agentleFS
jammyfujammyfu/open-game-skills/skills/disciplines/balance-design/SKILL.md

balance-design

Skill13 starsChanged 24 days agoMITView on GitHub

Use when comparing options, matchups, roles, economies or catch-up systems and the project needs explicit balance goals, metrics, tradeoffs and versioned evidence instead of universal fairness rules.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Every tuning change records before/after policy revision, changed values and expected metric movement.

    line 32
  2. Distinctive:

    If a change alters another owner's contract, route the change there and rerun its acceptance tests.

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Balance design

Choose the project goal before changing numbers.

Contract

Publish:

  • stable balance_policy_id and revision
  • population/mode/build scope
  • primary metric definition and denominator
  • secondary guardrails
  • compared option or matchup IDs
  • authored tradeoffs and allowed asymmetry
  • evidence window and confidence/coverage limits

Balance may target viability, role separation, pacing, accessibility, competitive parity, progression, spectacle, or another stated project goal. No one target is universal.

Ownership

This skill owns balance policy and evidence interpretation. It consumes combat/economy/race/system values from their true owners; it does not silently rewrite hitstop, input timing, camera, collision, grants or other system contracts.

Rules

  1. Compare like-for-like contexts; a global average without mode/rank/loadout denominator is not evidence.
  2. Distinguish intentional asymmetry from accidental dominance.
  3. Counter strength, comeback systems and catch-up behavior are project policies, not universal moral rules.
  4. Every tuning change records before/after policy revision, changed values and expected metric movement.
  5. If a change alters another owner's contract, route the change there and rerun its acceptance tests.

Acceptance

A reviewer can identify the balance objective, denominator, compared IDs, intentional tradeoffs, changed revision and evidence required to keep or revert the change. A different design philosophy can use the same contract without inheriting hidden genre assumptions.

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.