← ClaudeAtlas

interaction-reward-momentslisted

Design and improve in-session reward moments — the reveal, choice, feedback, anticipation and game-feel beats inside one session (손맛, 타격감, 연출, 밋밋하다, 도파민 포인트) — for games, interactive narrative, fortune/saju, AI companion, journaling, learning and similar consumer interactive apps. Use when the deliverable is a named scene, loop, screen or beat: 'the level-complete screen feels hollow', 'make the gacha pull land', 'the tutorial's first win is flat', or a short-session / quit-mid-session complaint (session length is a diagnostic, never a target). Also owns the strength, safety and accessibility of a feel effect — flash, shake, haptics, camera motion — as game feel, not general UI or visual design. A retention metric or a return cited only as motivation ('D7 is low, fix the reward staging') does NOT disqualify this skill. Route away when the deliverable is the cadence or schedule of a battle pass, login rewards, streak or daily quest, to retention-strategy-designer — but the staging of any one of those beats (th
ajitta/Game-Engagement-Retention-Skills · ★ 1 · AI & Automation · score 77
Install: claude install-skill ajitta/Game-Engagement-Retention-Skills
# Interaction Reward Moments A reward moment is a short interaction where anticipation, agency, uncertainty, feedback and meaning combine into one experience peak — a design term, never a claim about neurochemistry, and "dopamine point" never reaches an answer. This file carries the procedure only: every lens, pattern, bound, range and citation lives in a reference module named below, read at generation time and never recalled. Session length is a diagnostic of loop satisfaction, never a target — a four-minute session is evidence about the loop, and inflating the number is not the deliverable. ## Input $ARGUMENTS **Step 0 — 입력 확인.** Fill each required input from the request. For any you cannot fill: if a wrong guess would change **which** proposals you make, ask — one message, all missing items bundled, at most four questions, then stop and wait. If a wrong guess would only change the tuning, write it under `## 전제` tagged `[가정]` and proceed. Never ask twice. If the session cannot ask (non-interactive, piped prompt, or the user said to just answer), assume everything and answer. Assumption bookkeeping is not the deliverable: `## 전제` keeps its four-line cap, carries only the assumptions that would change *which* proposals you make, and never says that you were unable to ask — a first screen spent on caveats is a first screen the designer did not get an answer on. Required: product and genre or domain · platform — mobile, PC-Steam, console, web, Roblox-UGC · shipping market