assessment
Assessment: read-only inspection, codebase overview, value analysis, health checks, ADR consultation, decision analysis, multi-perspective critique.
Game development: design, asset pipelines, Phaser, vanilla JS frontend, GM mode, match booking.
$ npx -y skills add notque/vexjoy-agent --skill game-dev --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/game-devContext preview
The summary Claude sees to decide when to auto-load this skill.
Game development: design, asset pipelines, Phaser, vanilla JS frontend, GM mode, match booking.
name: game-dev
description: "Game development: design, asset pipelines, Phaser, vanilla JS frontend, GM mode, match booking."
agent: project-coordinator-engineer
user-invocable: true
allowed-tools:
- Read
- Write
- Edit
- Bash
- Grep
- Glob
- Task
- Skill
routing:
force_route: true
not_for: "non-game frontend (use frontend), non-game backend (use workflow)"
triggers:
- game design
- game design audit
- game improvement
- core loop
- game feel
- game balance
- game economy
- make game
- game pipeline
- game audio
- deploy game
- phaser
- 2d game
- platformer
- arcade physics
- tilemap
- AI sprite
- generate sprite
- spritesheet pipeline
- animated spritesheet
- large GM implementation
- GM systems overhaul
- pixel art
- screen shake
- game qa
pairs_with:
- frontend
- workflow
complexity: Comprehensive
category: game-developmentFive modes: **Design** (diagnosis, auditing, improvement), **Pipeline** (full lifecycle orchestration), **Sprite** (AI sprite generation), **Phaser** (2D engine builds), **GM** (large multi-system implementations). Cross-cutting concerns (audio, QA, deploy) load as needed. Classify the request and follow the matching section.
| Mode | Signals | |------|---------| | **Design** | game design, improve game, retention, churn, core loop, audit, game feel, balance, economy | | **Pipeline** | make game, scaffold, game lifecycle, game audio, deploy game, game QA | | **Sprite** | AI sprite, generate character, portrait, spritesheet, animated sheet, pixel art | | **Phaser** | Phaser, 2D game, platformer, arcade physics, tilemap, side scroller | | **GM** | large GM implementation, multi-system GM, CPU systems, multi-wave overhaul |
If the request spans modes, load both primary references. Design + Pipeline is common (design an improvement then implement it). Sprite + Phaser is common (generate assets then wire into a Phaser game).
---
Evidence-led game design diagnosis with 61 runnable capabilities. Start from repository evidence; never guess when the repo can answer.
1. **Intake.** Read target repository's governing files. Search for game, product, UI, analytics, and research guidance. Use file search to find design docs, player copy, rules, UI, config, tests, analytics, issues. Separate facts into: observed, documented, measured, inferred. 2. **Ask only what the repo cannot answer.** Which player moment matters? What external evidence exists (playtests, telemetry, reviews)? Which constraints bind (platform, phase, team, time)? 3. **Load references.** Route greedily -- load every module that could change the recommendation:
| Signal | Load | |--------|------| | Promise, fantasy, loops, goals | `references/core-loop-and-pillars.md` | | Ideation, novelty, removal, reuse | `references/creative-and-options.md` | | Player motives, personas, values | `references/player-and-social.md` | | Information, bias, randomness | `references/cognition-and-choice.md` | | Failure, difficulty, fairness | `references/fairness-and-failure.md` | | FTUE, flow, friction, session | `references/pacing-and-return.md` | | Co-op, competition, social | `references/social-and-competitive.md` | | Rewards, currencies, passes | `references/progression-and-economy.md` | | Pitch, mood, prototype | `references/emotion-and-presentation.md` | | Scope, sequence, estimates | `references/planning-and-production.md` | | Full health report | All modules + `references/full-diagnostic.md` |
4. **Diagnose.** Trace the player path: cue -> interpretation -> choice -> response -> cost/reward -> feedback -> next intention. State player consequence, evidence, competing explanations, confidence, severity. 5. **Decide.** Offer 2-5 distinct options. For each: player-visible change, pillar fit, scope, dependencies, effort, reversibility, success metric, stop rule. Prefer reversible experiments. Reject dark patterns. 6. **Completion gate.** Every finding has evidence or is marked as inference. Every recommendation has a validation plan.
When request is bare "game design" or "what reviews are available": load `references/capability-catalog.md` and present the full domain-organized catalog of 61 capabilities.
When asked to improve a game's retention, churn, or engagement: load `references/autonomous-improvement.md`. Inspect the real game, run relevant capabilities, make the smallest safe reversible improvement, verify, leave a measurement plan.
---
Full lifecycle orchestration: SCAFFOLD -> ASSETS -> DESIGN -> AUDIO -> QA -> DEPLOY. Each phase can be entered independently.
| Request | Entry Phase | |---------|-------------| | make a game, new game | SCAFFOLD | | generate assets, add sprites | ASSETS | | add juice, particles, screen shake | DESIGN | | add audio, background music | AUDIO | | test game, visual regression | QA | | deploy, ship, publish, iOS | DEPLOY |
Detect engine (Three.js, Phaser, or vanilla canvas). Delegate to the appropriate engine skill or scaffold from template.
Route by asset type:
| Asset | Reference | |-------|-----------| | 3D model, GLB, mesh | `references/game-asset-generator.md` + `references/meshyai.md` | | Sprite, pixel art, tile | Load Sprite mode below | | Image, texture, concept art | `references/fal-ai-image.md` | | Environment, gaussian splat | `references/worldlabs.md` | | Free assets, Sketchfab | `references/asset-sources.md` | | Motion data, BVH, mocap | `references/motion-pipeline.md` |
Add game feel: screen shake, particles, hit-stop, juice. Load `references/game-feel-patterns.md`.
Web Audio API patterns, AudioManager, AudioBridge. Load `references/game-audio.md`.
Automated testing,
Essays and writing behind this toolkit live at vexjoy.com. VexJoy Agent connects plain-English requests to specialist agents, skills, and workflows. /do selects the knowledge and tools needed for your task.
Repo: notque/vexjoy-agent
Assessment: read-only inspection, codebase overview, value analysis, health checks, ADR consultation, decision analysis, multi-perspective critique.
Business operations: strategy, technology, growth, competitive intelligence, support, finance, HR, legal, operations, sales, productivity, product management.