Integrates the CrazyGames JavaScript SDK (v3) into a browser or HTML5 game. Handles SDK initialization, user authentication and profile retrieval, persistent key/value storage, interstitial and rewarded ad breaks, adblock detection, responsive banner ads, gameplay lifecycle hooks (loadingStart/Stop, gameplayStart/Stop, happytime), and optional Xsolla Pay Station in-app purchases with analytics order tracking. Use when the user mentions CrazyGames, wants to publish or integrate a game on CrazyGames, or needs to add SDK features like ads, user accounts, game events, storage, or in-game purchases to a browser/HTML5/JavaScript game.

Review code for maintainability improvements and best practices.

Write clear, conventional git commit messages

Build a premium PRESENTED slide deck — classic one-slide-at-a-time slides you advance with a clicker — as a Vite + React app. It keeps the Slidev navigation UI (floating glass dock + thumbnail rail + click-builds + presenter) but slides are RESPONSIVE React (reflow to any screen, no fixed canvas) and fully interactive. Use this for a deck you'll PRESENT (talk over, projector, screen-share) when you want web interactivity and responsiveness without Slidev's constraints. The repo IS the running app (Vite + React) — you install it in place, theme the tokens, and AUTHOR an original deck from the user's real topic/brand.

Test-driven development (TDD) with red-green-refactor loop. Use when user wants to build features, fix bugs, mentions "tdd", wants integration tests, or implementing all new code.

Use when writing TypeScript code for Roblox using roblox-ts, especially when unsure if a JavaScript API exists or how to handle Luau interop

Node.js package manager with strict dependency resolution. Use when running pnpm specific commands, configuring workspaces, or managing dependencies with catalogs, patches, or overrides.

Write tests, mock functions, assert values, and configure test suites for Roblox/Luau code using Jest Roblox — a Luau port whose API diverges from JS Jest in subtle, non-obvious ways that LLM training data does not cover. Use whenever encountering Jest in Roblox/Luau code: editing .spec test files, calling jest.fn/jest.mock/spyOn, using describe/it/expect, or debugging Jest tests.

Use when building ECS-based games in Roblox with roblox-ts using jecs for entities, components, queries, and relationships

Opinionated preferences for roblox-ts development. Use when setting up new roblox-ts projects or when coding style/tooling decisions arise.

Use when designing components, systems, or entity structures for jecs in Roblox. Use when deciding if data should be one component or multiple, when archetype transitions seem expensive, or when choosing entity members vs relationships.

为给定问题挑选“最适合回答的人”的专家角色，并用该角色给出回答（含选择理由与行动清单）

Use when 需要计算/解释投资组合的年化收益率、月度现金流与长期（如30年）资产路径，且包含固定支出与不确定收入（自由职业波动、随机收入、回款集中）并需要给出耗尽概率与分位数（P10/P50/P90）

Build UIs with @nuxt/ui v4 — 125+ accessible Vue components with Tailwind CSS theming. Use when creating interfaces, customizing themes to match a brand, building forms, or composing layouts like dashboards, docs sites, and chat interfaces.

改进你的问题

Run an explicitly requested three-option workflow with three independent executors, one independent paired critic per option, bounded revision loops, and a blind evidence-backed judge. Use only when the user invokes $three-way-judge or explicitly requests this exact panel; this v1 skill does not run the nine-review deep mode.

Analyzes discovery call transcripts from Attio (primary) and Granola (secondary) against the Discovery Questions Tracker template, creates or appends to a Google Sheet in the Discovery folder with full scoring, customer answers, and evidence, and posts a summary note to the Attio company record. Outputs an xlsx with tabs matching the original spreadsheet template. Use when the user wants to process a discovery call, fill out discovery questions, create a discovery doc, or run /discovery.

Use when drafting evidence-backed opening lines or subject lines for an eligible contact.

Use when transforming or auditing an existing or already-scoped one-off draft against approved or provisional voice rules after its message type is chosen.

Use when creating an evidence-based candidate-account list or an offline sourcing plan from supplied account criteria and records.