Production-ready CSS transitions for web apps. Use when implementing notification badges, dropdowns, modals, panel reveals, page transitions, card resizes, number pop-ins, text swaps, icon swaps, success checks, avatar group hovers, error state shakes, search/input clear, skeleton loaders, shimmer text, sliding tabs, tooltips, staggered text reveals, card hover tilt, plus-to-menu morph, accordions, toasts, like buttons, learn-more hovers, checkbox checks, spinning counters, or toggles. Triggers on "add a transition", "animate the dropdown", "make the modal open smoothly", "swap icon", "page slide", "stagger animation", "open / close transition", "make it animate", "fade between", "success animation", "form error", "shake on invalid", "hover lift", "avatar stack hover", "clear the search", "skeleton loader", "loading shimmer", "shimmer text", "sliding tabs", "segmented control", "tooltip", "reveal text", "tilt card", "3D hover tilt", "cursor glare", "plus to menu", "FAB morph", "accordion", "collapsible", "expand / collapse", "disclosure", "toast", "snackbar", "like button", "heart animation", "learn more arrow", "checkbox", "check animation", "spinning counter", "odometer", "slot machine digits", "toggle", "switch". Also "motion tokens", "scan for ad-hoc transitions", "replace hardcoded durations with motion tokens", "tokenize my animations", and the commands transitions reveal, transitions review, transitions apply, transitions refine.

Ships a finished feature, bug fix, or refactor end-to-end — explores the change's impact on docs/site/README, generates release notes (via pr-release if present, otherwise inline from git log), writes a complete PR description (including QA screenshots and summary when qa-report/qa-execution artifacts exist), commits staged changes following the repo's commitlint config, opens the PR via gh CLI, and optionally launches a CodeRabbit review watch loop. Use when a feature/bug/refactor is implementation-complete and ready to ship. Do not use for draft PRs without finished work, for amending an already-merged PR, for repo-level release publishing (use pr-release directly), or for in-progress development checkpoints.

Maintains workflow-scoped task memory for CompozyOS runs using .compozy/tasks/<name>/memory/ files. Use when a task prompt provides workflow memory paths and requires the agent to read, update, compact, and promote durable context across spec task executions. Do not use for PR review remediation, global user preferences, or programmatic event-log summarization.

Performs a comprehensive code review of a spec implementation and generates a review round directory with issue files compatible with cy-fix-reviews. Use when reviewing implemented spec tasks, creating a manual review round without an external provider, or performing a quality audit of code changes. Do not use for fetching reviews from external providers, fixing existing review issues, executing spec tasks, or editing source code.

Executes agent-authored review remediation using existing round files under .compozy/tasks/<name>/reviews-NNN/. Use when resolving batched review issues, updating issue markdown files, implementing fixes, and verifying the result. Do not use for task execution, review generation, or generic coding tasks without review issue files.

Executes one spec task end-to-end uninterrupted — resolves spec conflicts autonomously, implements, validates, and updates tracking without pausing for questions. Use when a prompt includes a task specification that must be implemented, validated, and reflected in task tracking files. Do not use for PR review batches, generic coding tasks without a spec task file, or standalone verification-only work.

Use when the user wants to audit local git worktrees against origin/x, choose by number or A, and decide whether stale worktree directories, already-merged worktrees, or no-delta worktrees can be cleaned up. Triggers on "worktree clean", "worktree 合并到 x", "检测哪些 worktree 已进 x".

AI-agent-driven UI verification for OneKey. Use to actually drive the running app and confirm a visual/interactive change works — Electron desktop via Chrome DevTools Protocol (CDP) on port 9222 with playwright-core, and React Native (iOS/Android) via callstack agent-device. Triggers on "verify the UI", "drive the app", "screenshot the change", "check it on desktop/simulator", "CDP 9222", "agent-device", "UI 验证", "跑一下看看", "截图确认".

Reference-only catalog of UI workaround recipes. Do NOT auto-load — invoke ONLY when the user explicitly asks for "1k-ui-recipes" or a specific recipe by name (iOS tab bar scroll offset, startViewTransition, collapsible tab horizontal scroll, Android bottom tab touch intercept, keyboard avoidance, iOS overlay navigation freeze, web keyboardDismissMode, iOS modal Fabric frame animation, Android background thread timers/microtasks).

OneKey TradingView app bridge guide. Use when changing or debugging TradingView/WebView/iframe communication, chart URL params, kline/history/realtime messages, marks, Hyperliquid price scale, Perps SYMBOL_CHANGE, chart lines, order draft/cancel/drag-amend messages, FORCE_RECOVER_WS, or tradingview_* methods between the app repo and the chart repo. 适用于 TradingView 通信、图表 WebView 通信、K 线、perps 线、marks、消息桥排查。

App-side OneKey Trade/Swap/Market guide for Swap core, Swap Pro, Wallet Home and Home Token entries, Send/Earn/Market/Buy handoffs, native/mobile host differences, K-line/chart, token selectors, cold-start frame-by-frame validation, quote/build/send flows, history/status, provider channels, PrivateSend-like channels, stock-trading channels, limit/order flows, fees, slippage, ETA, and cross-module funding handoffs.

Jotai state management patterns — atoms, globalAtom, contextAtom, and persistence.

Sentry error tracking and monitoring for OneKey. Use when configuring Sentry, filtering errors, analyzing crash reports, or debugging production issues. Covers platform-specific setup (desktop/mobile/web/extension) and error filtering strategies.

Analyze accumulated bug fix cases and propose updates to the self-testing checklist. Use periodically (weekly/monthly) to evolve quality checks based on real issues.

Generate a 24-hour PR activity report grouped by module with Chinese summaries. Use when the user asks for PR statistics, daily report, PR summary, or mentions "PR 统计", "每日报告", "PR 汇总", "日报".

Reviews package version upgrades — diffs source between versions, traces call sites, and generates compatibility reports.

Use only for explicit OneKey Perps/Hyperliquid (`views/Perp`, ServiceHyperLiquid, perpetuals, 永续/合约, Perps trading). Covers orderbook/L2/BBO, TWAP, scale/TIF/trigger/reduce-only, Perps TradingView/K-line, Perps Relay deposit, token selector, positions/account state/PnL/funding/margin/liquidation. Exclude generic Swap/Market/TradingView; Swap Relay quote/status/pending/requestId alone is not enough unless Perps deposit/Hyperliquid/`views/Perp`/`usePerpDeposit`/`fetchPerpDeposit*`/`perpsDepositOrderAtom` is explicit.

Performance optimization for React/React Native — re-renders, memoization, FlashList, memory leaks, and bundle size.

Systematic performance optimization and regression debugging for OneKey mobile app (iOS). Use when: (1) Fixing performance regressions - when metrics like tokensStartMs, tokensSpanMs, or functionCallCount have regressed and need to be brought back to normal levels, (2) Improving baseline performance - when there's a need to optimize cold start time or reduce function call overhead, (3) User requests performance optimization/improvement/debugging for the app's startup or home screen refresh flow.

Monitors a PR's CI checks and review comments until all pass and issues are resolved. Auto-fixes CI failures, addresses inline review comments, replies, and resolves threads. Use when watching CI status, waiting for checks to pass, fixing CI errors, or resolving review feedback on a pull request.