Art & Design

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.

Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

Tool lifecycle UI components for React/Next.js from ui.inference.sh. Display tool calls: pending, progress, approval required, results. Capabilities: tool status, progress indicators, approval flows, results display. Use for: showing agent tool calls, human-in-the-loop approvals, tool output. Triggers: tool ui, tool calls, tool status, tool approval, tool results, agent tools, mcp tools ui, function calling ui, tool lifecycle, tool pending

UI design and implementation for real product surfaces with taste-first critique, reference routing, project-specific design briefs, variation comparison, and implementation verification. Use when Codex should redesign, build, polish, or critique frontend UI by reading project context, exploring taste, routing through `references/catalog.md`, synthesizing `PROJECT_DESIGN.md` or `design.md`, using investment gates to avoid wrong taste/reference/scope, implementing in the existing stack, and evaluating whether the result is actually better. Best for app screens, dashboards, landing pages, query tools, product surfaces, and design explorations; not for backend-only work or tiny cosmetic edits.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Create technical diagrams using Mermaid syntax for architecture, sequences, ERDs, flowcharts, and state machines. Use for visualizing system design, data flows, and processes. Triggers: diagram, mermaid, architecture diagram, sequence diagram, flowchart, ERD, entity relationship, state diagram, C4 model, component diagram, visualize, draw.

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

Frontend design mode for strong visual direction, UI polish, redesigns, landing pages, and production-grade interface work, including shadcn-based surfaces. Use when the user says `/fd` or explicitly asks for better design, styling, layout, visual quality, or UX polish.

Route design-related HTML artifact tasks to the right artifact skill, reference, design system generation, or export skill.

Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.

Use when the user wants to write, draft, or author an RFC (Request for Comments) / technical design doc for a feature, change, or architectural decision. Interactively interviews the user, grounds the proposal in the actual codebase, presents 2-3 concrete API/code-snippet approaches to choose from, then writes a review-ready RFC. Triggers on "write an RFC", "draft an RFC", "RFC for X", "design doc for X", or /rfc.

Use when the user runs /prove-it or says prove it, prove the changes, show me in the browser, or asks to prove a UI or API change. Don't use only because the agent is about to say done, for types-only work, or for docs with no behavior to prove.

Route design-related HTML artifact tasks to the right artifact skill, reference, design system generation, or export skill.

Route design-related HTML artifact tasks to the right artifact skill, reference, design system generation, or export skill.

OpenChatCut product knowledge — UI layout, editor features, and how generation providers are configured. Use when the user asks about the product interface, how to use a feature, where to find something, or needs GUI guidance for something the agent cannot do directly. Also use as fallback when a task fails and the user needs to complete it manually in the UI. NOT for live project-state queries ("where are my folders?", "what's on my timeline?", "where is clip X?") — those are answered by `read_project`, not by this skill.

Describe patterns that may indicate bad-faith or manipulative communication including gish gallop, whataboutism, tone policing, motte-and-bailey, sealioning, lying by omission, deflection, and strategic evasion. Use when the user suspects manipulation, notices repeated non-engagement, wants to analyze debate tactics, or mentions 'bad faith', 'deflection', 'manipulation', 'dodging the question', 'avoiding the issue', 'gaslighting', 'moving goalposts'. Describes behavioral patterns without making psychological diagnoses.

Spark, pandas, polars, DuckDB optimization for batch data processing. Activate on: batch processing, Spark optimization, polars, DuckDB, pandas performance, data frame, shuffle, partition, memory optimization. NOT for: streaming pipelines (use streaming-pipeline-architect), warehouse queries (use data-warehouse-optimizer).

Use when designing a background-job system, choosing between BullMQ / Sidekiq / RQ / Temporal / SQS, deciding queue-vs-workflow, sizing concurrency vs rate limits, building dead-letter queues, or making handlers idempotent. Triggers: jobs running twice on retry, lost jobs after worker crash, DLQ filling up, Redis OOM from job backlog, exactly-once requested, "do we need Temporal?", visibility timeout / lockDuration confusion, exponential backoff vs jitter, fan-out fan-in workflows. NOT for outbound webhook publishing (different concerns), receiver-side webhook handling (different concerns), event-streaming/Kafka topology, or in-process async (event loop only).

Use when building content-heavy sites with Astro, deciding between SSG/SSR/hybrid, choosing client directives (idle/visible/load/media), structuring content collections with type-safe schemas, integrating React/Vue/Solid/Svelte components in the same project, or migrating from Next.js for marketing/docs. Triggers: client:idle vs client:load tradeoffs, content collections schema with zod, image optimization via @astrojs/image, view transitions, server islands, MDX layouts. NOT for SPA-style apps that need full interactivity (use Next/Remix), Astro internals/plugin authoring, or non-content sites where islands provide no benefit.

Expert in background job processing with Bull/BullMQ (Redis), Celery, and cloud queues. Implements retries, scheduling, priority queues, and worker management. Use for async task processing, email campaigns, report generation, batch operations. Activate on "background job", "async task", "queue", "worker", "BullMQ", "Celery". NOT for real-time WebSocket communication, synchronous API calls, or simple setTimeout operations.

>- Refactor apps so backend owns runtime truth and UI only projects snapshots. Use when tools have split authority. NOT for cosmetic UI work or new features before drift is removed.

Automatically intercepts and optimizes prompts using the prompt-learning MCP server. Learns from performance over time via embedding-indexed history. Uses APE, OPRO, DSPy patterns. Activate on "optimize prompt", "improve this prompt", "prompt engineering", or ANY complex task request. Requires prompt-learning MCP server. NOT for simple questions (just answer them), NOT for direct commands (just execute them), NOT for conversational responses (no optimization needed).

AWS CDK infrastructure builder using TypeScript with L2/L3 constructs and Well-Architected patterns. Activate on: AWS CDK, CDK construct, CDK stack, CDK pipeline, AWS infrastructure as code TypeScript, L2 construct, CDK patterns. NOT for: Terraform IaC (use terraform-module-builder), Kubernetes manifests (use kubernetes-manifest-generator), serverless framework (use devops-automator).

Build audio transcription pipelines with Whisper, Deepgram, and AssemblyAI including speaker diarization and real-time streaming. Activate on: transcription, speech-to-text, diarization, audio processing, meeting transcripts. NOT for: text-to-speech synthesis (voice-audio-engineer), music generation (ai-engineer).