Loading...
Loading...
Found 1,893 Skills
Stage 2 code quality review. Triggers: 'quality review', 'check code quality', or /review stage 2. Requires spec-review to have passed first. Checks SOLID, DRY, security, and test quality. Do NOT use for spec compliance — use spec-review instead.
Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic). Not for ASR auth (/riva-asr).
Process external code review feedback with technical rigor. Use when receiving feedback from another LLM, human reviewer, or CI tool. Verifies claims before implementing, tracks disposition.
Expert-level real estate systems, property management, MLS integration, CRM, virtual tours, and market analysis
Use when porting a workflow to a different AI provider, deployment environment, model tier, or organizational context.
MSW 아바타 관리 — 코스튬(CostumeManagerComponent 17슬롯) + 애니메이션 3계층 파이프라인(StateComponent → AvatarStateAnimationComponent → AvatarRendererComponent). State 키(대문자)/AvatarBodyActionStateName(소문자)/MapleAvatarBodyActionState enum/스프라이트 액션 ID(swingO1, shoot1) 4단계 구분, IsLegacy/ActionSheet/StateToAvatarBodyActionSheet 두 시스템, PlayerControllerComponent 자동 상태 전이와 ActionStateChangedEvent 충돌 시 RemoveActionSheet/SetActionSheet/BodyActionStateChangeEvent로 해결. DefaultPlayer뿐 아니라 모든 엔티티(NPC, 몬스터 등)에 적용 가능. Use for avatar costume get/set, 17 equip slots, animation state mapping, action override, weapon-specific attack motion, custom shoot/cast/dance action. Keywords: avatar, costume, animation, state, action, shoot, swing, weapon, ActionStateChangedEvent, BodyActionStateChangeEvent, RemoveActionSheet, SetActionSheet, StateToAvatarBodyActionSheet, AvatarStateAnimationComponent, AvatarRendererComponent, MapleAvatarBodyActionState, PlayerControllerComponent, 아바타, 코스튬, 애니메이션, 상태, 동작, 장비, 무기, 공격, 활, 칼, 사격, 휘두르기, 커스텀 액션, 자동 재생 차단, 매핑 변경.
Adversarial robustness engineering for ML/AI—evasion, poisoning, extraction, membership-inference threat models; robust training, sanitization, detectors; ASR/certified evals; lab model attacks; data-pipeline integrity; production I/O guardrails (classical ML and LLM/multimodal). Use for adversarial examples, robustness suites, poison audits, deploy guardrails—not LLM app red team (ai-redteam), governance (ai-risk-governance), safety classifier R&D (ml-research-engineer-safeguards), safeguard serving (ml-infrastructure-engineer-safeguards), privacy research (privacy-research-engineer-safeguards), AppSec pentest (penetration-tester).
Build 3D objects, props, maps, and environments in Roblox Studio via MCP. CSG patterns, spatial coordination, player scale reference, platform quirks. Use when the AI is placing parts, doing unions/subtracts, or building geometry.
12 production footguns ranked by severity. Data loss, exploits, memory leaks, mobile perf.
Run the Codex Readiness unit test report. Use when you need deterministic checks plus in-session LLM evals for AGENTS.md/PLANS.md.
Specialized research expert for parallel information gathering. Use for focused research tasks with clear objectives and structured output requirements.
Complete Love2D game development from prototype to polished release. Covers core architecture, graphics, animation, tiles, collision, audio, and iOS deployment. Use when building Love2D games, implementing game mechanics, or deploying to mobile platforms.