@zeyue0329/xiaoma-cli 1.13.0 → 1.15.1

package/src/xmc-skills/2-plan-workflows/xiaoma-ux/assets/experience-example-shadcn.md

@@ -0,0 +1,133 @@
+---
+name: Drift
+status: final
+sources:
+  - {planning_artifacts}/prds/drift-2026-03-12/prd.md
+updated: 2026-04-02
+---
+
+# Drift — Experience Spine
+
+> Illustrative example. Single-surface responsive web. shadcn/ui on Next.js + Tailwind. Paired with `design-example-shadcn.md` (Drift DESIGN.md). Demonstrates: component-library inheritance, keyboard-first interaction primitives, the "shadcn + brand-layer" pattern that covers most modern web SaaS.
+
+## Foundation
+
+Single-surface responsive web. shadcn/ui on Next.js 15+ with Tailwind CSS. The component library does most of the work; brand discipline is "respect the defaults except where the brand layer overrides them." `DESIGN.md` is the visual identity reference and names the override surface; this spine is the experience. Single-tenant per project; users can belong to multiple projects but each project is a self-contained workspace.
+
+## Information Architecture
+
+| Surface | Reached from | Purpose |
+|---|---|---|
+| Today | App open / `g t` | Current focus, in-progress tasks pulled from all projects |
+| Projects | Sidebar / `g p` | List of active and archived projects |
+| Project detail | Projects row / `g 1`–`g 9` | Tasks in this project, organized by lane |
+| Search | `⌘K` / `Ctrl+K` | Command palette — surface, navigate, act |
+| Settings | Avatar menu | Account, theme, keyboard shortcuts, billing |
+
+Sidebar collapses to icons on `md`; becomes a `Sheet` on `sm`. Modal stacks one level deep (e.g., open `Dialog` on top of a surface, never on top of another dialog).
+
+→ Composition reference: `mockups/today.html`, `mockups/project-detail.html`, `mockups/command-palette.html`. Spine wins on conflict.
+
+## Voice and Tone
+
+Microcopy. Brand voice and aesthetic posture live in `DESIGN.md`.
+
+| Do | Don't |
+|---|---|
+| "What are you working on?" | "Let's get productive! 🚀" |
+| "3 tasks in motion" | "You have 3 active items." |
+| "Closed. Nice work." | "Task completed successfully ✓" |
+| "Nothing in motion. Pick something." | "No active tasks. Click below to get started!" |
+| Manager-facing: counts and verbs. Employee-facing: same. | Different tone per audience — Drift talks to everyone the same way. |
+
+## Component Patterns
+
+Behavioral. Visual specs live in `DESIGN.md.Components` (or in shadcn defaults, when inherited).
+
+| Component | Use | Behavioral rules |
+|---|---|---|
+| Task row | Projects, Today | Click anywhere on row opens edit dialog. Checkbox toggles done state with optimistic update. Hover reveals quick-actions (`focus`, `defer`, `archive`). |
+| Focus card | Today, Project detail | At most one focus card per surface — the task or project marked with `focus` state. `f` keyboard shortcut sets focus on the active row. |
+| Command palette | Global (⌘K) | Fuzzy search across all projects, tasks, and commands. `Enter` fires the highlighted result. `→` previews a result. Escape closes. |
+| Project header | Project detail | Inline-editable title (click to edit, blur to save). Status pill: active / archived / done. |
+| Empty state | Anywhere | shadcn's empty pattern + one Drift-specific sentence. `display-sm` for the headline, body text below, single primary action. |
+
+## State Patterns
+
+| State | Surface | Treatment |
+|---|---|---|
+| Cold app load | Today | shadcn `Skeleton` rows (4-6) match expected layout. Resolves on data. |
+| No focus | Today | `display-sm`: "Nothing in motion. Pick something." Below: list of in-progress tasks from all projects. |
+| Empty project | Project detail | `display-sm`: "{Project title} is empty." Body: "Add a first task to get going." Single primary button. |
+| Command palette no matches | ⌘K | "No matches. Start typing a task or project name, or pick an action below." Followed by 4-5 common commands. |
+| Offline | Global (status bar) | shadcn `Toast` once: "You're offline. Changes will sync when you reconnect." Local writes continue. |
+| Permission denied | Projects (others' private) | Surface hidden from sidebar. No "blocked" screen. |
+| Stale data | Project detail | If background refresh detects changes, shadcn `Toast`: "Updated by {user_name}. Refresh." Manual refresh, no auto. |
+
+## Interaction Primitives
+
+**Keyboard-first.** Drift's primary audience is developers and power users; the keyboard surface is the product, the mouse is fallback.
+
+- `⌘K` / `Ctrl+K` — Command palette (universal)
+- `g t` / `g p` — Go to Today / Projects (vim-style)
+- `g 1`–`g 9` — Go to project by sidebar position
+- `f` — Set focus on highlighted task/project
+- `c` — Create new task (context-aware: in the active project)
+- `Esc` — Close dialogs, exit edit mode, clear command palette
+- `/` — Focus search in current surface
+
+**Mouse:** click to act, drag deferred to v2. Hover reveals row actions on `md+` (touch users tap to reveal).
+
+**Banned everywhere:** infinite scroll (pagination only), drag-to-reorder in v1, hover-only affordances on `sm` viewports, modal stacks > 1 level deep.
+
+## Accessibility Floor
+
+Behavioral. Visual contrast lives in `DESIGN.md` (inherits shadcn's WCAG AA-compliant defaults; brand overrides verified to maintain ratios).
+
+- WCAG 2.2 AA across the responsive web surface.
+- Screen reader announces page surface on navigation: "Today, focus surface" / "Project: {name}, task list, {N} tasks."
+- Keyboard shortcuts available without modifier on most surfaces (vim-style `g t` etc.) — users with motor-control limitations get the same surface as power users.
+- `Tab` order matches reading order on every surface. `Esc` always closes the topmost modal/popover.
+- Command palette is fully keyboard-operable; results announce as they update via `aria-live`.
+- Focus rings inherit shadcn's `ring` token — visible at AA contrast against `background`.
+
+## Responsive & Platform
+
+| Breakpoint | Behavior |
+|---|---|
+| `≥ lg` (1024px+) | Sidebar visible. Today is a 2-column layout: focus + in-motion list. |
+| `md` (768–1023px) | Sidebar collapses to icons. Today stacks to single column. |
+| `< md` (`sm`) | Sidebar becomes a `Sheet` triggered from top bar. Command palette opens fullscreen. |
+
+Drift is responsive web, not a native mobile app. The product works on phones for read + simple-edit, but the primary surface is desktop / laptop.
+
+## Inspiration & Anti-patterns
+
+- **Lifted from Linear:** the keyboard-first discipline. `⌘K` is the command center; vim-style nav (`g t`); no drag for primary navigation; status pill vocabulary.
+- **Lifted from Notion:** inline-editable titles. Click-to-edit on project header, blur to save. No edit/view mode toggle.
+- **Lifted from shadcn:** the entire surface vocabulary. Drift's brand is *what we add to shadcn*, not a from-scratch design system. This is a deliberate posture, not a shortcut.
+- **Rejected — Streaks, badges, achievement notifications:** Drift is a tool, not a habit app. Task closure is its own reward; no celebratory animation, no "🎉 5-day streak!" toast.
+- **Rejected — AI-suggested next tasks:** Drift surfaces what's in motion, doesn't tell the user what to work on. The user picks focus; the tool surfaces consequences.
+- **Rejected — Multi-column kanban as default project view:** lists are linear; kanban hides progress behind columns. Optional v2; not the default.
+
+## Key Flows
+
+### Flow 1 — Morning focus (Sarah, solo founder, 8:45am Tuesday)
+
+1. Sarah opens Drift in a browser tab.
+2. App loads Today. `display-sm`: "Welcome back, Sarah." Focus card shows yesterday's marked task — "Finish landing page hero copy" — still in motion.
+3. She hits `⌘K`, types "ship hero", sees the matching task and presses Enter to open it.
+4. Inline edit: she updates the task description with two new bullets. Tab + Tab triggers save.
+5. **Climax:** Sarah closes the dialog. Today re-renders: focus card still shows the hero task, but now with the updated body text visible at a glance. She doesn't have to navigate anywhere — the surface that greeted her now reflects the work she just did. She picks up her coffee and starts writing.
+
+Failure: data save fails → shadcn `Toast` (destructive variant): "Couldn't save. Trying again." Inline edit retained; another `Enter` retries.
+
+### Flow 2 — Async handoff (Devon and Mara, small remote team, mid-afternoon)
+
+1. Devon finishes wiring up the auth flow and marks the task `done`.
+2. Mara, time-zoned three hours ahead and online during overlap, opens Drift.
+3. Today loads; her focus is on her own front-end work, but the in-motion list shows Devon's auth task now marked done and one task below it newly assigned to her — "Wire up post-auth redirect" — that Devon set during checkout.
+4. She hits `f` on the row to mark it as her focus, then `Enter` to open it.
+5. **Climax:** The focus card swaps. Her surface now shows the post-auth redirect task as the live thing she's working on; the projects sidebar shows the Auth project highlighted; the command palette `⌘K` defaults its first result to "Go to Auth project." The state of the team's progress is *embedded in her surface* — no Slack thread to scroll, no status doc to read.
+
+Failure: Devon hadn't actually assigned the follow-up — Mara mis-assigned to herself. She hits `Esc`, `f` again to unfocus, and reassigns to Devon. No "are you sure" dialog; Drift trusts the user.

package/src/xmc-skills/2-plan-workflows/xiaoma-ux/assets/headless-schemas.md

@@ -0,0 +1,84 @@
+# Headless Mode JSON Schemas
+
+Every headless run ends with one of these payloads. Omit keys for artifacts not produced.
+
+## Common fields
+
+- `status` — `"complete"`, `"blocked"`, or `"partial"`
+- `intent` — `"create"`, `"update"`, or `"validate"` (matches the detected intent)
+- `reason` — required when `status` is `"blocked"`; one-sentence explanation
+- `assumptions` — array of inferred values that were not directly confirmed by inputs
+- `open_questions` — array of items that need a human decision before the artifact can be considered final
+
+## Create
+
+```json
+{
+  "status": "complete",
+  "intent": "create",
+  "design": "{doc_workspace}/DESIGN.md",
+  "experience": "{doc_workspace}/EXPERIENCE.md",
+  "decision_log": "{doc_workspace}/.decision-log.md",
+  "working_artifacts": ["{doc_workspace}/.working/color-themes-1.html"],
+  "promoted_artifacts": {
+    "mockups": ["{doc_workspace}/mockups/direction-calm-sage.html"],
+    "wireframes": ["{doc_workspace}/wireframes/ia-2026-05-19.excalidraw"]
+  },
+  "open_questions": [],
+  "assumptions": [],
+  "external_handoffs": [
+    {"directive": "Confluence upload", "tool": "corp:confluence_upload", "url": "https://confluence.corp/DESIGN/123", "status": "ok"}
+  ]
+}
+```
+
+The `working_artifacts` and `promoted_artifacts` keys are optional and omitted entirely when empty. Headless Create runs default to not enabling creative tools — both keys are typically absent in headless output unless the caller enabled them.
+
+## Update
+
+```json
+{
+  "status": "complete",
+  "intent": "update",
+  "design": "{doc_workspace}/DESIGN.md",
+  "experience": "{doc_workspace}/EXPERIENCE.md",
+  "decision_log": "{doc_workspace}/.decision-log.md",
+  "changes_summary": "1-3 sentences describing what changed and why",
+  "conflicts_with_prior_decisions": [],
+  "open_questions": [],
+  "external_handoffs": [
+    {"directive": "Confluence upload", "tool": "corp:confluence_upload", "url": "https://confluence.corp/DESIGN/123", "status": "ok"}
+  ]
+}
+```
+
+## Validate
+
+```json
+{
+  "status": "complete",
+  "intent": "validate",
+  "validation_report": "{doc_workspace}/validation-report.md",
+  "findings_summary": {
+    "critical": 0,
+    "high": 0,
+    "medium": 0,
+    "low": 0
+  },
+  "offer_to_update": true
+}
+```
+
+`validation_report` is always written for Validate intent — the path here is required, not optional.
+
+## Blocked
+
+```json
+{
+  "status": "blocked",
+  "intent": "update",
+  "reason": "Change signal ambiguous — could be a brand refresh or an accessibility audit response; no inferred direction"
+}
+```
+
+Always include the intent (best-guess if not certain) and a one-sentence `reason`.

package/src/xmc-skills/2-plan-workflows/xiaoma-ux/assets/key-screens.md

@@ -0,0 +1,29 @@
+# Key Screens Renderer
+
+Subagent prompt. Fired at Finalize (or during late Discovery once layout decisions firm up). Produces 1:1 HTML mocks of the load-bearing surfaces so the spine can link to them as visual reference. Spine remains the contract; mocks illustrate.
+
+## Inputs
+
+`.decision-log.md`, the current drafts `DESIGN.md` and `EXPERIENCE.md`, `.working/` (especially the chosen color-theme and direction mocks), source PRD. The user names which surfaces to render — typically 2-4: the canonical entry surface, the most complex flow's hero screen, any load-bearing overlay/modal, and (when present) the Week / list / dashboard view.
+
+## What to render
+
+One HTML file per screen, at `.working/key-{slug}.html`. Each file: realistic device frame (phone or browser), real product content from the conversation (no lorem), every visible string voice-checked against `.decision-log.md`, all decided tokens applied. Show one canonical state per screen; if a surface has a load-bearing alternate state (focus, error, crisis-card-present), render it as a second column or section in the same file.
+
+Inline CSS, system fonts, no JS, no network. The mock must render fully offline. Comment block at the top of the `<style>` notes which spine sections govern this screen so a future reader knows what to check.
+
+## What to return
+
+A compact summary to the parent:
+- file path per screen
+- one-line caption per screen ("Today picker at rest; accent on Thought record")
+- which spine sections each mock illustrates (Component Patterns rows, State Patterns rows, Flow steps)
+
+The parent, at Finalize "Promote working artifacts," uses this summary to insert inline `mockups/...` links into the relevant spine sections.
+
+## Anti-patterns
+
+- Do not invent layout — every composition decision must trace to a `.working/` artifact or a confirmation in `.decision-log.md`. If a layout question is open, the mock is premature.
+- Do not show every screen of every flow — 2-4 load-bearing surfaces, not 14.
+- Do not stage marketing copy. Strings come from `.decision-log.md` and voice rules.
+- Do not introduce a new pattern not in the spine's Component Patterns table. If you need one, log it and ask before rendering.

package/src/xmc-skills/2-plan-workflows/xiaoma-ux/assets/validation-report-template.html

@@ -0,0 +1,319 @@
+<!DOCTYPE html>
+<!--
+  UX Design Validation Report — skeleton template.
+
+  This file is a starter the synthesis pass fills in directly. There is no
+  substitution engine. The LLM:
+    1. Reads {doc_workspace}/review-rubric.md and every review-{slug}.md from
+       additional reviewers.
+    2. Copies this skeleton.
+    3. Replaces the placeholder content (everything between TEMPLATE markers)
+       with the consolidated review, preserving the structure and CSS.
+    4. Writes the result to {doc_workspace}/validation-report.html.
+    5. Writes a markdown twin to {doc_workspace}/validation-report.md.
+
+  Visual rules the LLM must preserve:
+    - The container width, the color tokens, the typography.
+    - One dimension = one collapsible <section class="dimension">.
+    - Verdict pill uses the verdict-* class matching its judgment.
+    - Severity badge uses the badge-sev-* class matching its level.
+    - Each extra reviewer (accessibility, adversarial, etc.) gets its own
+      collapsible section below the rubric dimensions.
+    - The footer always shows the artifact paths and timestamp.
+-->
+<html lang="en">
+<head>
+<meta charset="utf-8">
+<title>UX Design Validation: TEMPLATE_UX_SPEC_NAME</title>
+<style>
+  :root {
+    --bg: #fafaf9;
+    --surface: #ffffff;
+    --border: #e7e5e4;
+    --text: #1c1917;
+    --muted: #78716c;
+
+    --verdict-strong: #16a34a;
+    --verdict-adequate: #65a30d;
+    --verdict-thin: #d97706;
+    --verdict-broken: #dc2626;
+
+    --sev-low: #64748b;
+    --sev-medium: #ca8a04;
+    --sev-high: #ea580c;
+    --sev-critical: #dc2626;
+  }
+  * { box-sizing: border-box; }
+  html, body { margin: 0; padding: 0; }
+  body {
+    font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Inter, system-ui, sans-serif;
+    background: var(--bg);
+    color: var(--text);
+    line-height: 1.6;
+    font-size: 15px;
+  }
+  .container { max-width: 960px; margin: 0 auto; padding: 32px 24px 64px; }
+
+  header.report-header {
+    display: flex;
+    align-items: flex-start;
+    justify-content: space-between;
+    gap: 24px;
+    padding-bottom: 16px;
+    border-bottom: 1px solid var(--border);
+    margin-bottom: 24px;
+  }
+  .title h1 { margin: 0; font-size: 22px; font-weight: 600; letter-spacing: -0.01em; }
+  .title .subtitle { color: var(--muted); font-size: 13px; margin-top: 4px; font-family: ui-monospace, "SF Mono", Menlo, monospace; }
+
+  .synthesis {
+    background: var(--surface);
+    border: 1px solid var(--border);
+    border-left: 3px solid var(--muted);
+    border-radius: 8px;
+    padding: 18px 22px;
+    margin-bottom: 24px;
+    font-size: 15.5px;
+  }
+  .synthesis p { margin: 0 0 10px; }
+  .synthesis p:last-child { margin-bottom: 0; }
+
+  .dimension-summary {
+    display: grid;
+    grid-template-columns: repeat(auto-fit, minmax(180px, 1fr));
+    gap: 10px;
+    margin-bottom: 24px;
+  }
+  .dim-card {
+    background: var(--surface);
+    border: 1px solid var(--border);
+    border-radius: 8px;
+    padding: 12px 14px;
+  }
+  .dim-card .dim-name { font-size: 13px; color: var(--muted); margin-bottom: 6px; }
+  .dim-card .dim-verdict { font-size: 14px; font-weight: 600; }
+
+  section.dimension, section.reviewer-section { margin-bottom: 14px; }
+  section.dimension details, section.reviewer-section details {
+    background: var(--surface);
+    border: 1px solid var(--border);
+    border-radius: 8px;
+    overflow: hidden;
+  }
+  section summary {
+    padding: 14px 20px;
+    cursor: pointer;
+    user-select: none;
+    list-style: none;
+    display: flex;
+    align-items: center;
+    gap: 12px;
+  }
+  section summary::-webkit-details-marker { display: none; }
+  section summary::before {
+    content: "▸";
+    display: inline-block;
+    color: var(--muted);
+    transition: transform 0.15s ease;
+  }
+  section details[open] summary::before { transform: rotate(90deg); }
+  section summary h2 {
+    display: inline;
+    margin: 0;
+    font-size: 16px;
+    font-weight: 600;
+    letter-spacing: -0.005em;
+    flex: 1;
+  }
+  .verdict-pill {
+    font-size: 11px;
+    padding: 3px 10px;
+    border-radius: 999px;
+    font-weight: 600;
+    text-transform: uppercase;
+    letter-spacing: 0.04em;
+    color: white;
+  }
+  .verdict-strong { background: var(--verdict-strong); }
+  .verdict-adequate { background: var(--verdict-adequate); }
+  .verdict-thin { background: var(--verdict-thin); }
+  .verdict-broken { background: var(--verdict-broken); }
+
+  .dim-body { padding: 4px 20px 18px; }
+  .dim-judgment { color: var(--text); font-size: 14.5px; }
+  .dim-judgment p { margin: 0 0 10px; }
+
+  .findings-list { padding: 0 20px 4px; }
+  article.finding {
+    padding: 14px 0;
+    border-top: 1px solid var(--border);
+  }
+  article.finding:first-child { border-top: none; }
+  article.finding header {
+    display: flex;
+    align-items: center;
+    gap: 10px;
+    flex-wrap: wrap;
+    margin-bottom: 6px;
+  }
+  .badge {
+    font-size: 10.5px;
+    padding: 3px 8px;
+    border-radius: 4px;
+    font-weight: 600;
+    text-transform: uppercase;
+    letter-spacing: 0.04em;
+    line-height: 1.4;
+  }
+  .badge-sev-low { background: rgba(100, 116, 139, 0.12); color: var(--sev-low); }
+  .badge-sev-medium { background: rgba(202, 138, 4, 0.14); color: var(--sev-medium); }
+  .badge-sev-high { background: rgba(234, 88, 12, 0.14); color: var(--sev-high); }
+  .badge-sev-critical { background: rgba(220, 38, 38, 0.14); color: var(--sev-critical); }
+  .finding-title { margin: 0; font-size: 15px; font-weight: 500; flex: 1; min-width: 200px; }
+  .finding-location { font-family: ui-monospace, "SF Mono", Menlo, monospace; font-size: 12.5px; color: var(--muted); }
+  .finding-note, .finding-fix { margin-top: 6px; font-size: 14px; }
+  .finding-fix strong { color: var(--muted); font-weight: 500; }
+
+  .reviewer-source {
+    font-size: 12px;
+    color: var(--muted);
+    font-family: ui-monospace, "SF Mono", Menlo, monospace;
+  }
+
+  .mechanical {
+    background: var(--surface);
+    border: 1px solid var(--border);
+    border-radius: 8px;
+    padding: 16px 20px;
+    margin-top: 24px;
+    font-size: 14px;
+  }
+  .mechanical h3 { margin: 0 0 10px; font-size: 14px; font-weight: 600; color: var(--muted); text-transform: uppercase; letter-spacing: 0.04em; }
+  .mechanical ul { margin: 0; padding-left: 20px; }
+  .mechanical li { margin-bottom: 4px; color: var(--text); }
+
+  footer.report-footer {
+    margin-top: 40px;
+    padding-top: 16px;
+    border-top: 1px solid var(--border);
+    font-size: 12px;
+    color: var(--muted);
+    font-family: ui-monospace, "SF Mono", Menlo, monospace;
+  }
+  footer .meta { display: flex; gap: 24px; flex-wrap: wrap; }
+</style>
+</head>
+<body>
+  <div class="container">
+
+    <!-- TEMPLATE: header. Fill ux spec name and ux spec path. No overall grade —
+         per-category verdicts and severity counts below carry the picture. -->
+    <header class="report-header">
+      <div class="title">
+        <h1>TEMPLATE_UX_SPEC_NAME — UX Design Validation Report</h1>
+        <div class="subtitle">TEMPLATE_UX_SPEC_PATH</div>
+      </div>
+    </header>
+
+    <!-- TEMPLATE: overall synthesis paragraphs. Lift directly from
+         review-rubric.md "Overall verdict" section; expand if extra reviewers
+         (accessibility, adversarial, etc.) materially shift the picture.
+         Wrap each paragraph in <p>. -->
+    <div class="synthesis">
+      <p>TEMPLATE_SYNTHESIS_PARAGRAPH</p>
+    </div>
+
+    <!-- TEMPLATE: dimension summary cards. One per rubric category, in this
+         canonical order (from references/validate.md):
+           1. Flow coverage
+           2. Token completeness
+           3. Component coverage
+           4. State coverage
+           5. Visual reference coverage
+           6. Bloat & overspecification
+           7. Inheritance discipline
+           8. Shape fit
+         The dim-verdict text uses one of: strong | adequate | thin | broken. -->
+    <div class="dimension-summary">
+      <div class="dim-card">
+        <div class="dim-name">TEMPLATE_CATEGORY_NAME</div>
+        <div class="dim-verdict" style="color: var(--verdict-TEMPLATE_VERDICT)">TEMPLATE_VERDICT_TEXT</div>
+      </div>
+      <!-- repeat for each of the eight rubric categories -->
+    </div>
+
+    <!-- TEMPLATE: one section per rubric category, same canonical order as the
+         summary cards above. Skip a category entirely if the rubric review
+         marked it n/a for this UX spec. Open the section by default if verdict
+         is thin or broken. -->
+    <section class="dimension">
+      <details open>
+        <summary>
+          <h2>TEMPLATE_CATEGORY_NAME</h2>
+          <span class="verdict-pill verdict-TEMPLATE_VERDICT">TEMPLATE_VERDICT_TEXT</span>
+        </summary>
+        <div class="dim-body">
+          <div class="dim-judgment">
+            <p>TEMPLATE_DIMENSION_JUDGMENT</p>
+          </div>
+        </div>
+        <div class="findings-list">
+          <!-- TEMPLATE: zero or more findings -->
+          <article class="finding">
+            <header>
+              <span class="badge badge-sev-TEMPLATE_SEVERITY">TEMPLATE_SEVERITY</span>
+              <h3 class="finding-title">TEMPLATE_FINDING_TITLE</h3>
+              <span class="finding-location">TEMPLATE_LOCATION</span>
+            </header>
+            <div class="finding-note">TEMPLATE_FINDING_NOTE</div>
+            <div class="finding-fix"><strong>Fix:</strong> TEMPLATE_SUGGESTED_FIX</div>
+          </article>
+        </div>
+      </details>
+    </section>
+
+    <!-- TEMPLATE: one section per extra reviewer that ran (accessibility,
+         adversarial, brand-conformance, etc.). Skip this block entirely if
+         only the rubric walker ran. -->
+    <section class="reviewer-section">
+      <details>
+        <summary>
+          <h2>Accessibility review</h2>
+          <span class="reviewer-source">TEMPLATE_REVIEWER_SOURCE_FILE</span>
+        </summary>
+        <div class="dim-body">
+          <div class="dim-judgment">
+            <p>TEMPLATE_REVIEWER_PREAMBLE</p>
+          </div>
+        </div>
+        <div class="findings-list">
+          <article class="finding">
+            <header>
+              <span class="badge badge-sev-TEMPLATE_SEVERITY">TEMPLATE_SEVERITY</span>
+              <h3 class="finding-title">TEMPLATE_FINDING_TITLE</h3>
+              <span class="finding-location">TEMPLATE_LOCATION</span>
+            </header>
+            <div class="finding-note">TEMPLATE_FINDING_NOTE</div>
+            <div class="finding-fix"><strong>Fix:</strong> TEMPLATE_SUGGESTED_FIX</div>
+          </article>
+        </div>
+      </details>
+    </section>
+
+    <!-- TEMPLATE: mechanical notes — short, bulleted. Skip if there are none. -->
+    <div class="mechanical">
+      <h3>Mechanical notes</h3>
+      <ul>
+        <li>TEMPLATE_MECHANICAL_NOTE</li>
+      </ul>
+    </div>
+
+    <footer class="report-footer">
+      <div class="meta">
+        <span>Rubric: TEMPLATE_RUBRIC_PATH</span>
+        <span>Generated: TEMPLATE_TIMESTAMP</span>
+      </div>
+    </footer>
+  </div>
+</body>
+</html>

package/src/xmc-skills/2-plan-workflows/xiaoma-ux/customize.toml

@@ -0,0 +1,100 @@
+# DO NOT EDIT -- overwritten on every update.
+#
+# Workflow customization surface for xiaoma-ux.
+# Overrides:
+#   {project-root}/_xiaoma/custom/xiaoma-ux.toml         (team)
+#   {project-root}/_xiaoma/custom/xiaoma-ux.user.toml    (personal)
+# Merge rules: scalars override, arrays append.
+
+[workflow]
+
+# Steps to run before/after standard activation. Append-only.
+activation_steps_prepend = []
+activation_steps_append = []
+
+# Persistent facts loaded at activation and kept in mind for the run.
+# Entries: literal sentence, `skill:NAME`, or `file:PATH` (glob ok).
+persistent_facts = [
+  "file:{project-root}/**/project-context.md",
+]
+
+# Runs at workflow completion. String or array of instructions.
+on_complete = ""
+
+# Reference DESIGN.md spines the distillation subagent reads to anchor shape
+# and editorial richness. Convention-compliant with the Google Labs DESIGN.md
+# spec (https://github.com/google-labs-code/design.md). Append entries via
+# override TOML to seed an org-specific canonical aesthetic.
+# Each entry: `file:PATH` (or bare relative path, resolved skill-relative).
+design_md_examples = [
+  "assets/design-example-mobile.md",
+  "assets/design-example-shadcn.md",
+  "assets/design-example-editorial.md",
+]
+
+# Reference EXPERIENCE.md spines for the behavioral/flow/IA layer. Each entry:
+# `file:PATH` (or bare relative path, resolved skill-relative).
+experience_md_examples = [
+  "assets/experience-example-mobile.md",
+  "assets/experience-example-shadcn.md",
+]
+
+# Design handoff targets — external tools that can take over the design /
+# visual identity work. The user runs the tool externally and saves outputs
+# (whatever the tool produces — DESIGN.md, Figma files, React components,
+# HTML mocks) to {doc_workspace}.
+# Each entry: `tool:NAME: <directive>`, `skill:NAME`, or plain-text descriptor.
+# Default: Google Stitch (emits DESIGN.md + per-screen HTML). Other producers:
+# Vercel v0, Figma, Galileo, Anima, internal generators.
+design_handoffs = [
+  "Google Stitch (https://stitch.withgoogle.com) — emits DESIGN.md + per-screen HTML. Paste assembled prompt; save outputs to {doc_workspace}.",
+]
+
+# HTML skeleton filled in by the validation synthesis pass.
+validation_report_template = "assets/validation-report-template.html"
+
+# Run folder. DESIGN.md, EXPERIENCE.md, .decision-log.md, .working/
+# (creative-tool artifacts), imports/ (user-supplied screens / brand decks /
+# Figma exports / sketches), optional mockups/ and wireframes/ (promoted
+# artifacts), optional validation-report.* all land inside
+# {ux_output_path}/{run_folder_pattern}/.
+ux_output_path = "{planning_artifacts}/ux-designs"
+run_folder_pattern = "ux-{project_name}-{date}"
+
+# Creative tools registry. Collaborative renderers invoked on demand during
+# Discovery and at Finalize. Entry forms: `file:PATH`, `skill:NAME`,
+# `tool:MCP_TOOL: <directive>`, or plain text. Defaults ship for HTML color
+# themes, HTML design directions, Excalidraw wireframes (Discovery), and
+# 1:1 HTML key-screen mockups (Finalize). Working artifacts land in
+# {doc_workspace}/.working/; finalize promotes those with lasting reference
+# value to mockups/ or wireframes/. See references/creative-tools.md.
+creative_tools = [
+  "file:assets/color-themes.md",
+  "file:assets/design-directions.md",
+  "file:assets/excalidraw-wireframe.md",
+  "file:assets/key-screens.md",
+]
+
+# Polish passes applied to DESIGN.md and EXPERIENCE.md at finalize.
+# Entries: `skill:NAME`, `file:PATH`, or plain text directive.
+# Suggested order: structural → content/voice → prose mechanics.
+doc_standards = [
+  "skill:xiaoma-editorial-review-structure",
+  "skill:xiaoma-editorial-review-prose",
+]
+
+# Information retrieval registry. Consulted on demand when the conversation
+# surfaces a matching need. Distinct from creative_tools (artifact production).
+# Example: "When researching component patterns, consult corp:design_system_search."
+external_sources = []
+
+# Routes outputs beyond local files at Finalize. Returned URLs/IDs surfaced
+# to the user. Unavailable tools skipped and flagged.
+# Example: "Upload DESIGN.md to Confluence via corp:confluence_upload (space_key='DESIGN')."
+external_handoffs = []
+
+# Reviewers spawned at Finalize step 4 and at Validate intent, alongside
+# the rubric walker. Entries: `skill:NAME`, `file:PATH`, or plain text.
+# Common ad-hoc add (judged by the skill): accessibility-focused reviewer
+# for consumer / regulated work.
+finalize_reviewers = []