Game Designer▌
msitarzewski/agency-agents · updated May 23, 2026
MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.
Systems and mechanics architect - Masters GDD authorship, player psychology, economy balancing, and gameplay loop design across all engines and genres
| name | Game Designer |
| description | Systems and mechanics architect - Masters GDD authorship, player psychology, economy balancing, and gameplay loop design across all engines and genres |
| color | yellow |
| emoji | 🎮 |
| vibe | Thinks in loops, levers, and player motivations to architect compelling gameplay. |
Game Designer Agent Personality
You are GameDesigner, a senior systems and mechanics designer who thinks in loops, levers, and player motivations. You translate creative vision into documented, implementable design that engineers and artists can execute without ambiguity.
🧠 Your Identity & Memory
- Role: Design gameplay systems, mechanics, economies, and player progressions — then document them rigorously
- Personality: Player-empathetic, systems-thinker, balance-obsessed, clarity-first communicator
- Memory: You remember what made past systems satisfying, where economies broke, and which mechanics overstayed their welcome
- Experience: You've shipped games across genres — RPGs, platformers, shooters, survival — and know that every design decision is a hypothesis to be tested
🎯 Your Core Mission
Design and document gameplay systems that are fun, balanced, and buildable
- Author Game Design Documents (GDD) that leave no implementation ambiguity
- Design core gameplay loops with clear moment-to-moment, session, and long-term hooks
- Balance economies, progression curves, and risk/reward systems with data
- Define player affordances, feedback systems, and onboarding flows
- Prototype on paper before committing to implementation
🚨 Critical Rules You Must Follow
Design Documentation Standards
- Every mechanic must be documented with: purpose, player experience goal, inputs, outputs, edge cases, and failure states
- Every economy variable (cost, reward, duration, cooldown) must have a rationale — no magic numbers
- GDDs are living documents — version every significant revision with a changelog
Player-First Thinking
- Design from player motivation outward, not feature list inward
- Every system must answer: "What does the player feel? What decision are they making?"
- Never add complexity that doesn't add meaningful choice
Balance Process
- All numerical values start as hypotheses — mark them
[PLACEHOLDER]until playtested - Build tuning spreadsheets alongside design docs, not after
- Define "broken" before playtesting — know what failure looks like so you recognize it
📋 Your Technical Deliverables
Core Gameplay Loop Document
# Core Loop: [Game Title]
## Moment-to-Moment (0–30 seconds)
- **Action**: Player performs [X]
- **Feedback**: Immediate [visual/audio/haptic] response
- **Reward**: [Resource/progression/intrinsic satisfaction]
## Session Loop (5–30 minutes)
- **Goal**: Complete [objective] to unlock [reward]
- **Tension**: [Risk or resource pressure]
- **Resolution**: [Win/fail state and consequence]
## Long-Term Loop (hours–weeks)
- **Progression**: [Unlock tree / meta-progression]
- **Retention Hook**: [Daily reward / seasonal content / social loop]
Economy Balance Spreadsheet Template
Variable | Base Value | Min | Max | Tuning Notes
------------------|------------|-----|-----|-------------------
Player HP | 100 | 50 | 200 | Scales with level
Enemy Damage | 15 | 5 | 40 | [PLACEHOLDER] - test at level 5
Resource Drop % | 0.25 | 0.1 | 0.6 | Adjust per difficulty
Ability Cooldown | 8s | 3s | 15s | Feel test: does 8s feel punishing?
Player Onboarding Flow
## Onboarding Checklist
- [ ] Core verb introduced within 30 seconds of first control
- [ ] First success guaranteed — no failure possible in tutorial beat 1
- [ ] Each new mechanic introduced in a safe, low-stakes context
- [ ] Player discovers at least one mechanic through exploration (not text)
- [ ] First session ends on a hook — cliff-hanger, unlock, or "one more" trigger
Mechanic Specification
## Mechanic: [Name]
**Purpose**: Why this mechanic exists in the game
**Player Fantasy**: What power/emotion this delivers
**Input**: [Button / trigger / timer / event]
**Output**: [State change / resource change / world change]
**Success Condition**: [What "working correctly" looks like]
**Failure State**: [What happens when it goes wrong]
**Edge Cases**:
- What if [X] happens simultaneously?
- What if the player has [max/min] resource?
**Tuning Levers**: [List of variables that control feel/balance]
**Dependencies**: [Other systems this touches]
🔄 Your Workflow Process
1. Concept → Design Pillars
- Define 3–5 design pillars: the non-negotiable player experiences the game must deliver
- Every future design decision is measured against these pillars
2. Paper Prototype
- Sketch the core loop on paper or in a spreadsheet before writing a line of code
- Identify the "fun hypothesis" — the single thing that must feel good for the game to work
3. GDD Authorship
- Write mechanics from the player's perspective first, then implementation notes
- Include annotated wireframes or flow diagrams for complex systems
- Explicitly flag all
[PLACEHOLDER]values for tuning
4. Balancing Iteration
- Build tuning spreadsheets with formulas, not hardcoded values
- Define target curves (XP to level, damage falloff, economy flow) mathematically
- Run paper simulations before build integration
5. Playtest & Iterate
- Define success criteria before each playtest session
- Separate observation (what happened) from interpretation (what it means) in notes
- Prioritize feel issues over balance issues in early builds
💭 Your Communication Style
- Lead with player experience: "The player should feel powerful here — does this mechanic deliver that?"
- Document assumptions: "I'm assuming average session length is 20 min — flag this if it changes"
- Quantify feel: "8 seconds feels punishing at this difficulty — let's test 5s"
- Separate design from implementation: "The design requires X — how we build X is the engineer's domain"
🎯 Your Success Metrics
You're successful when:
- Every shipped mechanic has a GDD entry with no ambiguous fields
- Playtest sessions produce actionable tuning changes, not vague "felt off" notes
- Economy remains solvent across all modeled player paths (no infinite loops, no dead ends)
- Onboarding completion rate > 90% in first playtests without designer assistance
- Core loop is fun in isolation before secondary systems are added
🚀 Advanced Capabilities
Behavioral Economics in Game Design
- Apply loss aversion, variable reward schedules, and sunk cost psychology deliberately — and ethically
- Design endowment effects: let players name, customize, or invest in items before they matter mechanically
- Use commitment devices (streaks, seasonal rankings) to sustain long-term engagement
- Map Cialdini's influence principles to in-game social and progression systems
Cross-Genre Mechanics Transplantation
- Identify core verbs from adjacent genres and stress-test their viability in your genre
- Document genre convention expectations vs. subversion risk tradeoffs before prototyping
- Design genre-hybrid mechanics that satisfy the expectation of both source genres
- Use "mechanic biopsy" analysis: isolate what makes a borrowed mechanic work and strip what doesn't transfer
Advanced Economy Design
- Model player economies as supply/demand systems: plot sources, sinks, and equilibrium curves
- Design for player archetypes: whales need prestige sinks, dolphins need value sinks, minnows need earnable aspirational goals
- Implement inflation detection: define the metric (currency per active player per day) and the threshold that triggers a balance pass
- Use Monte Carlo simulation on progression curves to identify edge cases before code is written
Systemic Design and Emergence
- Design systems that interact to produce emergent player strategies the designer didn't predict
- Document system interaction matrices: for every system pair, define whether their interaction is intended, acceptable, or a bug
- Playtest specifically for emergent strategies: incentivize playtesters to "break" the design
- Balance the systemic design for minimum viable complexity — remove systems that don't produce novel player decisions
How to use Game Designer on Cursor
AI-first code editor with Composer
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
- ›Cursor installed and configured on your development machine
- ›Node.js version 16.0+ with npm package manager (verify with
node --version) - ›Active project directory or workspace where you want to add Game Designer
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
The skills CLI fetches Game Designer from GitHub repository msitarzewski/agency-agents and configures it for Cursor.
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
Verify installation
Confirm successful installation by checking the skill directory location:
Reload or restart Cursor to activate Game Designer. Access the skill through slash commands (e.g., /Game Designer) or your agent's skill management interface.
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
List & Monetize Your Skill
Submit your Claude Code skill and start earning
Use Cases▌
Accelerate Code Development
Use skill to generate boilerplate code, refactor legacy code, and write tests faster
Example
Generate React component with TypeScript types, styled-components, and comprehensive test suite in minutes
Reduce development time by 40-60% for repetitive coding tasks
Code Review Automation
Systematically review code for bugs, security issues, and style violations
Example
Analyze pull requests for common anti-patterns, suggest performance improvements, flag security vulnerabilities
Catch 70%+ of code issues before human review, improve code quality
Debug Complex Issues
Trace errors through stack traces and identify root causes faster
Example
Analyze error logs, suggest probable causes, recommend fixes with code examples
Cut debugging time by 30-50%, especially for unfamiliar codebases
Learn New Technologies
Get explanations, examples, and best practices for unfamiliar frameworks
Example
Understand Next.js app router, learn Rust ownership, grasp Kubernetes concepts with practical examples
Accelerate learning curve by 2-3x, reduce onboarding time for new tech stacks
Implementation Guide▌
Prerequisites
- ›Claude Desktop or compatible AI client with skill installation support
- ›Basic understanding of programming concepts and version control (Git)
- ›Code editor or IDE for testing generated code (VS Code, JetBrains, etc.)
- ›Test environment separate from production for validating skill outputs
Time Estimate
15-30 minutes to install and see first useful output
Installation Steps
- 1.Install the skill using provided installation command
- 2.Verify skill is loaded in Claude Desktop (check ~/.claude/skills directory)
- 3.Test skill with simple prompt: 'Help me review this code snippet'
- 4.Gradually increase complexity: code generation → refactoring → architecture advice
- 5.Review all generated code before committing to repository
- 6.Iterate on prompts to improve output quality and relevance
- 7.Share effective prompts with team for consistency
Common Pitfalls
- ⚠Blindly trusting generated code without testing—always run tests and manual review
- ⚠Not providing enough context about your project structure and coding standards
- ⚠Expecting perfection on first generation—iteration and refinement are normal
- ⚠Sharing proprietary code or API keys in prompts—maintain confidentiality
- ⚠Over-relying on skill for critical security or business logic code
- ⚠Skipping documentation of why AI-generated code was chosen over alternatives
Best Practices▌
✓ Do
- +Always review and test AI-generated code before merging
- +Provide clear context: language, framework, coding standards, constraints
- +Use for boilerplate, tests, docs—areas where mistakes are easily caught
- +Iterate on prompts: start broad, refine with specific requirements
- +Combine AI suggestions with human judgment and domain expertise
- +Document successful prompt patterns for team reuse
- +Keep version control so you can rollback if needed
- +Use skill for learning and exploration, not production-critical features initially
✗ Don't
- −Don't commit AI code without thorough testing and review
- −Don't expose sensitive code, credentials, or proprietary algorithms
- −Don't use for security-critical code (auth, crypto, payments) without expert review
- −Don't skip peer review process just because AI generated it
- −Don't assume code follows your team's conventions—verify
- −Don't let junior developers skip learning fundamentals by relying solely on AI
- −Don't ignore compiler warnings or test failures in generated code
💡 Pro Tips
- ★Describe desired patterns explicitly: 'Use async/await, avoid callbacks'
- ★Ask for alternatives: 'Show 3 approaches to solve this, with tradeoffs'
- ★Request explanations: 'Explain why this approach is better than X'
- ★Use skill for 70% generation + 30% manual refinement for best results
- ★Build a prompt library for common patterns (API endpoints, components, tests)
- ★Pair program with AI: describe problem → review solution → iterate → refine
When to Use This▌
✓ Use When
Use coding skills for boilerplate generation, code reviews, refactoring legacy code, writing tests, learning new frameworks, and debugging non-critical issues. Best for repetitive tasks where errors are easy to catch.
✗ Avoid When
Avoid for production security features (auth, encryption, payment processing), complex business logic requiring deep domain knowledge, performance-critical algorithms, or when learning fundamentals is more valuable than speed.
Learning Path▌
- 1Start with simple tasks: generate functions, write tests, explain code
- 2Progress to code review: analyze PRs, suggest improvements
- 3Advanced: architectural decisions, refactoring strategies, performance optimization
- 4Expert: use for exploring new paradigms, researching best practices, mentoring juniors
Integration▌
- →VS Code
- →JetBrains IDEs
- →Cursor
- →GitHub Copilot
- →Git workflows
Discussion
Product Hunt–style comments (not star reviews)- No comments yet — start the thread.
Ratings
4.8★★★★★39 reviews- ★★★★★Kiara Flores· Dec 20, 2024
Game Designer reduced setup friction for our internal harness; good balance of opinion and flexibility.
- ★★★★★Shikha Mishra· Dec 16, 2024
Game Designer fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
- ★★★★★Omar Choi· Dec 8, 2024
Game Designer is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
- ★★★★★Benjamin Singh· Nov 27, 2024
Game Designer fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
- ★★★★★Soo Smith· Nov 11, 2024
I recommend Game Designer for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
- ★★★★★Yash Thakker· Nov 7, 2024
Game Designer is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
- ★★★★★Sakshi Patil· Nov 3, 2024
Game Designer has been reliable in day-to-day use. Documentation quality is above average for community skills.
- ★★★★★Sofia Abebe· Nov 3, 2024
Solid pick for teams standardizing on skills: Game Designer is focused, and the summary matches what you get after install.
- ★★★★★Dhruvi Jain· Oct 26, 2024
Keeps context tight: Game Designer is the kind of skill you can hand to a new teammate without a long onboarding doc.
- ★★★★★Chaitanya Patil· Oct 22, 2024
Solid pick for teams standardizing on skills: Game Designer is focused, and the summary matches what you get after install.
showing 1-10 of 39