Brief â plan
openbooklet.com/s/brief-planopenbooklet.com/s/[email protected]GET /api/v1/skills/brief-planDirection first, building second. Nothing is modelled until the brief and the plan exist, because the plan is what lets several agents build at once without asking each other where things are.
Make a Mirage world playable as a small game with @miragekit/game - interactables (pick up, use, open, light), inventory, flags, events, hinged doors and pushable props (Rapier physics, lazy WASM), a character controller, keyboard / mouse / gamepad / touch input, procedural 3D sound, save / load and an accessible HTML overlay (objective, prompt, toasts, menu). Use when the user wants something to do in a world - "add a lever / key / door / quest", "make it a game", "pick up", "inventory", "save game", "sound", "HUD" - or a scenario needs near / prompt / flags.
Write or fix one Mirage world module (modules/<name>.js) that follows the world protocol - positions only from the site plan, seeded randomness, anchors offered and consumed, NOTES.md requests, walk-grid collision and collider proxies, materials through patch() hooks or the texture layer, triangle and draw-call budgets, and a self-test. Use when asked to "build the pier / walls / terrain / trees module", "add X to the world", when a sub-agent is given one module of a Mirage world, or when a module fails, leaks, flickers or blocks the walk.
Lead several agents building one Mirage world at the same time, one module each - the coordination contract (site plan as single source of truth, file ownership, anchors, append-only NOTES.md requests, merge order, conflict rules), how to launch workers in Claude Code (background sub-agents), Codex or Cursor, and how to integrate and verify. Use when a Mirage world has three or more modules to write, or the user says "build in parallel", "use sub-agents", "split the world", "fan out", "team of agents".
The agent self-test loop for a Mirage world - build, run it in the real Chrome, drive it with a scripted JSON scenario (walk routes, keys, interactions), collect screenshots, a contact sheet and metrics (positions, collision, console errors, flicker along a path, frame time), read the pass/fail report, fix, rerun. Use after any change to a Mirage world, before saying a world or module is done, and when the user says "test it", "playtest", "does it work", "check collisions", "is it flickering", "how fast is it", "screenshots".
Auto-indexed from paraldaMeta/mirage-engine
Are you the author? Claim this skill to take ownership and manage it.
Related Skills
graceful-error-recovery
Use this skill when a tool call, command, or API request fails. Diagnose the root cause systematically before retrying or changing approach. Do not retry the same failing call without first understanding why it failed.
audience-aware-communication
Use this skill when writing any explanation, documentation, or response that will be read by someone else. Match vocabulary, depth, and format to the audience's expertise level before writing.
Refactoring Expert
Expert in systematic code refactoring, code smell detection, and structural optimization. Use PROACTIVELY when encountering duplicated code, long methods, complex conditionals, or any code quality issues. Detects code smells and applies proven refactoring techniques without changing external behavior.
Research Expert
Specialized research expert for parallel information gathering. Use for focused research tasks with clear objectives and structured output requirements.
clarify-ambiguous-requests
Use this skill when the user's request is ambiguous, under-specified, or could be interpreted in multiple ways. If proceeding with a wrong assumption would waste significant work, always ask exactly one focused clarifying question before doing anything.
structured-step-by-step-reasoning
Use this skill for any problem that involves multiple steps, tradeoffs, or non-trivial logic. Think out loud before answering to improve accuracy and transparency. Apply whenever the answer is not immediately obvious.