菜单
Use when starting any UX/UI design task — visual design, IA, interaction, accessibility (WCAG 2.2), user research across mobile, web, desktop, game, and AI surfaces, plus first-principles audience-derived needs analysis. Routes to 11 specialist sheets.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when working on a Python task and unsure which specialist to load - routes to type-system, mypy-resolution, project-tooling, delinting, testing, async, scientific-computing, ML-workflows, debugging-and-profiling, or Textual-TUI specialists based on symptoms
Use when a Claude is taking **standing ownership** of a software product across many sessions — discovery, strategy, specs, and value validation — deciding *what to build, why, for whom,* and *whether it worked*, with continuity, decision provenance, and an authority boundary that escalates irreversible or outward-facing actions to the human owner. Owns the product disciplines: opportunity assessment (JTBD, problem validation, business case), vision/strategy/positioning and intent-roadmapping, PRDs with falsifiable acceptance criteria, delivery orchestration and acceptance, product-value metrics and experimentation, and the product anti-pattern catalog. Orchestrates rather than reimplements: routes sequencing/flow/WSJF to `/axiom-program-management`, plans to `/axiom-planning`, solution/architecture to `/axiom-solution-architect`, research method to `/lyra-ux-designer`. Do **not** load to build one feature, choose an architecture, or manage delivery flow for already-decided work.
This skill should be used when the user asks to "track work", "create an issue", "find something to work on", "what should I work on next", "triage bugs", "close an issue", "check what's blocked", "plan a milestone", "review sprint progress", "coordinate agents", or when working in a project that uses filigree for issue tracking. Provides workflow patterns, team coordination protocols, and operational guidance for the filigree issue tracker.
Use when designing a system that spans more than one process, machine, or failure domain and a partition, crash, or duplicate must not silently corrupt state. Use when you see split-brain, lost writes under partition, duplicate processing, stuck or half-applied sagas, retry storms, dual writes drifting apart, or "works in staging, melts under load." Architecture-level — how to design correctness under partial failure, not how to deploy it. Single-service API internals → `axiom-web-backend`; CI/CD and ops → `axiom-devops-engineering`; replay/seed determinism → `axiom-determinism-and-replay`; broker/event-sourcing mechanics → the event-driven pack.
Use when designing a system whose past behaviour must be recoverable as a fact — RL training substrates, multi-agent simulations, deterministic game engines, replay-debuggable services, multiplayer lockstep, or any pipeline where "I cannot reproduce that bug" is unacceptable. Use when teams disagree about what "snapshot", "seed", or "replay" mean across modules. Use when cross-machine or cross-process determinism is required, or a regulator will ask "what was the input at tick T?". Architecture-level — how to design a deterministic system. For verifying an existing simulation against known patterns, use `/check-determinism` from yzmir-simulation-foundations instead.
Use when building or fixing the path from commit to running production — CI/CD pipelines and verification gates, zero-downtime deployment, infrastructure as code, container build hygiene, Kubernetes/orchestration runtime, observability (metrics/logs/traces, SLI/SLO), incident response and on-call, release management and rollback, secrets and configuration, environment parity and promotion, DevSecOps and software supply-chain security, GitOps/declarative delivery, and SRE/reliability — routes to 13 specialist reference sheets instead of giving surface-level generic ops advice.
| name | using-ux-designer |
| description | Use when starting any UX/UI design task — visual design, IA, interaction, accessibility (WCAG 2.2), user research across mobile, web, desktop, game, and AI surfaces, plus first-principles audience-derived needs analysis. Routes to 11 specialist sheets. |
This meta-skill routes you to the right UX design skills based on your situation. Load this skill when you need UX expertise but aren't sure which specific skill to use.
Core Principle: Different UX tasks require different skills. Match your situation to the appropriate skill, load only what you need.
Load this skill when:
Don't use for: Backend logic, database design, pure technical implementation without UX implications. For static documentation or marketing sites (developer-tool docs, landing pages, OSS project sites), route to the sibling lyra-site-designer pack instead — this pack is for application UI (interactive web apps, mobile, desktop, game, AI surfaces).
IMPORTANT: All reference sheets are located in the SAME DIRECTORY as this SKILL.md file.
When this skill is loaded from:
skills/using-ux-designer/SKILL.md
Reference sheets like ux-fundamentals.md are at:
skills/using-ux-designer/ux-fundamentals.md
NOT at:
skills/ux-fundamentals.md ← WRONG PATH
When you see a link like [ux-fundamentals.md](ux-fundamentals.md), read the file from the same directory as this SKILL.md.
Symptoms: "What is...", "Explain...", "Teach me about...", "How does X work in UX?"
Route to: ux-fundamentals.md
Examples:
Symptoms: "Review this design", "Critique this interface", "Is this usable?", "Does this follow best practices?"
Route to: Relevant competency skills based on critique focus
General Review (no specific focus):
Specific Focus:
Add platform extension if design is platform-specific:
Symptoms: "Design a...", "Create interface for...", "Build a [feature] screen"
Route to: Competency skills + platform extension
Standard Web/Mobile Feature:
Complex Navigation/IA:
Research Phase (early discovery):
Symptoms: "Chatbot UX", "AI assistant", "copilot", "agent", "RAG UI", "streaming output", "model output is wrong / overconfident", "citations", "tool-call confirmation"
Route to: ai-experience-patterns.md
Add:
aria-live streaming + WCAG 2.2 SC 3.3.8 (don't gate AI behind cognitive auth tests)Examples:
Symptoms: "Colors don't work", "Typography feels off", "Hierarchy unclear", "Layout cramped"
Route to: visual-design-foundations.md
Add: accessibility-and-inclusive-design.md if contrast/readability concerns
Symptoms: "Users can't find features", "Navigation confusing", "Menu structure", "Content organization"
Route to: information-architecture.md
Add: Platform extension for platform-specific nav patterns
Symptoms: "Button states unclear", "No loading feedback", "Micro-interactions", "Touch targets too small"
Route to: interaction-design-patterns.md
Add: Platform extension for platform-specific interaction conventions
Symptoms: "WCAG compliance", "Accessibility audit", "Colorblind-safe", "Keyboard navigation", "Screen reader"
Route to: accessibility-and-inclusive-design.md
Note: This skill should be referenced by all other design decisions (accessibility is universal)
Symptoms: "Understand users", "User interviews", "Usability testing", "Mental models", "Journey mapping"
Route to: user-research-and-validation.md
Add: Other skills once research informs design direction
Symptoms: "Mobile app", "iOS", "Android", "Touch interface", "Phone", "Tablet"
Route to:
Mobile-Specific Concerns:
Symptoms: "Web app", "Dashboard", "SaaS", "Data visualization", "Admin panel", "Responsive design"
Route to:
Web-Specific Concerns:
Symptoms: "Desktop app", "Electron", "Native application", "Multi-window", "Keyboard shortcuts"
Route to:
Desktop-Specific Concerns:
Symptoms: "Game", "HUD", "Menu system", "Game interface", "In-game UI", "Player experience"
Route to:
Game-Specific Concerns:
Load in order:
Load in order:
Load in order:
When designing documentation UX:
/technical-writer (content structure, microcopy, UI text)Example: "Design documentation site navigation" → Load IA here; route the writing-side structure to /technical-writer. If the surface is a static docs site, hand off to /site-designer (next section).
When the surface is a static documentation site or marketing page (not an interactive application):
lyra-site-designer — owns information architecture, HTML/CSS, design tokens, and developer-UX patterns for docs-first frameworks (Starlight / VitePress / Docusaurus).This pack stays in scope for: SaaS dashboards, web applications, mobile apps, desktop tools, game UI, AI / chat / agent surfaces.
When designing secure interfaces:
/security-architect (threat modelling for authentication UX)Example: "Design login with MFA" → Load interaction-design-patterns.md + route threat modelling to /security-architect
User Request
|
├─ "What is...?" / "Explain..." → ux-fundamentals
|
├─ "Review this design"
| ├─ General → visual-design + IA + accessibility
| └─ Specific concern → Relevant competency skill
| └─ Add platform extension if platform-specific
|
├─ "Design a [feature]"
| ├─ Research phase? → user-research-and-validation first
| └─ Design phase
| ├─ Identify competencies needed (visual, IA, interaction)
| ├─ Detect platform (mobile, web, desktop, game)
| └─ Load competency + platform extension
|
└─ Specific domain
├─ Visual → visual-design-foundations
├─ Navigation → information-architecture
├─ Interaction → interaction-design-patterns
├─ Accessibility → accessibility-and-inclusive-design
├─ AI / chatbot / agent / RAG / streaming → ai-experience-patterns
└─ Research → user-research-and-validation
Load: ux-fundamentals.md (teaches principles)
Load: visual-design + IA + accessibility + [platform-extension]
Load: Relevant competencies + [platform-extension]
Load: accessibility-and-inclusive-design.md (primary) Reference: visual-design (contrast), interaction-design (keyboard nav)
Load: information-architecture.md (primary) Add: user-research-and-validation (if testing/validation needed)
Focused expertise: Load only what's needed for the task Clear boundaries: Each skill has distinct responsibility Composable: Combine skills for complex scenarios Efficient: Avoid loading all 11 specialist sheets at once Explicit: User sees which skills are active
After routing, load the appropriate specialist skill for detailed guidance:
This pack ships three slash commands that wrap common workflows over the sheets above:
/lyra-ux-designer:design-review - multi-competency critique across visual, IA, interaction, and accessibility; add ai-experience-patterns when the surface is a chat / agent / AI interface/lyra-ux-designer:create-interface - design a new component with platform-aware patterns and accessibility built in; add ai-experience-patterns when the component is an AI surface/lyra-ux-designer:accessibility-audit - full WCAG 2.2 AA audit using the 6-dimension Universal Access Model, including the new 2.2 success criteria (2.4.11, 2.5.7, 2.5.8, 3.2.6, 3.3.7, 3.3.8)Three SME agents are available for delegated review work; all follow the SME Agent Protocol with Confidence / Risk / Information Gaps / Caveats sections:
ux-critic - multi-competency design review against best practice (visual + IA + interaction + accessibility); the default criticaccessibility-auditor - WCAG 2.2 AA compliance specialist applying the Universal Access Model; produces remediation-prioritised findingsux-theorist - first-principles needs derivation; invoke BEFORE design review when prior reviews keep waving inherited decisions through (premise relitigation)Cross-faction:
/technical-writer - Documentation UX and microcopy/security-architect - Security-aware interface design