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
- smileynet/game-spicetheir own version, first seen Feb 17, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- smileynet/game-spice★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository194 other files it gives its agents.
- llms.txtllms.txt
- hd-sprite-sequenceSkill
- pixel-animationSkill
- skin-weightsSkill
- spine-skeletalSkill
- sprite-atlasSkill
- sprite-catalogSkill
- sprite-skinSkill
- art-bibleSkill
- asset-pack-intakeSkill
- character-rigSkill
- materialsSkill
- model-pipelineSkill
- open-asset-fixtureSkill
- vfx-generateSkill
- a11y-controlsSkill
- ability-gateSkill
- action-feelSkill
- ad-breakSkill
- adventure-toolSkill
- aggro-tableSkill
- aim-assistSkill
- ammo-reloadSkill
- analytics-funnelSkill
- animation-blendSkill
- animation-graphSkill
- asset-runtimeSkill
- attack-tellSkill
- audio-busesSkill
- audio-feelSkill
- avatar-createSkill
- balance-designSkill
- boss-designSkill
- browser-inputSkill
- camera-anti-clipSkill
- camera-modestySkill
- camera-shotsSkill
- cert-handoffSkill
- chemistry-verbsSkill
- climb-vaultSkill
- cloud-saveSkill
- collision-layersSkill
- combo-designSkill
- cover-shooterSkill
- cover-spaceSkill
- crafting-loopSkill
- currency-dualSkill
- cutscene-handoffSkill
- day-nightSkill
- death-carrySkill
- debug-slateSkill
- deck-buildSkill
- dialogue-beatSkill
- dialogue-flagsSkill
- dodge-iframeSkill
- durability-economySkill
- encounter-designSkill
- enemy-aiSkill
- enemy-fireSkill
- enemy-kit-balanceSkill
- The first 60 shown.
The file
Files
Difficulty design
Difficulty is a versioned project policy, not a fixed ordering of knobs.
Contract
Publish:
- stable
difficulty_policy_idand 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
- Scaling must be observable in project data or documentation; no silent rule changes that cannot be reproduced.
- Static regions, level sync, rank-based scaling, adaptive systems and fixed challenge are all valid when explicitly chosen.
- Readability comes from the owning tell/UI/accessibility contracts. High threat does not imply one universal tell length.
- Compare changes in a declared measurement context; do not mix different builds, modes or player populations without labeling them.
- 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.
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
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.

