LoogacyStudio
- 40 skills
- 0 followers
- 9 hours ago last updated
- ▌ Benchmark Core · loogacystudio bundleUse when a benchmark agent or skill needs the shared benchmark framework rules — capability map, corpus discovery, corpus adapter contract, lifecycle boundaries, or run-record finalization guidance — rather than one benchmark artifact like a judged run or rerun manifest.
- ▌ Create Subagent · loogacystudio bundleUse when an agent must decide whether a task should stay single-agent or be compiled into a reusable multi-agent topology with explicit subagent roles, context boundaries, orchestration contracts, and provider-specific implementation overlays.
- ▌ Session Handoff · loogacystudio bundleUse when work must continue in a fresh AI agent or later session and a continuation-ready handoff document is needed to preserve goals, decisions, evidence, and exact next steps without ambiguity.
- ▌ Skill Authoring · loogacystudioUse when a repo customization or governance artifact needs a controlled update, review, or new scaffold, especially for skills, prompts, agents, hooks, instructions, learning notes, or change-log discipline.
- ▌ Plan Design Grill · loogacystudio bundleUse when a user wants a plan, proposal, architecture, rollout, or design stress-tested through relentless branch-by-branch questioning that exposes assumptions, resolves forks, and ends with a shared understanding of decisions, risks, and next steps.
- ▌ Benchmark Judge Run · loogacystudio bundleUse when a benchmark execution record or variant run needs a canonical judged record with route-first classification, five-dimension rubric scoring, post-score failure tags, separate invariance or robustness notes, and optional scaffold-to-completed finalization.
- ▌ Create Reusable Skill · loogacystudio bundleCreates or upgrades reusable agent skills by selecting the right skill pattern, generating the minimum useful file structure, drafting SKILL.md, and validating the result before returning it. Use when building a new skill, refactoring a weak skill, or scaffolding companion references and assets.
- ▌ Benchmark Author Item · loogacystudio bundleUse when a new benchmark item, seed draft, or ad hoc eval case needs to be turned into the repository's canonical benchmark-item format with clear task family, route expectation, artifact contract, scoring focus, and variant hooks.
- ▌ Godot Tscn · loogacystudio bundleUse when a Godot/.NET task needs a Layer 4 overlay skill for reading, editing, generating, diff-reviewing, or validating `.tscn` scene files directly, and the agent must preserve scene-file structure, resource ordering, node paths, connections, and editor-compatible conventions instead of treating the file as generic text.
- ▌ Benchmark Author Variants · loogacystudio bundleUse when a benchmark item or judged run needs a reusable variant pack from the repository's canonical metamorphic and adversarial families, with explicit invariants, drift budget, safe-failure rules, and execution-ready transformed input packages.
- ▌ Godot Csharp · loogacystudio bundleUse when a Godot/.NET task needs a Layer 4 overlay skill for writing, refactoring, or translating C# gameplay, tool, editor, resource, or node code, and the agent must stay idiomatic to Godot's C# API, avoid GDScript-only assumptions, choose the right engine-facing patterns, and return implementation guidance plus validation notes.
- ▌ UI UX Review · loogacystudio bundleUse when a Godot/.NET task needs a Layer 4 overlay UX review for a HUD, menu, overlay, prompt flow, or tool UI, and the agent must evaluate information hierarchy, focus, interaction clarity, feedback, readability, and cognitive load before returning concrete quick wins, structural improvements, and verification ideas.
- ▌ Benchmark Cluster Failures · loogacystudio bundleUse when multiple judged benchmark runs need to be grouped into reusable failure-pattern records with taxonomy-aligned tags, root-weakness hypotheses, severity and regression framing, and bounded next-action guidance for downstream proposal or gate work.
- ▌ Benchmark Review Candidate · loogacystudio bundleUse when a wording, routing-policy, rubric, template, or other candidate revision needs a formal promotion review against target-suite gain, protected-suite regressions, invariance, robustness, mutation-surface rules, and official-adoption governance requirements.
- ▌ Runtime Triage · loogacystudio bundleUse when a Godot/.NET task needs a Layer 4 overlay first-response diagnosis for a build failure, editor error, runtime exception, crash, scene load failure, startup failure, or unexplained bad behavior, and the agent must classify the symptom, identify the most likely layer, request only the minimum missing evidence, and return a focused triage report before broader investigation structure is justified.
- ▌ Benchmark Author Skill Evals · loogacystudio bundleUse when a reusable agent skill needs a small, scoreable eval pack with explicit success criteria, trigger prompts, deterministic checks, rubric-based qualitative grading, and extension hooks for regressions, thrashing, or permission drift.
- ▌ Godot Godottest · loogacystudio bundleUse when a Godot/.NET task needs a Layer 4 overlay skill for GoDotTest-based C# testing, and the agent must write, run, debug, or collect coverage for suites, scene wiring, CLI invocation, VS Code debug configs, or coverage commands instead of guessing xUnit/NUnit patterns that do not apply inside Godot runtime.
- ▌ Benchmark Author Rerun Manifest · loogacystudio bundleUse when a bounded candidate revision needs a concrete rerun manifest with target suites, protected suites, benchmark anchors, execution paths, judging focus, and conditional follow-up checks before promotion review.
- ▌ Post Change Review · loogacystudio bundleUse when a Godot/.NET task needs a Layer 4 overlay completion review after a large refactor, multi-file implementation, or new feature, and the agent must assess layer boundaries, engine usage, docs or content sync, and verification evidence before the work should be treated as complete.
- ▌ Godot Dotnet Thread · loogacystudio bundleUse when a Godot/.NET task needs a Layer 4 overlay review or plan for threading, async/await, Task.Run, WorkerThreadPool, threaded resource loading, main-thread marshaling, scene-freeze mitigation, or node lifetime safety specifically because Godot engine state, SceneTree access, Node/Resource lifetime, or main-thread affinity is at risk. Do not use for generic .NET threading without a Godot engine boundary.
- ▌ Test Strategy Review · loogacystudio bundleUse when a Godot/.NET task needs a Layer 4 overlay validation plan for a feature, bug fix, refactor, migration, or UI change, and the agent must separate pure .NET tests from Godot runtime-dependent coverage, prioritize the highest-risk paths first, and return a minimal test matrix plus regression guidance.
- ▌ Version Upgrade Review · loogacystudio bundleUse when a Godot/.NET task needs a Layer 4 overlay upgrade review that evaluates engine, SDK, C# compatibility, addons/plugins, export pipeline, verification, and rollback risk, then returns a staged sequence instead of a risky all-at-once migration.
- ▌ Game Development Fsm · loogacystudio bundleUse when a cross-engine gameplay task has already narrowed to a state-machine-shaped solution and now needs a Layer 2 shared-runtime FSM refactor or sizing decision for growing if/else branches, repeated enter/exit behavior, or scattered transition rules, and the agent must choose the lightest state-machine shape — or explicitly stay simpler — without reopening a broader behavior-architecture comparison.
- ▌ Game Development Goap · loogacystudio bundleUse when a cross-engine gameplay task needs a Layer 2 shared-runtime GOAP design for goal-driven multi-step action planning, explicit world facts, action preconditions and effects, costs, and replanning rules, and the agent must design or review a GOAP system without letting facts, actions, or replanning drift into chaos.
- ▌ Scene Architecture Review · loogacystudio bundleUse when a Godot/.NET task needs a Layer 4 overlay architecture review of a scene, gameplay system, or UI flow specifically to assess scene composition, node responsibility, script ownership, signal boundaries, autoload fit, and UI-to-gameplay coupling, and the agent must judge maintainability seams rather than primarily evaluating readability, focus, feedback, or other UX-only concerns.
- ▌ Abstraction Integrity Review · loogacystudio bundleUse when a Godot/.NET task needs a Layer 4 overlay review to prevent abstraction decay during feature work, flow extension, or touched-code refactoring, especially around flag creep, boundary leakage, compatibility creep, or responsibility drift.
- ▌ Game Development Utility AI · loogacystudio bundleUse when a cross-engine gameplay task needs a Layer 2 shared-runtime Utility AI design for choosing among several simultaneously valid candidates, and the agent must design or review a Utility AI system with explicit scorers, score ownership, tuning rules, and observability instead of drifting into opaque score soup.
- ▌ Game Development Coordinator · loogacystudio bundleUse when a cross-engine gameplay task needs a Layer 2 shared-runtime coordination boundary for brittle reference chains, root-node god scripts, scattered cross-system callbacks, or unclear scene ownership, and the agent must design or review a bounded coordinator layer with an explicit public surface, internal ownership map, forwarding rules, collaboration boundaries, and god-object safeguards.
- ▌ Game Development Object Pool · loogacystudio bundleUse when a cross-engine gameplay task needs a Layer 2 shared-runtime performance review for spawn/despawn churn, GC spikes, or short-lived reusable objects, and the agent must decide whether pooling is truly justified before introducing reuse infrastructure.
- ▌ Game Development Command Flow · loogacystudio bundleUse when a cross-engine gameplay task needs a Layer 2 shared-runtime action-flow design for direct-call coupling, ad-hoc action queues, fragile undo/redo, or request-versus-execution boundaries, and the agent must design or review a command-flow architecture with explicit command contracts, producer and executor roles, validation, timing, and history or replay rules.
- ▌ Game Development Behavior Tree · loogacystudio bundleUse when a cross-engine gameplay task needs a Layer 2 shared-runtime behavior-tree design for hierarchical priorities, fallback branches, running tasks, or interruptible decisions, and the agent must design or review a behavior tree without letting the tree or blackboard become a junk drawer.
- ▌ Game Development World State Facts · loogacystudio bundleUse when a cross-engine gameplay task needs a Layer 1 foundation for world facts, blackboard state, stale observations, or freshness rules, and the agent must define or review a reusable world-state fact model with explicit source ownership, observed-vs-derived boundaries, freshness policy, write permissions, invalidation behavior, and inspection surfaces.
- ▌ Game Development Events And Signals · loogacystudio bundleUse when a cross-engine gameplay task needs a Layer 2 shared-runtime communication-topology review for signal spaghetti, hidden event coupling, duplicate subscriptions, or direct-call versus event boundaries, and the agent must design or review an events-and-signals topology with explicit ownership, lifecycle, payload, and traceability rules.
- ▌ Game Development Behavior Architecture · loogacystudio bundleUse when a cross-engine gameplay task needs a Layer 2 shared-runtime architecture decision — simpler rule flow, FSM, behavior tree, utility scoring, or GOAP-style planning — and the agent must stay comparative before locking in one control pattern.
- ▌ Game Development Condition Rule Engine · loogacystudio bundleUse when a cross-engine gameplay task needs a Layer 1 foundation for reusable condition semantics — preconditions, guard clauses, transition checks, or composite eligibility rules — and the agent must define or review a reusable condition model with explicit rule ownership, inputs, evaluation timing, composition, observability, and failure semantics.
- ▌ Game Development Gameplay Tags And Query · loogacystudio bundleUse when a cross-engine gameplay task needs a Layer 1 foundation for tag taxonomies, query semantics, label sprawl, or enum explosion pressure, and the agent must define or review a reusable gameplay-tag and query model with explicit taxonomy rules, ownership, mutation policy, query semantics, and over-tagging safeguards.
- ▌ Game Development Entity Reference Boundary · loogacystudio bundleUse when a cross-engine gameplay task needs a Layer 1 foundation for entity identity, stale references, payload safety, or handle-versus-pointer trade-offs, and the agent must define or review a reusable entity-reference boundary with explicit identity rules, lookup strategy, lifetime policy, payload safety, and debugging expectations.
- ▌ Game Development State Change Notification · loogacystudio bundleUse when a cross-engine gameplay task needs a Layer 1 foundation for change callbacks, invalidation signals, observer updates, or diff-vs-snapshot semantics, and the agent must define or review a reusable state-change notification model with explicit change boundaries, timing rules, payload shape, batching policy, and invalidation semantics.
- ▌ Game Development Resource Transaction System · loogacystudio bundleUse when a cross-engine gameplay task needs a Layer 1 foundation for cost, spend, reservation, refund, or commit-and-rollback semantics, and the agent must define or review a reusable resource-transaction model with explicit ownership, affordability timing, reservation semantics, failure handling, auditability, and integration boundaries.
- ▌ Game Development Time Source And Tick Policy · loogacystudio bundleUse when a cross-engine gameplay task needs a Layer 1 foundation for timer logic, update cadence, cooldown clocks, pause rules, or frame-vs-fixed-step policy, and the agent must define or review a reusable time-source and tick policy with explicit ownership, sampling cadence, drift handling, pause and scaling semantics, and observability boundaries.