete, shippable game (web or jam) built with an agent | `/gameforge:game-vibe-code` |
| A jam entry with a deadline | `/gameforge:game-jam-mode` |
Read the full skill on GitHub

Details

Skill name
game-prototype
Path
skills/workflows/game-prototype/SKILL.md
License
MIT
Repo updated
6 November 2026

FAQ

What does the Game Prototype skill do?

Runs hypothesis-driven prototyping: one question per prototype, a falsifiable hypothesis, the cheapest fidelity that answers it (paper, simulation, agent-built throwaway), a time box, observed playtests and a kill-or-promote call. Use for "prototype", "proof of concept", "test this mechanic", "is this fun". Not for building a small shippable game (use game-vibe-code).

How do I install the Game Prototype skill?

Claude Code plugin: /plugin marketplace add AlterLab-IEU/AlterLab_GameForge. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Game Prototype popular?

It lives in AlterLab-IEU/AlterLab_GameForge, which has 57 GitHub stars and 6 forks, and is included in 1 curated skill list.

Related skills

Game Accessibility Specialist

57

AlterLab-IEU/AlterLab_GameForge

Accessibility Specialist (Kael Oduya). Designs motor, visual, auditory and cognitive accommodations, runs accessibility audits, scopes the European Accessibility Act, CVAA and Game Accessibility Guidelines, and maps fixes to Godot, Unity, Unreal or web. Use for "accessibility audit", "EAA", "colorblind", "subtitles", "remapping". Not for general UX flows (use game-ux-designer).

Frontend & DesignIn 1 list

Game AI Assets

57

AlterLab-IEU/AlterLab_GameForge

Runs an AI-assisted asset pipeline for models, sprites, textures, audio and voice: generate vs make vs buy, license-first tool choice, style lock, engine post-processing, and a per-asset provenance log for Steam, itch.io and EU AI Act disclosures. Use for "generate a sprite with AI", "ElevenLabs", "can I ship this AI asset". Not for defining art style (use game-art-director).

AI, LLMs & AgentsIn 1 list

Game Analytics Setup

57

AlterLab-IEU/AlterLab_GameForge

Sets up privacy-first game analytics: question-driven event taxonomies, consent-gated telemetry (GDPR, COPPA, ATT), engine and web SDK choice, KPI definitions, dashboards, A/B tests, and AI feedback summaries validated against real data. Use for "analytics", "telemetry", "KPIs", "retention", "funnel", "A/B test". Not for balance tuning (use game-balance-check).

Data & AnalyticsIn 1 list

Game Retrospective

57

AlterLab-IEU/AlterLab_GameForge

Runs a sprint or milestone retrospective in the GDC post-mortem tradition: What Went Right, What Went Wrong, seven lenses including AI-assisted development, the Kill List and The One Thing, with actions fed into the next sprint. Use for "retro", "sprint retrospective", "milestone review", "kill list". Not for a whole-project post-mortem (use game-postmortem).

Productivity & NotesIn 1 list

Game Postmortem

57

AlterLab-IEU/AlterLab_GameForge

Runs a data-driven post-mortem for a shipped, canceled or major-phase project: git history, sprint and retro records, scope and quality trends, and what AI agents contributed and cost per milestone, ending in owned lessons archived to production/milestones/. Use for "post-mortem", "project review", "what did we learn". Not for a single sprint (use game-retrospective).

Productivity & NotesIn 1 list

Game Scope Check

57

AlterLab-IEU/AlterLab_GameForge

Checks scope against time and capacity: feature inventory, MoSCoW with effort caps, impact and risk scores, buffer math, scope-creep signals and a cut list, with velocity calibrated for AI-agent work and vibe debt counted as risk. Use for "scope creep", "can we fit this", "what should we cut", "are we on track". Not for sprint task planning (use game-sprint-plan).

Productivity & NotesIn 1 list

Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.