Builds a prototype component by component, self-reviewing each component against the Discovery Plan before moving to the next.
Score 70/100
Reviews subscription UX for conversion, clarity, trust, and lifetime value optimization.
Score 70/100
Interactive discovery-and-edit session for a ClaudeWorks profile — search the curated marketplace and local plugins, install missing picks with the user's confirmation, add them…
Score 70/100
Run Claude Code in autonomous iteration loops until task completion — PRD-based feature development, test coverage improvement, lint fixing, documentation generation, dataset…
Score 70/100
PLG motion design — free tier definition, activation sequence, expansion trigger points, viral mechanic assessment.
Score 70/100
Generates and edits SVG logos, icons, and graphics. Use when creating SVG files, designing logos or icons, writing path data, optimizing SVGs, building icon systems, animating SVG…
Score 70/100
Implement, review, or improve SwiftUI animations and transitions. Use when adding explicit animations with withAnimation, configuring implicit animations with .animation(_:body:)…
Score 70/100
Audit SwiftUI iOS feature code for accessibility against WCAG 2.2 Level A/AA and return patch-ready fixes.
Score 70/100
Fetch (or refresh) registered team-profile sources — git clone on first run, shallow git fetch + reset on subsequent runs — and register discovered profiles under a namespace.
Score 70/100
Synthesizes information from multiple sources into coherent insights and applies analogical reasoning to transfer knowledge across domains.
Score 70/100
Build production-ready design systems with Tailwind CSS, including design tokens, component variants, responsive patterns, and accessibility.
Score 70/100
Tailwind CSS v4.1 accessibility utilities. focus-visible, sr-only, reduced-motion, WCAG enforcement, touch targets, contrast ratios.
Score 70/100
Task management agent. Auto-invoked for task creation, status tracking, and kanban board operations using Markdown files across lane directories.
Score 70/100
Estimate software development tasks accurately using various techniques. Use when planning sprints, roadmaps, or project timelines.
Score 70/100
Execute implementation tasks from design documents using markdown checkboxes. Use when (1) implementing features from feature-design-assistant output, (2) resuming interrupted…
Score 70/100
Unified team skill for frontend development. Pure router — all roles read this file. Beat model is coordinator-only in monitor.md. Built-in ui-ux-pro-max design intelligence.
Score 70/100
Frontend debugging team using Chrome DevTools MCP. Dual-mode — feature-list testing or bug-report debugging. Triggers on "team-frontend-debug", "frontend debug".
Score 70/100
Unified team skill for UX improvement. Systematically discovers and fixes UI/UX interaction issues including unresponsive buttons, missing feedback, and state refresh problems.
Score 70/100
Unified team skill for visual accessibility QA. OKLCH color contrast, typography readability, focus management, WCAG AA/AAA audit at rendered level.
Score 70/100
Audit technical writing for learner comprehension and accessibility. Use when reviewing documentation, tutorials, or educational content for clarity.
Score 70/100
Generate Playwright E2E test plan and specification documents from project artifacts (user stories, module models, mockups, specifications).
Score 70/100
Converts research text into a Mermaid technical roadmap flowchart. Use when the user provides research proposals, experiment designs, or scientific text and asks for a roadmap or…
Score 70/100
OMX 스킬을 활용하는 Codex 다중 세션 스폰 오케스트레이터. PRD/태스크 파일을 스캔하여 각각 독립 git worktree + psmux 세션���로 Codex를 full-auto 실행한다.
Score 70/100
legacy alias. Phase 4b부터 psmux 규칙의 source of truth는 skill이 아니라 .claude/rules/tfx-psmux.md 와 AGENTS.md 의 always-on policy 이다.
Score 70/100
Telegram Mini App battle-tested solutions — safe areas, fixed positioning, BackButton, sharing. Активируй когда работаешь с TG WebApp API, safe area, fullscreen, модалями или…
Score 70/100
Evaluate physical therapy personalization and adaptive treatment systems. Analyzes exercise recommendation algorithms (rules-based, collaborative filtering, protocol-driven),…
Score 70/100
Problem redefinition before problem solving. Takes a stated problem, extracts its premises, then spawns reframers applying different lenses (problem-vs-symptom, scope-shift,…
Score 70/100
Routed by tia-openness-roadmap. C# Openness implementation of device-level operations: enumerating devices, creating and deleting devices, plugging and moving device items,…
Score 70/100
Routed by tia-openness-roadmap. C# Openness implementation of HMI engineering: HMI tags and tag tables, screens and screen items, templates, popup and slide-in screens, scripts,…
Score 70/100
Routed by tia-openness-roadmap. C# Openness implementation of import/export and round-trip engineering: XML, SimaticML, AML, CAx, choosing between file-based exchange and direct…
Score 70/100
Routed by tia-openness-roadmap. C# Openness implementation of topology and low-level network engineering: subnets, nodes, IO systems, DP master systems, ports, interfaces,…
Score 70/100
Routed by tia-openness-roadmap. C# Openness implementation of project and portal lifecycle: opening, attaching, creating, archiving, retrieving, saving, copying, closing, deleting…
Score 70/100
Routed by tia-openness-roadmap. Handles drive-specific engineering: Startdrive, SINAMICS, SIMATIC Drive Controller, PROFIdrive integrated properties, drive telegrams, and…
Score 70/100
Create TikZ diagrams in Obsidian using TikZJax plugin. Use when visualizing geometric shapes, coordinate systems, game scenes, circuit diagrams, chemical structures, or complex…
Score 70/100
Project and feature planning with 4 adaptive phases - Specify, Design, Tasks, Execute. Auto-sizes depth by complexity.
Score 70/100
tldraw is a feature-complete infinite canvas engine and whiteboard SDK for React. It provides drawing, diagramming, real-time multiplayer collaboration, and AI integrations out of…
Score 70/100
Use when sending commands to tmux panes, reading pane output, creating windows/panes, or monitoring tmux sessions.
Score 70/100
Patterns for running long-lived processes in tmux. Use when starting dev servers, watchers, tilt, or any process expected to outlive the conversation.
Score 70/100
Break a plan, spec, or PRD into independently-grabbable GitHub issues using tracer-bullet vertical slices.
Score 70/100
Turn the current conversation context into a PRD and submit it as a GitHub issue. Use when user wants to create a PRD from the current context.
Score 70/100
Mobile audit — app size, startup time, crash reporting, store compliance, accessibility, offline behavior.
Score 70/100
Scan recent conversation context and add untracked work items as CC tasks and roadmap entries.
Score 70/100
Use Task Master AI when an agent needs to turn a product request or PRD into a dependency-aware task graph, expand or scope tasks, and keep implementation work anchored to an…
Score 70/100
Use warc2text when an agent already has WARC captures and needs readable text, language identification, and exportable records for review, search, or corpus building instead of…
Score 70/100
Use Spec Kit when an agent should turn a feature idea into a spec-first workflow with explicit artifacts, planning steps, and task breakdowns before code is written.
Score 70/100
Generate PRDs, implementation plans, validation loops, issue investigations, and autonomous fix cycles inside Claude Code before coding starts.
Score 70/100
Reset per-turn skill discovery tracking so long-lived sessions don\u2019t leak outdated discovery flags while still honoring already-known skills.
Score 70/100
Block skill discovery only on the initial user message; run later discovery asynchronously while tools execute using the write-pivot guard.
Score 70/100
Wire VoiceOver, accessibility traits, UIAccessibilityReadingContent, accessibilityTextualContext, and announcement notifications into custom or wrapped Apple text editors.
Score 70/100
Audit a StyleSeed-based component or page for WCAG 2.2 AA issues and apply practical accessibility fixes where the code makes them safe.
Score 70/100
Implement WCAG 2.2 compliant interfaces with mobile accessibility, inclusive design patterns, and assistive technology support.
Score 70/100
Generate a new UI component that follows StyleSeed Toss conventions for structure, tokens, accessibility, and component ergonomics.
Score 70/100
UI 样式修改协作流程。当用户要求修改页面样式、调整布局、改 UI 细节时使用。通过"截图定位 → 现状描述 → 方案选择 → 改代码 → 微调"的结构化流程，减少沟通偏差，避免浪费 token。
Score 70/100
Anti-slop UI review — typography, color calibration, layout diversity, motion quality, interactive states. Activate when reviewing frontend components for design quality.
Score 70/100
UI design system toolkit for Senior UI Designer including design token generation, component documentation, responsive design calculations, and developer handoff tools.
Score 70/100
Création de design systems cohérents avec tokens, composants et guidelines. Se déclenche avec "design system", "composants UI", "tokens", "style guide", "atomic design", "Figma…
Score 70/100
Extract design systems from reference UI images and generate implementation-ready UI design prompts. Use when users provide UI screenshots/mockups and want to create consistent…
Score 70/100
Review UI code for StyleSeed design-system compliance, accessibility, mobile ergonomics, spacing discipline, and implementation quality.
Score 70/100
UI/UX review — accessibility, semantic HTML, z-index, animations, responsive, design tokens
Score 70/100
AI-powered adversarial UI testing via the browse CLI. Analyzes git diffs to test only what changed, or explores the full app to find bugs.
Score 70/100