monomind 2.7.9 → 2.7.11

package/packages/@monomind/cli/.claude/skills/monodesign/reference/ux-research.md

@@ -1,143 +0,0 @@
-# UX Research
-
-Validate design decisions with evidence. Research before redesigning; test before shipping.
-
-## When to Research
-
-| Signal | Method |
-|---|---|
-| "We don't know if users want this" | User interviews (5–8 participants) |
-| "We don't know if users can do this" | Usability testing (5 tasks, think-aloud) |
-| "We don't know which version is better" | A/B testing (statistical significance required) |
-| "We don't know who our users are" | Survey + analytics segmentation |
-| "We're redesigning a live product" | Contextual inquiry + session recording analysis |
-
-## Study Plan
-
-Before any research session:
-
-```markdown
-## Research Plan: [Feature/Product Name]
-
-**Research question**: [One clear question this study answers]
-**Method**: [Interview / Usability test / Survey / A/B test]
-**Participants**: [N=X; criteria: role, experience, age range; how recruited]
-**Timeline**: [Dates for recruiting, sessions, synthesis, readout]
-**Success**: [What finding would change a product decision]
-
-### Session protocol
-- [Task 1]: [Goal — what we want to observe, not prescribe]
-- [Task 2]: ...
-- Post-task questions: "How difficult was that? Why?"
-- Closing: "What surprised you? What would you change?"
-```
-
-## User Persona Template
-
-Personas are empirical — built from interview synthesis, not imagination. A persona without a source citation is a fiction.
-
-```markdown
-## [Persona Name] — [One-line description]
-
-**Source**: [N interviews + X survey responses, Month Year]
-
-### Context
-- Role: [job title, team size, seniority]
-- Environment: [device, OS, when/where they use the product]
-- Technical fluency: [1–5 scale with evidence]
-
-### Goals
-Primary: [What they're actually trying to accomplish]
-Secondary: [Nice-to-have outcomes]
-
-### Frustrations (direct quotes where possible)
-- "[Their words]" — quote from interview participant
-- [Observed behavior that contradicts stated preference]
-
-### Mental model
-[How they currently think about the problem domain — diagram if useful]
-
-### Decision triggers
-[What causes them to start using, stop using, recommend, or abandon]
-```
-
-## Usability Test Protocol
-
-5 participants reveals 85% of usability issues (Nielsen's rule). Run moderated think-aloud tests before major launches.
-
-```markdown
-## Usability Test: [Feature Name]
-
-**Prototype/build**: [URL or Figma link]
-**Tasks** (state goal, not steps):
-1. "Find a plan that fits your budget" ← correct
-   "Click Pricing, then select Pro" ← wrong (leads the user)
-2. ...
-
-**Observation sheet** (one per participant):
-| Task | Completed? | Time | Errors | Quotes / Observations |
-|------|-----------|------|--------|----------------------|
-| T1   |           |      |        |                      |
-
-**Severity scale**:
-- P0: Blocks task completion — fix before launch
-- P1: Causes errors or frustration — fix this sprint
-- P2: Causes hesitation — fix next sprint
-- P3: Polish issue — backlog
-```
-
-## Synthesis
-
-After 5+ sessions, synthesize before drawing conclusions. Affinity mapping is the default method.
-
-Steps:
-1. Transcribe or note-take immediately after each session
-2. Write observations on individual cards ("User tried X before Y")
-3. Group cards by theme across participants
-4. Count frequency: "4/5 users misread the CTA as navigation"
-5. Map to product decisions: what changes, what validates current design
-
-**Red flags that invalidate a finding:**
-- Only one participant showed this behavior
-- Observation conflicts with analytics data — investigate before concluding
-- "Users said they would do X" (stated preference ≠ behavior)
-
-## A/B Testing Standards
-
-Don't A/B test unless:
-- You have enough traffic for statistical significance (use a calculator — typically n=1,000+ per variant)
-- The test runs ≥2 weeks to account for weekly cycles
-- You have a pre-registered hypothesis ("Changing CTA copy will increase conversion by 10%")
-- You have a single primary metric per test
-
-**What to test**: CTAs, headlines, onboarding steps, form field count, pricing page layout.  
-**What not to test**: Navigation structure, brand identity, accessibility requirements.
-
-## Research Repository
-
-After each study, file a one-page summary:
-
-```markdown
-## Research Summary: [Study Name] — [Date]
-
-**Question**: [What we set out to learn]
-**Method + participants**: [Brief]
-**Top 3 findings**:
-1. [Finding with evidence — quote or count]
-2. ...
-3. ...
-**Recommended changes** (linked to findings):
-- Design: [What to change]
-- Product: [What to consider]
-**Follow-up questions this surfaced**: [What to research next]
-```
-
-Store in `docs/research/` or equivalent. Link from design decisions so future teammates understand why choices were made.
-
-## Inclusive Research
-
-- Recruit participants with disabilities in every study (not just accessibility-specific studies)
-- Test on real devices users own — not just latest iPhone/MacBook
-- Account for non-native language users if the product has international reach
-- Analyze session recordings for accessibility errors: keyboard traps, screen reader failures, zoom breakage
-- Don't use "average user" — disaggregate findings by user segment

package/packages/@monomind/cli/.claude/skills/monodesign/reference/ux-rules.md

@@ -1,211 +0,0 @@
-# UX Rules — Implementation-Level Guidance
-
-170+ rules across 10 categories, ordered by priority. Use during `audit`, `critique`, and `review` workflows to catch implementation-level issues that antipattern detection misses.
-
----
-
-## Priority 1: Accessibility (CRITICAL)
-
-| ID | Rule | Check |
-|----|------|-------|
-| `color-contrast` | Minimum 4.5:1 for normal text; 3:1 for large text (18px+ or 14px+ bold) | WCAG AA |
-| `focus-states` | Visible focus rings on all interactive elements (2–4px outline) | Never remove outlines |
-| `alt-text` | Descriptive alt text for all meaningful images; `alt=""` for decorative | |
-| `aria-labels` | aria-label for icon-only buttons; all interactive elements labeled | |
-| `keyboard-nav` | Tab order matches visual order; all actions reachable without a mouse | |
-| `form-labels` | `<label for="">` wired to every input; no placeholder-as-label | |
-| `skip-links` | "Skip to main content" link for keyboard users | |
-| `heading-hierarchy` | Sequential h1→h2→h3, no level skips | |
-| `color-not-only` | Never convey information by color alone — add icon or text | |
-| `dynamic-type` | Support system text scaling; no truncation as text grows | |
-| `reduced-motion` | `@media (prefers-reduced-motion: reduce)` wraps all animations | Non-negotiable |
-| `escape-routes` | Cancel/back affordance in all modals and multi-step flows | |
-| `keyboard-shortcuts` | Preserve system accessibility shortcuts | |
-
----
-
-## Priority 2: Touch & Interaction (CRITICAL)
-
-| ID | Rule | Check |
-|----|------|-------|
-| `touch-target-size` | Min 44×44pt interactive area; expand hit area beyond visual bounds if needed | |
-| `touch-spacing` | Minimum 8px gap between adjacent touch targets | |
-| `hover-vs-tap` | Primary interactions are click/tap; hover is enhancement only | |
-| `loading-buttons` | Disable button during async operations; show spinner or progress | |
-| `error-feedback` | Clear error messages near the problem element | |
-| `cursor-pointer` | `cursor: pointer` on all clickable elements | Web |
-| `tap-delay` | `touch-action: manipulation` to remove 300ms delay | Web |
-| `press-feedback` | Visual feedback on press (opacity, scale, ripple) within 80–150ms | |
-| `drag-threshold` | Movement threshold before starting drag to avoid accidental drags | |
-
----
-
-## Priority 3: Performance (HIGH)
-
-| ID | Rule | Check |
-|----|------|-------|
-| `image-optimization` | WebP/AVIF, responsive `srcset`/`sizes`, lazy load non-critical | |
-| `image-dimension` | Declare `width`/`height` or `aspect-ratio` to prevent CLS | Core Web Vitals |
-| `font-loading` | `font-display: swap` or `optional`; preload critical fonts only | |
-| `critical-css` | Above-the-fold CSS loads first (inline critical or early stylesheet) | |
-| `bundle-splitting` | Split code by route/feature (React Suspense, dynamic import) | |
-| `reduce-reflows` | Batch DOM reads then writes; no layout thrashing | |
-| `content-jumping` | Reserve space for async content (skeleton screens, aspect-ratio boxes) | |
-| `virtualize-lists` | Virtualize lists of 50+ items | |
-| `debounce-throttle` | Debounce/throttle for scroll, resize, and input events | |
-| `progressive-loading` | Skeleton/shimmer for operations >1s; never a blocking spinner | |
-
----
-
-## Priority 4: Style Selection (HIGH)
-
-| ID | Rule | Check |
-|----|------|-------|
-| `consistency` | One visual style across all pages; no mid-product style drift | |
-| `no-emoji-icons` | SVG icons only (Heroicons, Lucide, Phosphor); never emojis as icons | |
-| `effects-match-style` | Shadows, blur, radius aligned with chosen style | |
-| `state-clarity` | Hover/pressed/disabled states are visually distinct | |
-| `elevation-consistent` | Consistent shadow scale for cards, sheets, modals | |
-| `icon-style-consistent` | One icon set; consistent stroke weight and corner radius | |
-| `primary-action` | One primary CTA per screen; secondary actions visually subordinate | |
-| `blur-purpose` | Blur indicates background dismissal (modals, sheets); never decorative | |
-
----
-
-## Priority 5: Layout & Responsive (HIGH)
-
-| ID | Rule | Check |
-|----|------|-------|
-| `viewport-meta` | `width=device-width, initial-scale=1`; never disable zoom | |
-| `mobile-first` | Design mobile-first; scale up to tablet and desktop | |
-| `breakpoint-consistency` | Systematic breakpoints: 375 / 768 / 1024 / 1440 | |
-| `readable-font-size` | Min 16px body on mobile (avoids iOS auto-zoom) | |
-| `line-length-control` | Mobile 35–60 chars; desktop 60–75 chars | |
-| `horizontal-scroll` | No horizontal scroll on mobile | |
-| `spacing-scale` | 4pt/8dp incremental spacing system | |
-| `container-width` | Consistent max-width on desktop (max-w-6xl / 7xl) | |
-| `z-index-management` | Defined layered z-index scale (0 / 10 / 20 / 40 / 100 / 1000) | |
-| `fixed-element-offset` | Fixed navbar/bottom bar reserves safe padding for underlying content | |
-| `viewport-units` | Prefer `min-h-dvh` over `100vh` | |
-| `visual-hierarchy` | Hierarchy via size, spacing, contrast — not color alone | |
-
----
-
-## Priority 6: Typography & Color (MEDIUM)
-
-| ID | Rule | Check |
-|----|------|-------|
-| `line-height` | `1.5`–`1.75` for body text (`1.6` is the Editorial Sanctuary target) | |
-| `line-length` | `max-width: 65ch` on paragraph containers | |
-| `font-pairing` | Heading and body fonts have distinct personalities | |
-| `font-scale` | Consistent type scale (12 / 14 / 16 / 18 / 24 / 32) | |
-| `weight-hierarchy` | Bold headings (600–700), regular body (400), medium labels (500) | |
-| `color-semantic` | Semantic color tokens (primary, secondary, error, surface); no raw hex in components | |
-| `color-dark-mode` | Dark mode uses desaturated/lighter tonal variants; test contrast independently | |
-| `color-accessible-pairs` | All foreground/background pairs meet 4.5:1 (AA) or 7:1 (AAA) | |
-| `color-not-decorative-only` | Functional colors (error, success) also use icon or text — no color-only meaning | |
-| `letter-spacing` | Avoid tight tracking on body text; track only micro-labels, buttons, uppercase | |
-| `number-tabular` | Tabular/monospaced figures for data columns, prices, timers | |
-
----
-
-## Priority 7: Animation (MEDIUM)
-
-| ID | Rule | Check |
-|----|------|-------|
-| `duration-timing` | 150–300ms for micro-interactions; complex transitions ≤400ms | |
-| `transform-performance` | Animate `transform` and `opacity` only; never width/height/top/left | |
-| `easing` | `ease-out` for entering; `ease-in` for exiting; never linear for UI | |
-| `motion-meaning` | Every animation expresses cause-effect; no purely decorative motion | |
-| `spring-physics` | Prefer spring/physics curves over cubic-bezier for natural feel | |
-| `exit-faster` | Exit animations 60–70% of enter duration — feels responsive | |
-| `stagger-sequence` | Stagger list/grid entrances 30–50ms per item | |
-| `interruptible` | Animations are interruptible; user action cancels in-progress animation | |
-| `no-blocking-animation` | UI stays interactive during animations; never block input | |
-| `scale-feedback` | Subtle scale (0.95–1.05) on press for tappable cards/buttons | |
-| `layout-shift-avoid` | Animations must not trigger reflow or CLS | |
-| `loading-states` | Skeleton or progress indicator when loading exceeds 300ms | |
-| `excessive-motion` | Animate 1–2 key elements per view max | |
-
----
-
-## Priority 8: Forms & Feedback (MEDIUM)
-
-| ID | Rule | Check |
-|----|------|-------|
-| `input-labels` | Visible label per input — no placeholder-as-label | |
-| `error-placement` | Error message below the related field | |
-| `submit-feedback` | Loading → then success/error state on submit | |
-| `required-indicators` | Required fields marked (asterisk + sr-only explanation) | |
-| `empty-states` | Helpful message and action when no content | |
-| `toast-dismiss` | Auto-dismiss toasts in 3–5s | |
-| `confirmation-dialogs` | Confirm before all destructive actions | |
-| `disabled-states` | Disabled: reduced opacity (0.38–0.5) + cursor change + semantic attribute | |
-| `progressive-disclosure` | Reveal complex options progressively; don't overwhelm upfront | |
-| `inline-validation` | Validate on blur, not on keystroke; show error only after user finishes | |
-| `password-toggle` | Show/hide toggle for password fields | |
-| `error-clarity` | Error messages state cause + how to fix (not just "Invalid input") | |
-| `focus-management` | After submit error, auto-focus the first invalid field | |
-| `error-summary` | Multiple errors get a summary at top with anchor links to each field | |
-| `toast-accessibility` | Toasts use `aria-live="polite"` — never steal focus | |
-| `undo-support` | Allow undo for destructive or bulk actions | |
-| `multi-step-progress` | Multi-step flows show step indicator; allow back navigation | |
-| `timeout-feedback` | Request timeout shows clear feedback with retry option | |
-
----
-
-## Priority 9: Navigation Patterns (HIGH)
-
-| ID | Rule | Check |
-|----|------|-------|
-| `back-behavior` | Back navigation is predictable and consistent; preserves scroll/state | |
-| `deep-linking` | All key screens reachable via URL for sharing | |
-| `nav-label-icon` | Navigation items have both icon and text label | |
-| `nav-state-active` | Current location visually highlighted (color, weight, or indicator) | |
-| `nav-hierarchy` | Primary nav vs secondary nav are clearly separated | |
-| `modal-escape` | Modals/dialogs have a clear close affordance | |
-| `search-accessible` | Search easily reachable from top bar or primary nav | |
-| `breadcrumb-web` | Breadcrumbs for 3+ level deep hierarchies | Web |
-| `state-preservation` | Back restores previous scroll position, filter state, and input | |
-| `overflow-menu` | When actions exceed space, use overflow/more menu instead of cramming | |
-| `navigation-consistency` | Navigation placement same across all pages | |
-| `modal-vs-navigation` | Modals are not used for primary navigation flows | |
-| `focus-on-route-change` | After page transition, move focus to main content for screen readers | |
-| `destructive-nav-separation` | Dangerous actions (delete, logout) spatially separated from normal nav | |
-
----
-
-## Priority 10: Charts & Data (LOW)
-
-| ID | Rule | Check |
-|----|------|-------|
-| `chart-type` | Match chart to data: trend → line, comparison → bar, proportion → pie/donut | |
-| `color-guidance` | Accessible color palettes; no red/green-only pairs (colorblind) | |
-| `data-table` | Table alternative for screen readers; charts alone are not accessible | |
-| `legend-visible` | Always show legend; position near the chart | |
-| `tooltip-on-interact` | Tooltips on hover/focus showing exact values | |
-| `axis-labels` | Label axes with units; avoid truncated labels | |
-| `responsive-chart` | Charts reflow or simplify on small screens | |
-| `empty-data-state` | Meaningful empty state when no data | |
-| `no-pie-overuse` | No pie/donut for >5 categories; use bar chart | |
-| `gridline-subtle` | Grid lines are low-contrast (e.g. gray-200); don't compete with data | |
-| `focusable-elements` | Interactive chart elements are keyboard-navigable | |
-| `screen-reader-summary` | Text summary or aria-label describing chart's key insight | |
-| `tooltip-keyboard` | Tooltip content keyboard-reachable; not hover-only | |
-| `sortable-table` | Data tables support sorting with `aria-sort` | |
-| `animation-optional` | Chart entrance animations respect `prefers-reduced-motion` | |
-
----
-
-## Quick Decision: When to use this reference
-
-| You're doing | Jump to |
-|---|---|
-| Accessibility review | Priority 1 |
-| Mobile/touch audit | Priority 2 |
-| Performance audit | Priority 3 |
-| Animation review | Priority 7 |
-| Form UX | Priority 8 |
-| Navigation review | Priority 9 |
-| Data visualization | Priority 10 |
-| Full pre-ship review | Use `pre-delivery-checklist.md` |

package/packages/@monomind/cli/.claude/skills/monodesign/reference/ux-writing.md

@@ -1,107 +0,0 @@
-# UX Writing
-
-## The Button Label Problem
-
-**Never use "OK", "Submit", or "Yes/No".** These are lazy and ambiguous. Use specific verb + object patterns:
-
-| Bad | Good | Why |
-|-----|------|-----|
-| OK | Save changes | Says what will happen |
-| Submit | Create account | Outcome-focused |
-| Yes | Delete message | Confirms the action |
-| Cancel | Keep editing | Clarifies what "cancel" means |
-| Click here | Download PDF | Describes the destination |
-
-**For destructive actions**, name the destruction:
-- "Delete" not "Remove" (delete is permanent, remove implies recoverable)
-- "Delete 5 items" not "Delete selected" (show the count)
-
-## Error Messages: The Formula
-
-Every error message should answer: (1) What happened? (2) Why? (3) How to fix it? Example: "Email address isn't valid. Please include an @ symbol." not "Invalid input".
-
-### Error Message Templates
-
-| Situation | Template |
-|-----------|----------|
-| **Format error** | "[Field] needs to be [format]. Example: [example]" |
-| **Missing required** | "Please enter [what's missing]" |
-| **Permission denied** | "You don't have access to [thing]. [What to do instead]" |
-| **Network error** | "We couldn't reach [thing]. Check your connection and [action]." |
-| **Server error** | "Something went wrong on our end. We're looking into it. [Alternative action]" |
-
-### Don't Blame the User
-
-Reframe errors: "Please enter a date in MM/DD/YYYY format" not "You entered an invalid date".
-
-## Empty States Are Opportunities
-
-Empty states are onboarding moments: (1) Acknowledge briefly, (2) Explain the value of filling it, (3) Provide a clear action. "No projects yet. Create your first one to get started." not just "No items".
-
-## Voice vs Tone
-
-**Voice** is your brand's personality, consistent everywhere.
-**Tone** adapts to the moment.
-
-| Moment | Tone Shift |
-|--------|------------|
-| Success | Celebratory, brief: "Done! Your changes are live." |
-| Error | Empathetic, helpful: "That didn't work. Here's what to try..." |
-| Loading | Reassuring: "Saving your work..." |
-| Destructive confirm | Serious, clear: "Delete this project? This can't be undone." |
-
-**Never use humor for errors.** Users are already frustrated. Be helpful, not cute.
-
-## Writing for Accessibility
-
-**Link text** must have standalone meaning: "View pricing plans" not "Click here". **Alt text** describes information, not the image: "Revenue increased 40% in Q4" not "Chart". Use `alt=""` for decorative images. **Icon buttons** need `aria-label` for screen reader context.
-
-## Writing for Translation
-
-### Plan for Expansion
-
-German text is ~30% longer than English. Allocate space:
-
-| Language | Expansion |
-|----------|-----------|
-| German | +30% |
-| French | +20% |
-| Finnish | +30-40% |
-| Chinese | -30% (fewer chars, but same width) |
-
-### Translation-Friendly Patterns
-
-Keep numbers separate ("New messages: 3" not "You have 3 new messages"). Use full sentences as single strings (word order varies by language). Avoid abbreviations ("5 minutes ago" not "5 mins ago"). Give translators context about where strings appear.
-
-## Consistency: The Terminology Problem
-
-Pick one term and stick with it:
-
-| Inconsistent | Consistent |
-|--------------|------------|
-| Delete / Remove / Trash | Delete |
-| Settings / Preferences / Options | Settings |
-| Sign in / Log in / Enter | Sign in |
-| Create / Add / New | Create |
-
-Build a terminology glossary and enforce it. Variety creates confusion.
-
-## Avoid Redundant Copy
-
-If the heading explains it, the intro is redundant. If the button is clear, don't explain it again. Say it once, say it well.
-
-## Loading States
-
-Be specific: "Saving your draft..." not "Loading...". For long waits, set expectations ("This usually takes 30 seconds") or show progress.
-
-## Confirmation Dialogs: Use Sparingly
-
-Most confirmation dialogs are design failures; consider undo instead. When you must confirm: name the action, explain consequences, use specific button labels ("Delete project" / "Keep project", not "Yes" / "No").
-
-## Form Instructions
-
-Show format with placeholders, not instructions. For non-obvious fields, explain why you're asking.
-
----
-
-**Avoid**: Jargon without explanation. Blaming users ("You made an error" → "This field is required"). Vague errors ("Something went wrong"). Varying terminology for variety. Humor for errors.

package/packages/@monomind/cli/.claude/skills/monodesign/scripts/command-metadata.json

@@ -1,94 +0,0 @@
-{
-  "craft": {
-    "description": "Full confirmed-brief-then-build flow. Runs multi-round shape discovery first, resolves visual probe and north-star mock gates when available, then builds and visually iterates. Use when building a new feature end-to-end.",
-    "argumentHint": "[feature description]"
-  },
-  "init": {
-    "description": "Sets up a project for monodesign. Runs a multi-round discovery interview when context is missing and writes PRODUCT.md (strategic: users, brand, principles); offers DESIGN.md (visual: colors, typography, components) when code exists; pre-configures live mode; then recommends the best commands to run next. Every other command reads these files before doing work. Use once per project.",
-    "argumentHint": ""
-  },
-  "document": {
-    "description": "Generate a DESIGN.md file that captures the current visual design system. Auto-extracts colors, typography, spacing, radii, and component patterns from the codebase, then asks the user to confirm descriptive language for atmosphere and color character. Follows the Google Stitch DESIGN.md format so the file is tool-compatible. Use when you need a visual design spec an AI agent can follow to stay on-brand.",
-    "argumentHint": ""
-  },
-  "extract": {
-    "description": "Pull reusable patterns, components, and design tokens into the design system. Identifies repeated patterns and consolidates them. Use when you have drift across the codebase and want to bring things back to a consistent system.",
-    "argumentHint": "[target]"
-  },
-  "live": {
-    "description": "Interactive live variant mode. Select elements in the browser, pick a design action, and get AI-generated HTML+CSS variants hot-swapped via HMR. Requires a running dev server. Use when you want to visually experiment with design alternatives in real time.",
-    "argumentHint": ""
-  },
-  "adapt": {
-    "description": "Adapt designs to work across different screen sizes, devices, contexts, or platforms. Implements breakpoints, fluid layouts, and touch targets. Use when the user mentions responsive design, mobile layouts, breakpoints, viewport adaptation, or cross-device compatibility.",
-    "argumentHint": "[target] [context (mobile, tablet, print...)]"
-  },
-  "animate": {
-    "description": "Review a feature and enhance it with purposeful animations, micro-interactions, and motion effects that improve usability and delight. Use when the user mentions adding animation, transitions, micro-interactions, motion design, hover effects, or making the UI feel more alive.",
-    "argumentHint": "[target]"
-  },
-  "audit": {
-    "description": "Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.",
-    "argumentHint": "[area (feature, page, component...)]"
-  },
-  "bolder": {
-    "description": "Amplify safe or boring designs to make them more visually interesting and stimulating. Increases impact while maintaining usability. Use when the user says the design looks bland, generic, too safe, lacks personality, or wants more visual impact and character.",
-    "argumentHint": "[target]"
-  },
-  "clarify": {
-    "description": "Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand. Use when the user mentions confusing text, unclear labels, bad error messages, hard-to-follow instructions, or wanting better UX writing.",
-    "argumentHint": "[target]"
-  },
-  "colorize": {
-    "description": "Add strategic color to features that are too monochromatic or lack visual interest, making interfaces more engaging and expressive. Use when the user mentions the design looking gray, dull, lacking warmth, needing more color, or wanting a more vibrant or expressive palette.",
-    "argumentHint": "[target]"
-  },
-  "critique": {
-    "description": "Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, automated anti-pattern detection, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.",
-    "argumentHint": "[area (feature, page, component...)]"
-  },
-  "delight": {
-    "description": "Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful. Use when the user asks to add polish, personality, animations, micro-interactions, delight, or make an interface feel fun or memorable.",
-    "argumentHint": "[target]"
-  },
-  "distill": {
-    "description": "Strip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean. Use when the user asks to simplify, declutter, reduce noise, remove elements, or make a UI cleaner and more focused.",
-    "argumentHint": "[target]"
-  },
-  "harden": {
-    "description": "Make interfaces production-ready: error handling, i18n, text overflow, edge case management, and resilience under real-world data. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.",
-    "argumentHint": "[target]"
-  },
-  "onboard": {
-    "description": "Design onboarding flows, first-run experiences, and empty states that guide new users to value. Covers welcome screens, account setup, progressive disclosure, contextual tooltips, feature announcements, and activation moments. Use when the user mentions onboarding, first-time users, empty states, activation, getting started, new user flows, or the aha moment.",
-    "argumentHint": "[target]"
-  },
-  "layout": {
-    "description": "Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.",
-    "argumentHint": "[target]"
-  },
-  "optimize": {
-    "description": "Diagnoses and fixes UI performance across loading speed, rendering, animations, images, and bundle size. Use when the user mentions slow, laggy, janky, performance, bundle size, load time, or wants a faster, smoother experience.",
-    "argumentHint": "[target]"
-  },
-  "overdrive": {
-    "description": "Pushes interfaces past conventional limits with technically ambitious implementations — shaders, spring physics, scroll-driven reveals, 60fps animations. Use when the user wants to wow, impress, go all-out, or make something that feels extraordinary.",
-    "argumentHint": "[target]"
-  },
-  "polish": {
-    "description": "Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.",
-    "argumentHint": "[target]"
-  },
-  "quieter": {
-    "description": "Tones down visually aggressive or overstimulating designs, reducing intensity while preserving quality. Use when the user mentions too bold, too loud, overwhelming, aggressive, garish, or wants a calmer, more refined aesthetic.",
-    "argumentHint": "[target]"
-  },
-  "shape": {
-    "description": "Plan UX and UI before code. Runs a required multi-round discovery interview, uses visual probes when available, and produces a user-confirmed design brief for implementation.",
-    "argumentHint": "[feature to shape]"
-  },
-  "typeset": {
-    "description": "Improves typography by fixing font choices, hierarchy, sizing, weight, and readability so text feels intentional. Use when the user mentions fonts, type, readability, text hierarchy, sizing looks off, or wants more polished, intentional typography.",
-    "argumentHint": "[target]"
-  }
-}