Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

Implements and debugs browser Summarizer, Writer, and Rewriter integrations in JavaScript or TypeScript web apps. Use when adding availability checks, model download UX, session creation, summarize or write or rewrite flows, streaming output, abort handling, or permissions-policy constraints for built-in writing assistance APIs. Don't use for generic prompt engineering, server-side LLM SDKs, or cloud AI services.

Implements and debugs browser Proofreader API integrations in JavaScript or TypeScript web apps. Use when adding Proofreader availability checks, monitored model downloads, proofread flows, correction metadata handling, or permissions-policy checks for built-in proofreading. Don't use for generic prompt engineering, server-side LLM SDKs, or cloud AI services.

Implements and debugs browser Web Neural Network API integrations in JavaScript or TypeScript web apps. Use when adding navigator.ml checks, MLContext creation, MLGraphBuilder flows, device selection, tensor dispatch and readback, or explicit fallback paths to ONNX Runtime Web or other local runtimes. Don't use for model training, server-side ML inference, or cloud AI APIs.

Implements and debugs browser Translator API integrations in JavaScript or TypeScript web apps. Use when adding Translator support checks, language-pair availability flows, model download UX, session creation, translate() or translateStreaming() calls, input-usage measurement, or permissions-policy handling for on-device translation. Don't use for server-side translation SDKs, cloud translation services, or generic multilingual content pipelines.

Implements and debugs browser WebMCP integrations in JavaScript or TypeScript web apps. Use when exposing imperative tools through document.modelContext (with a navigator.modelContext fallback), annotating HTML forms for declarative tools, handling agent-invoked form flows, or validating WebMCP behavior in the current Chrome preview. Don't use for server-side MCP servers, REST tool backends, or non-browser providers.

Implements and debugs browser Language Detector API integrations in JavaScript or TypeScript web apps. Use when adding LanguageDetector support checks, availability and model download flows, session creation, detect() calls, input-usage measurement, permissions-policy handling, or compatibility fallbacks for built-in language detection. Don't use for server-side language detection SDKs, cloud translation services, or generic NLP pipelines.

Implements and debugs browser Prompt API integrations in JavaScript or TypeScript web apps. Use when adding LanguageModel availability checks, session creation, prompt or promptStreaming flows, structured output, download progress UX, or iframe permission-policy handling. Don't use for server-side LLM SDKs, REST AI APIs, or non-browser providers.

Build and deploy serverless applications using EasySAM. Use when the user wants to scaffold a new project, add AWS resources (Lambda, DynamoDB, S3, etc.), or set up CI/CD for an EasySAM project.

Development guide for using the Prismarine DynamoDB ORM. Use when defining DynamoDB models, generating client code, or performing database operations using Prismarine.

Orchestrate an authorized, stateful web/API security assessment with bounded preflight, early auth/OOB handoffs, persistent capability and branch scheduling, resumable source/public/auth work, request budgets, evidence gates, clean replay, and redacted reporting. This is the VerumX3/v3 release and is materially different from verumx1; use it for authorized bug bounty or pentest work that must detect missing prerequisites before expensive mapping and never count blocked work as negative coverage.

When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatGPT,' 'optimize for Perplexity,' 'AI citations,' 'AI visibility,' 'zero-click search,' 'how do I show up in AI answers,' 'LLM mentions,' 'optimize for Claude/Gemini,' 'llms.txt,' 'OKF,' 'Open Knowledge Format,' 'knowledge bundle,' or 'agent-readable site.' Use this whenever someone wants their content to be cited or surfaced by AI assistants and AI search engines. For traditional technical and on-page SEO audits, see seo-audit. For structured data implementation, see schema.

Daily maintainer routine — open issues / PR review / build health / broken-link audit via canonical MAINTAINER-PIPELINE. TRIGGER when: user says "maintainer", "跑 maintainer", "daily PR review", "issue triage", or routine `twmd-maintainer-daily` fires.

讀者站上回報（Supabase）→ 分類/反 spam/去重 → GitHub issue（對齊既有 template）→ 接 MAINTAINER 飛輪。Routine twmd-feedback-triage fires 07:00 daily（maintainer-am 之前）; manual via "/twmd-feedback-triage" or "跑 feedback triage" or "把回報轉成 issue". TRIGGER when: routine twmd-feedback-triage fires / user says "跑 feedback triage" / "處理讀者回報" / "把站上回報開成 issue".

Multi-language batch sync (主權的巴別塔) via canonical SQUEEZE-MODELS-MAX-PIPELINE — priority schema (P0/P1/P2/P2.5/P3) + backend cascade + 統一調度器 babel-dispatch.py。 TRIGGER when: user says "巴別塔", "多語 batch", "多語同步", "跑 babel", "繼續 babel".

Add tasks, backlog items, bugs, chores, ideas, follow-ups, or draft issues to the Bangle 2 GitHub Projects board. Use when the user says "add a task", "put this on the board", "make a project task", "track this", "add a backlog item", or asks Codex to create a draft task in the bangle-io GitHub project.

Plan, build, and review one evidence-backed SEO content wave for the Minutes site, including SERP research, page inventory, design-system compliance, internal linking, generated LLM text, and a shipped-wave retro. Use when the user asks for an SEO wave, a group of comparison or use-case pages, a docs or resource hub expansion, or a coordinated batch of search landing pages.

Guidance for delegating focused work to child Agents.

Plan, build, and review one evidence-backed SEO content wave for the Minutes site, including SERP research, page inventory, design-system compliance, internal linking, generated LLM text, and a shipped-wave retro. Use when the user asks for an SEO wave, a group of comparison or use-case pages, a docs or resource hub expansion, or a coordinated batch of search landing pages.

Interview the user about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".