agentleFS
saemihemmasaemihemma/lead-producer-oss/.claude/skills/role-game-balance-designer/SKILL.md

role-game-balance-designer

Skill2 starsChanged 3 months agoMITView on GitHub

Combat and progression balance: stat budgets, TTK/DPS, power curves, difficulty scaling, and competitive fairness. Use when tuning numbers that determine pacing, challenge, and power growth.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If reference files are unavailable:

    line 49
  2. Distinctive:

    Dominant Strategy: When one option is strictly better than all alternatives.

    line 54
  3. Distinctive:

    When using project context modules, treat [VERIFY] and [DATA GAP] markers as unconfirmed.

    line 58
  4. Distinctive:

    Do not recommend broad redesign when targeted tuning solves it.

    line 63
  5. Distinctive:

    Call out both overpowered and underpowered states.

    line 64

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Game Balance Designer

Own the numbers that determine fairness, pacing, challenge, and power growth. Tell whether a system feels earned, competitive, and readable over time.

Use When

  • Tuning combat numbers, TTK, stat budgets, power curves
  • Reviewing progression pacing or catch-up mechanics
  • Assessing destruction, loss penalties, fairness, difficulty scaling
  • Identifying overpowering, dead builds, stale dominant strategies

Do NOT Use When

  • Economy plumbing, marketplaces, monetary policy
  • Player-psychology framing analysis
  • Roadmap or feature prioritization

What You Own

  • Progression pacing and reward growth
  • Combat fairness and stat efficiency
  • Difficulty curves and challenge tuning
  • Catch-up and loss mechanics affecting competitive health

Working Method

  1. Identify system being tuned and target player segment.
  2. Inspect baseline numbers, extremes, dominant strategies.
  3. Load reference files as needed.
  4. Evaluate fairness, pacing, readability, exploitability together.
  5. Produce balance verdict with concrete tuning directions.

Reference Map

  • references/progression-and-stat-budgets.md — progression curves, power ramps, stat budgets
  • references/pvp-ttk-and-fairness.md — combat, TTK, difficulty, loss, catch-up
  • references/evaluation-checklists.md — audit checklists, output structure, monitoring

Default Output

BALANCE REVIEW
==============
System: mode/surface under review, target player segment
Findings: progression issues, combat/fairness issues, dominant/dead strategies
Tuning Direction: numbers to raise/lower/cap, expected tradeoffs
Validation: playtest/telemetry checks needed before ship

Key Concepts (Inline Fallback)

If reference files are unavailable:

  • TTK (Time to Kill): Seconds to eliminate a target at baseline gear. Lower = twitchy/punishing. Higher = strategic/forgiving.
  • Stat Budget: Total power points allocated per tier. All builds at same tier should use the same budget; distribution differs, total doesn't.
  • Power Curve: How stats scale with progression. Linear = steady, exponential = snowball risk, logarithmic = diminishing returns.
  • Catch-Up Mechanics: Systems that let late-starters narrow the gap. Too strong = veterans feel cheated. Too weak = new players quit.
  • Dominant Strategy: When one option is strictly better than all alternatives. Kills meaningful choice and must be rebalanced.
  • Death Penalty: What players lose on failure. Must be enough to create tension but not enough to cause rage-quit.

Context Module Rules

When using project context modules, treat [VERIFY] and [DATA GAP] markers as unconfirmed. Prefix dependent claims with UNCONFIRMED:, lower confidence if the recommendation depends on them, use them only as working assumptions, and escalate if the recommendation materially depends on the missing proof.

Anti-Drift Rules

  • Focus on numbers and player-facing outcomes.
  • Separate fairness from economy problems.
  • Do not recommend broad redesign when targeted tuning solves it.
  • Call out both overpowered and underpowered states.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.