lux

Lazy-load for LUX Unity bridge and MCP game-development operations: status, compile, tests, logs, launch, screenshots, hierarchy, dynamic code, record/replay, and one-loop MCP workflows.

Lazy-load only when this workflow is explicitly needed. Use for durable technical choices. Output a short ADR: Context, Decision, Alternatives, Consequences, Verification, Owner. Prefer existing LUX boundaries: gateway owns CLI/server, bridge owns Unity protocol, Skills owns passive workflows. Reject duplicate state, hidden fallback, and broad rewrites without evidence.

Lazy-load only when this workflow is explicitly needed. Use to review an existing design or implementation for boundary drift. Check SSoT, responsibility split, protocol consistency, atomicity, idempotency, and observable failures. Return ranked findings with file references, risk level, and the smallest corrective action.

Lazy-load only when this workflow is explicitly needed. Use when a change risks architectural drift. Enforce: .lux is SSoT; clear subsystem ownership; consistent schemas; atomic operations; idempotent retries; no silent fallback. Report violations and concrete repair steps.

Lazy-load only when this workflow is explicitly needed. Use for high-risk product, automation, or ethical decisions. Run: clarify intent; quantify evidence; check user/data/IP/fairness risks; define stop and rollback conditions; record approval. Verdicts: PASS, REVIEW, or REJECT.

Lazy-load only when this workflow is explicitly needed. Use to turn observed failures into actionable reports. Capture summary, environment, exact steps, expected result, actual result, logs, suspected subsystem, severity, reproducibility, and minimal next diagnostic. Do not invent fallback data.

Lazy-load only when this workflow is explicitly needed. Use to classify and route defects. Determine impact, scope, likely owner, regression window, blocking status, and verification path. Prefer quick reproduction and narrow hypotheses before implementation.

Lazy-load only when this workflow is explicitly needed. Use to write release notes from verified changes. Group by Added, Changed, Fixed, Removed, Security, and Internal. Mention user-visible impact first. Exclude unverified claims and noisy implementation detail.

Lazy-load only when this workflow is explicitly needed. Use after incidents or milestones. Record what happened, impact, root causes, what worked, what failed, concrete follow-ups, owners, and prevention checks. Keep it blameless and evidence-based.

Lazy-load only when this workflow is explicitly needed. Use to document or reduce debt. Describe symptom, cost, affected files, invariant risk, simplest cleanup, tests needed, and what not to change. Prefer deletion and reuse over new abstractions.

Lazy-load only when this workflow is explicitly needed. Use to design or run regression checks for changed behavior. Prefer targeted tests first, then typecheck/lint/build/smoke. Include command, expected signal, observed result, and remaining untested risk.

Lazy-load only when this workflow is explicitly needed. Use before packaging or publishing. Verify build, tests, docs, CLI help, version metadata, migration notes, security posture, rollback plan, and known limitations. Do not release with unexplained failing checks.

Lazy-load only when this workflow is explicitly needed. Use for fast confidence after a change. Run the smallest commands that prove the edited path starts, responds, or compiles. Report exact command output summary and stop when the core claim is proven.

Lazy-load only when this workflow is explicitly needed. Use when adding or refactoring helper utilities for tests. Keep helpers small, deterministic, local to the test domain, and named by behavior. Avoid hiding assertions or creating broad fixtures that mask failures.

Lazy-load only when this workflow is explicitly needed. Use to configure test environments. Make setup explicit, deterministic, isolated, and reversible. Avoid global state leaks, hidden network dependency, and shared temp paths.

Lazy-load only when this workflow is explicitly needed. Use to review LUX diffs for correctness, maintainability, security, and tests. Check Rust Axum/CLI conventions, React strict hooks, no UI mock fallback data, Unity 6000+ bridge compatibility, protocol consistency, and fresh verification evidence.

Lazy-load only when this workflow is explicitly needed. Use to investigate latency, memory, CPU, file IO, startup, or UI responsiveness. Define the measured claim, collect baseline data, identify the hot path, change one variable, and verify improvement without weakening correctness.

Lazy-load only when this workflow is explicitly needed. Use for credentials, command execution, network exposure, logs, generated code, or Unity automation guardrails. Check auth, input validation, path traversal, secret redaction, destructive actions, auditability, and least privilege.

Review a file or small set of files for standards, architecture, SOLID, performance, testability, and implementation risks, with optional specialist subreviews.

Guided game concept ideation from vague ideas to a structured concept brief, using collaborative questioning, concept generation, loop design, and scope validation.

Check whether a project is ready to advance to the next development phase by verifying artifacts, quality evidence, manual unknowns, and advisory reviewer feedback.

Quickly orient the user in the project workflow, identify the most likely current phase, and recommend the single best next action with concise supporting context.

Create, update, or summarize a sprint plan from current milestones, prior velocity, ready work, risks, and available capacity, with an optional feasibility review.

Adapter

Builder

Command

Composite

Decorator

Dependency Injection

Dirty Flag

Facade

Factory Method

Mediator

Memento

MVP

Object Pooling

Observer

Prototype

Proxy

Service Locator