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.

Enforces fresh verification evidence before any completion, fix, or passing claim, and before commits or PR creation. Use when an agent is about to report success, hand off work, or commit code. Do not use for early planning, brainstorming, or tasks that have not yet reached a concrete verification step.

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.

Decomposes Specs into robust, independently implementable task files, assigning every test case from _tests.md to exactly one task and enriching tasks from codebase exploration. Use when a spec exists and needs to be broken down into executable tasks, or when task files need enrichment with implementation context. Do not use for spec creation or direct task execution.

When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," or "CTA copy." For email copy, see email-sequence. For popup copy, see popup-cro.

Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, micro-interactions, enter/exit animations, choosing or reviewing icons, or any visual detail work. Triggers on UI polish, design details, "make it feel better", "feels off", stagger animations, border radius, optical alignment, image outlines, box shadows, icons, icon stroke weight, icon states, motion restraint.

OKLCH color space and color usage for web projects. Convert hex/rgb/hsl to oklch, generate palettes, check contrast, handle gamut boundaries, theme with Tailwind v4, and apply color with meaning. Triggers on oklch, color conversion, palette generation, contrast ratio, gamut, display p3, design tokens, semantic color tokens, hue drift, chroma, dark mode colors, accent color, color meaning, light and dark appearance, increased contrast.

Guide for tool registration and tool UI in assistant-ui. Use when implementing LLM tools, tool call rendering, or human-in-the-loop patterns.

Guide for assistant-stream package and streaming protocols. Use when implementing streaming backends, custom protocols, or debugging stream issues.

Guide for assistant-ui library - AI chat UI components. Use when asking about architecture, debugging, or understanding the codebase.

Guide for assistant-ui runtime system and state management. Use when working with runtimes, accessing state, or managing thread/message data.

Guide for assistant-ui UI primitives - ThreadPrimitive, ComposerPrimitive, MessagePrimitive. Use when customizing chat UI components.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

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.