Give a Hearth game real art and sound — importing and slicing spritesheets, animations, procedural sprites and sounds, autonomous CC0 asset sourcing (Kenney, itch.io, OpenGameArt, Freesound, Google Fonts) with licensing rules, and pixel-art discipline (never stretch; read the art before using it). Use when the game…
Structure a Hearth game's world — scenes, entities, components, tilemaps and autotiling (surfaces must connect), collider/sprite alignment, prefabs, animation state machines, and input bindings. Use when creating or arranging what exists in a Hearth game (levels, objects, hierarchies); behavior scripts are…
Write behavior in Hearth — Lua/JS scripts, the ctx API (input, timers, tweens, events, camera, audio, save), script modules and require, the dot-call and userdata pitfalls, deterministic RNG, and the check-script/edit-script iteration loop. Use when making things happen in a Hearth game (movement, AI, pickups, rules)…
Shape a complete Hearth game, not just working mechanics — scoping to session length (the verbs × levels × enemies budget), the teach → develop → escalate → climax → end arc, real endings (a win state, not just game-over), one-element-at-a-time difficulty ramps, scenes-as-levels pacing with gated progress and…
Make a Hearth game feel good, not just run — the juice stack (hit-stop, screen shake, flash, particle bursts, layered sound), tween easing, camera effects, anticipation/recovery animation idioms, game-UX conventions (menus, pause, onboarding, difficulty, save etiquette), effect-asserting playtests, and the quality bar…
Let the engine hunt bugs for you — bot playtesting via hearth sweep. Seeded bot policies (mash/idle/wander/seek) play a scene headlessly across many seeds and report softlocks, crashes, stuck states, and unmet objectives as a compact evidence report; objectives double as executable acceptance criteria; a failing seed…
Operate the Hearth engine as a coding agent — the session loop (recall → snapshot → change → validate → playtest → screenshot → remember), project memory, permission modes, verification, review/undo, and export. Load FIRST whenever a project has a hearth.json or the task mentions Hearth. Routes to the domain skills…
Decision-quality layer for Claude Code that improves user-facing answers and Claude's own technical choices with high-signal tradeoff analysis, context-gap detection, and grounded recommendations.
Use for deeper technical decision analysis when the answer depends on multiple competing constraints, hidden costs, or uncertain assumptions, and a stronger recommendation is needed without changing the user's workflow, including when Claude reaches a meaningful technical crossroads during its own reasoning.
Compare practical implementation approaches to the same engineering goal. Use when the user has one target outcome but multiple technical paths, such as incremental refactor vs rewrite, frontend-heavy vs backend-heavy implementation, service split vs monolith extension, wrapper library vs direct integration, or…
Improve technical and product decision-making with grounded analysis. Use when the user or Claude is deciding between approaches, asking "should I use X or Y?", evaluating a refactor, choosing frontend vs backend responsibilities, judging whether architecture is overkill, assessing a library or dependency choice, or…
Identify missing information, hidden assumptions, and uncertainty that make a technical decision unreliable. Use when the current recommendation may be under-informed, when a decision could flip based on unknown constraints, scale, ownership, security, rollout, or operational details, or when Claude is about to act on…
Compare technical options across the factors that actually matter in context. Use when Claude or the user needs a concrete tradeoff analysis between two or more approaches, such as library choice, architecture choice, refactor vs leave it, frontend vs backend ownership, build vs buy, short-term speed vs long-term…