balance-check
Identifies gameplay balance outliers and progression issues in game configuration files.
Install
mkdir -p .claude/skills/balance-check && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18159" && unzip -o skill.zip -d .claude/skills/balance-check && rm skill.zipInstalls to .claude/skills/balance-check
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Analyzes game balance data files, formulas, and configuration to identify outliers, broken progressions, degenerate strategies, and economy imbalances. Use after modifying any balance-related data or design. Use when user says 'balance report', 'check game balance', 'run a balance check'.Key capabilities
- →Identify the balance domain (Combat, Economy, Progression, Loot)
- →Read relevant data files from `assets/data/` and `design/balance/`
- →Read the GDD for the system from `design/gdd/` to understand intended design targets
- →Perform domain-specific analysis checks (e.g., DPS, resource flow rates, XP curves)
- →Output a structured balance check report with findings and recommendations
- →Guide the user through fixing balance issues and re-running checks
How it works
The skill identifies the balance domain, reads data files and design documents, performs domain-specific analysis, and generates a report with findings and recommendations.
Inputs & outputs
When to use balance-check
- →Balance combat stats
- →Check economy faucets
- →Tune progression curves
About this skill
Phase 1: Identify Balance Domain
Determine the balance domain from $ARGUMENTS[0]:
- Combat → weapon/ability DPS, time-to-kill, damage type interactions
- Economy → resource faucets/sinks, acquisition rates, item pricing
- Progression → XP/power curves, dead zones, power spikes
- Loot → rarity distribution, pity timers, inventory pressure
- File path given → load that file directly and infer domain from content
If no argument, ask the user which system to check.
Phase 2: Read Data Files
Read relevant files from assets/data/ and design/balance/ for the identified domain.
Note every file read — they will appear in the Data Sources section of the report.
Phase 3: Read Design Document
Read the GDD for the system from design/gdd/ to understand intended design targets,
tuning knobs, and expected value ranges. This is the baseline for "correct" behaviour.
Phase 4: Perform Analysis
Run domain-specific checks:
Combat balance:
- Calculate DPS for all weapons/abilities at each power tier
- Check time-to-kill at each tier
- Identify any options that dominate all others (strictly better)
- Check if defensive options can create unkillable states
- Verify damage type/resistance interactions are balanced
Economy balance:
- Map all resource faucets and sinks with flow rates
- Project resource accumulation over time
- Check for infinite resource loops
- Verify gold sinks scale with gold generation
- Check if any items are never worth purchasing
Progression balance:
- Plot the XP curve and power curve
- Check for dead zones (no meaningful progression for too long)
- Check for power spikes (sudden jumps in capability)
- Verify content gates align with expected player power
- Check if skip/grind strategies break intended pacing
Loot balance:
- Calculate expected time to acquire each rarity tier
- Check pity timer math
- Verify no loot is strictly useless at any stage
- Check inventory pressure vs acquisition rate
Phase 5: Output the Analysis
## Balance Check: [System Name]
### Data Sources Analyzed
- [List of files read]
### Health Summary: [HEALTHY / CONCERNS / CRITICAL ISSUES]
### Outliers Detected
| Item/Value | Expected Range | Actual | Issue |
|-----------|---------------|--------|-------|
### Degenerate Strategies Found
- [Strategy description and why it is problematic]
### Progression Analysis
[Graph description or table showing progression curve health]
### Recommendations
| Priority | Issue | Suggested Fix | Impact |
|----------|-------|--------------|--------|
### Values That Need Attention
[Specific values with suggested adjustments and rationale]
Phase 6: Fix & Verify Cycle
After presenting the report, ask:
"Would you like to fix any of these balance issues now?"
If yes:
- Ask which issue to address first (refer to the Recommendations table by priority row)
- Guide the user to update the relevant data file in
assets/data/or formula indesign/balance/ - After each fix, offer to re-run the relevant balance checks to verify no new outliers were introduced
- If the fix changes a tuning knob defined in a GDD or referenced by an ADR, remind the user:
"This value is defined in a design document. Run
/propagate-design-change [path]on the affected GDD to find downstream impacts before committing."
If no:
- Summarize open issues and suggest saving the report to
design/balance/balance-check-[system]-[date].mdfor later
End with:
"Re-run
/balance-checkafter fixes to verify."
When not to use it
- →When the user is not asking for a balance report
- →When the user is not checking game balance
- →When the user is not running a balance check
Limitations
- →Analysis is based on files in `assets/data/`, `design/balance/`, and `design/gdd/`
- →The skill focuses on specific balance domains: Combat, Economy, Progression, Loot
- →Recommendations are based on identified outliers and degenerate strategies
How it compares
This skill automates the process of cross-referencing game data with design baselines and performing domain-specific analysis, providing a structured report and fix-verify cycle, unlike a manual review.
Compared to similar skills
balance-check side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| balance-check (this skill) | 0 | 2mo | No flags | Intermediate |
| backtesting-trading-strategies | 10 | 10d | Review | Intermediate |
| data-quality-frameworks | 6 | 2mo | Review | Intermediate |
| trulens-running-evaluations | 1 | 2mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
backtesting-trading-strategies
jeremylongshore
Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".
data-quality-frameworks
wshobson
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
trulens-running-evaluations
truera
Execute TruLens evaluations and view results
test-reporting-analytics
proffesor-for-testing
Advanced test reporting, quality dashboards, predictive analytics, trend analysis, and executive reporting for QE metrics. Use when communicating quality status, tracking trends, or making data-driven decisions.
extract-test-set
tradingstrategy-ai
Extract raw price dataframe for a test case
detect-metrics
tidymodels
Detect and list all metric functions in the yardstick package. Use when a user asks to find, list, or identify all metrics in the package.