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

difficulty-design

Skill12 starsChanged 22 days agoMITView on GitHub

Use when a project needs explicit difficulty modes, scaling rules, challenge curves or assist policies with measurable outcomes instead of hidden HP-only inflation or genre-specific defaults.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Difficulty design

Difficulty is a versioned project policy, not a fixed ordering of knobs.

Contract

Publish:

  • stable difficulty_policy_id and revision
  • named mode/scaling policy
  • affected systems and excluded systems
  • measurement context: build, segment, player cohort or test mode
  • challenge metrics and guardrails
  • transition/switch rules, including whether mid-session changes are allowed
  • evidence required to accept a tuning change

Possible levers include space, information, resources, enemy composition, timing windows, numbers, assists, checkpoints or other project-defined systems. Their order and use depend on the game.

Ownership

This skill selects and evaluates the difficulty policy. It does not directly own combat clocks, hitboxes, economy ledgers, navigation, camera or save state.

Rules

  1. Scaling must be observable in project data or documentation; no silent rule changes that cannot be reproduced.
  2. Static regions, level sync, rank-based scaling, adaptive systems and fixed challenge are all valid when explicitly chosen.
  3. Readability comes from the owning tell/UI/accessibility contracts. High threat does not imply one universal tell length.
  4. Compare changes in a declared measurement context; do not mix different builds, modes or player populations without labeling them.
  5. A change that crosses another owner's contract reruns that owner's acceptance tests.

Acceptance

A reviewer can name the active policy/revision, what can change, what must remain stable, the measurement context and the evidence needed to show the intended challenge changed without hidden collateral rule changes.

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.