qfai 1.7.13 → 1.7.15

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/01_Context.md

@@ -4,12 +4,21 @@
 
 ## UI-bearing Classification
 
+Classification determines whether UI/UX sidecar artifacts are required.
+
 - ui_bearing: [true|false]
 - primary_surface: [web|mobile|desktop|cli|mixed|non-ui]
 - secondary_surfaces:
   - [optional]
 - classification_rationale: [Why this classification was chosen]
 
+Notes:
+
+- `primary_surface` is a classification field. Valid values: `web|mobile|desktop|cli|mixed|non-ui`.
+- `non-ui` is only valid when `ui_bearing: false`. It is a classification value, not a prototyping surface.
+- `cli` is a UI-bearing surface. When classified as `cli`, set `ui_bearing: true`.
+- Prototyping surfaces (used in `prototyping.yaml`) are a subset: `web|mobile|desktop|cli|mixed`.
+
 ## Metadata
 
 | Key           | Value                        |

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/03_Story-Workshop.md

@@ -73,7 +73,7 @@ Screen-level contract details are finalized in `uiux/40_screen_contracts.md`. Pr
 ## Appendix: Screen Mock — Optional Fallback (HTML+CSS)
 
 <!-- Optional fallback only — do not use as the primary UI definition artifact.
-     Include only when it materially clarifies the selected direction.
+     Include only when it materially clarifies the selected anchor.
      Behavior Obligations and sidecar artifacts (uiux/) are the primary UI definitions.
      The required state SSOT is uiux/40_screen_contracts.md (`default/loading/empty/error`). -->
 

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/04_Sources.md

@@ -14,71 +14,122 @@
 
 ## Trend Scan
 
-### Visual Tone Trends
+### user expectation / market norm
 
 #### Entry 1
 
 - reference: [Source name or URL]
-- observation: [What visual tone signal was observed]
-- freshness_date: YYYY-MM-DD
-- confidence: [high|medium|low]
-- source_translation: [How the signal translates into this project]
+- observation: [What user expectation or market norm signal was observed]
+- decision_connection: [How the signal translates into this project]
+- evaluation_connection: [How the signal should be evaluated in design review]
 - local_implication: [What should change locally]
 
-### Layout / Composition Trends
+### product neighbor / comparable flow
 
 #### Entry 1
 
 - reference: [Source name or URL]
-- observation: [What layout or composition signal was observed]
-- freshness_date: YYYY-MM-DD
-- confidence: [high|medium|low]
-- source_translation: [How the signal translates into this project]
+- observation: [What comparable product or flow signal was observed]
+- decision_connection: [How the signal translates into this project]
+- evaluation_connection: [How the signal should be evaluated in design review]
 - local_implication: [What should change locally]
 
-### Density / Hierarchy Trends
+### platform convention
 
 #### Entry 1
 
 - reference: [Source name or URL]
-- observation: [What density or hierarchy signal was observed]
-- freshness_date: YYYY-MM-DD
-- confidence: [high|medium|low]
-- source_translation: [How the signal translates into this project]
+- observation: [What platform convention signal was observed]
+- decision_connection: [How the signal translates into this project]
+- evaluation_connection: [How the signal should be evaluated in design review]
 - local_implication: [What should change locally]
 
-### Interaction / Motion Trends
+### accessibility / compliance relevant signal
 
 #### Entry 1
 
 - reference: [Source name or URL]
-- observation: [What interaction or motion signal was observed]
-- freshness_date: YYYY-MM-DD
-- confidence: [high|medium|low]
-- source_translation: [How the signal translates into this project]
+- observation: [What accessibility or compliance signal was observed]
+- decision_connection: [How the signal translates into this project]
+- evaluation_connection: [How the signal should be evaluated in design review]
 - local_implication: [What should change locally]
 
-### Component Styling Trends
+### color
 
 #### Entry 1
 
+- source_id: [SRC-ID from Source Registry]
 - reference: [Source name or URL]
-- observation: [What component styling signal was observed]
-- freshness_date: YYYY-MM-DD
-- confidence: [high|medium|low]
-- source_translation: [How the signal translates into this project]
-- local_implication: [What should change locally]
+- observation: [What color trend or signal was observed]
+- decision_connection: [How the color signal translates into this project]
+- evaluation_connection: [Which TRD-XX axis evaluates this color signal; leave blank to trigger UIX-VAL-T01]
+- local_implication: [What color choices should change locally]
 
-### Stale / Overused AI Slop Patterns
+### typography
 
 #### Entry 1
 
+- source_id: [SRC-ID from Source Registry]
 - reference: [Source name or URL]
-- observation: [What stale pattern should be avoided]
-- freshness_date: YYYY-MM-DD
-- confidence: [high|medium|low]
-- source_translation: [Why this stale pattern is relevant to avoid here]
-- local_implication: [What should be explicitly avoided locally]
+- observation: [What typographic trend or signal was observed]
+- decision_connection: [How the typography signal translates into this project]
+- evaluation_connection: [Which TRD-XX axis evaluates this typography signal; leave blank to trigger UIX-VAL-T01]
+- local_implication: [What typeface or scale choices should change locally]
+
+### Visual
+
+#### Entry 1
+
+- source_id: [SRC-ID from Source Registry]
+- reference: [Source name or URL]
+- observation: [What visual motif trend or signal was observed]
+- decision_connection: [How the visual motif translates into this project]
+- evaluation_connection: [Which TRD-XX axis evaluates this visual motif; leave blank to trigger UIX-VAL-T01]
+- local_implication: [What visual motif choices should change locally]
+
+### spacing
+
+#### Entry 1
+
+- source_id: [SRC-ID from Source Registry]
+- reference: [Source name or URL]
+- observation: [What spacing convention or density trend was observed]
+- decision_connection: [How the spacing signal translates into this project]
+- evaluation_connection: [Which TRD-XX axis evaluates this spacing signal; leave blank to trigger UIX-VAL-T01]
+- local_implication: [What spacing or density choices should change locally]
+
+### shape
+
+#### Entry 1
+
+- source_id: [SRC-ID from Source Registry]
+- reference: [Source name or URL]
+- observation: [What shape language trend was observed (border-radius, geometric vs organic, etc.)]
+- decision_connection: [How the shape language translates into this project]
+- evaluation_connection: [Which TRD-XX axis evaluates this shape signal; leave blank to trigger UIX-VAL-T01]
+- local_implication: [What shape-language choices should change locally]
+
+### imagery
+
+#### Entry 1
+
+- source_id: [SRC-ID from Source Registry]
+- reference: [Source name or URL]
+- observation: [What imagery or illustration style trend was observed]
+- decision_connection: [How the imagery signal translates into this project]
+- evaluation_connection: [Which TRD-XX axis evaluates this imagery signal; leave blank to trigger UIX-VAL-T01]
+- local_implication: [What imagery or illustration choices should change locally]
+
+### design_guideline_research
+
+#### Entry 1
+
+- source_id: [SRC-ID from Source Registry]
+- guideline_name: [Applicable platform or library guideline family]
+- rule_refs:
+  - [Specific rule or section reference]
+- local_translation: [How the guideline changes this project's local design decisions]
+- evidence: [Concrete note, screenshot, or doc excerpt reference supporting the translation]
 
 ## Competitive Reference Registry
 

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/14_Review-Request.md

@@ -37,22 +37,22 @@
 - Mermaid diagrams use ` ```mermaid ` fences only
 - Strategy alignment and chosen_option consistency (when UI-bearing)
 - Taste reflection completeness and clarity (when UI-bearing)
-- Trend scan freshness and source translation quality (when UI-bearing)
+- Trend scan freshness and evidence traceability (when UI-bearing)
 - 3-layer axes evaluation quality and traceability (when UI-bearing)
 - Option comparison integrity (when UI-bearing)
-- Selected anchor screen clarity and direction justification (when UI-bearing)
+- Selected anchor screen clarity and anchor justification (when UI-bearing)
 - Screen contract sufficiency and strong schema completeness (when UI-bearing)
 - Generic fallback risk — ensure no unreviewed generic/placeholder UI remains (when UI-bearing)
 - OQ register exit condition (open count = 0)
 - Deferred items have full metadata
 
-## Selected Direction Consistency
+## Selected Anchor Consistency
 
 <!-- Required for UI-bearing packs. Verifies sidecar-family alignment. -->
 
-- Selected direction: verify `uiux/31_selected_anchor_screen.md` Selected Direction is populated and references a compared option from `uiux/30_option_comparison.md`
-- Strategy alignment: verify `uiux/10_implementation_strategy.md` aligns with the selected direction in `uiux/31_selected_anchor_screen.md`
-- Evaluation traceability: verify selected direction rationale aligns with 3-layer evaluation family (20/21/22/23 + optional 24)
+- Selected anchor: verify `uiux/31_selected_anchor_screen.md` selected anchor is populated and references a compared option from `uiux/30_option_comparison.md`
+- Strategy alignment: verify `uiux/10_implementation_strategy.md` aligns with the selected anchor in `uiux/31_selected_anchor_screen.md`
+- Evaluation traceability: verify selected anchor rationale aligns with 3-layer evaluation family (20/21/22/23 + optional 24)
 
 ## Sidecar Artifact Review Scope
 
@@ -62,7 +62,7 @@
 - Verify uiux/10_implementation_strategy.md strict canonical schema is complete
 - Verify scoring axes have evaluation criteria and measurement approaches
 - Verify option comparison covers 2+ options against all scoring axes in `uiux/30_option_comparison.md`
-- Verify `uiux/31_selected_anchor_screen.md` Selected Direction references a compared option
+- Verify `uiux/31_selected_anchor_screen.md` selected anchor references a compared option
 - Verify `uiux/24_design_eval_dynamic_overrides.md` has documented override rules
 - Verify screen contracts use nested strong schema with all 4 required states (default/loading/empty/error) and treat `uiux/40_screen_contracts.md` as the state SSOT
 

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/prototyping.yaml

@@ -1,9 +1,17 @@
 prototyping:
-  recommended_mode: standard
+  recommended_mode: full-harness
   rationale: >
-    Fill this with a concrete reason tied to evidence obligations.
+    Fill this with a concrete reason tied to the full-harness evidence obligations.
   allowed_modes:
-    - low-cost
-    - standard
     - full-harness
+  # Replace `web` with one of the prototyping-supported surfaces if needed:
+  #   web | mobile | desktop | mixed
+  # (discussion classification also allows `cli` and `non-ui`, but those are
+  #  not valid prototyping execution surfaces; see
+  #  `packages/qfai/src/core/prototyping/surfacePolicy.ts` — PROTOTYPING_SUPPORTED_SURFACES.)
   surface: web
+  mode_expectations:
+    full-harness:
+      expected_iterations: "2+"
+      process: "measure -> score -> fix code -> re-run"
+      calibration_ref: "qfai.config.yaml#prototyping.calibration"

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/review/Rxx_reviewer.md

@@ -14,9 +14,9 @@
 - [ ] Mermaid diagrams are sufficient for decisions (scope/AC/risk consistency)
 - [ ] Mermaid diagrams use ` ```mermaid ` fences only
 - [ ] Taste interview completeness (when UI-bearing)
-- [ ] Trend freshness and translation quality (when UI-bearing)
+- [ ] Trend freshness and evidence traceability (when UI-bearing)
 - [ ] 3-layer evaluation quality and traceability (when UI-bearing)
-- [ ] Option comparison integrity and selected direction clarity (when UI-bearing)
+- [ ] Option comparison integrity and selected anchor clarity (when UI-bearing)
 - [ ] Strong screen contract completeness (when UI-bearing)
 - [ ] OQ register exit condition (open count = 0)
 - [ ] Deferred items have full metadata

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/review/review_request.md

@@ -23,9 +23,9 @@
   - Security/operations risks are reflected in diagrams where relevant
 - Mermaid diagrams use ` ```mermaid ` fences only (no ` ```text ` or language-less fences)
 - Taste interview completeness and clarity (when UI-bearing)
-- Trend freshness and source translation quality (when UI-bearing)
+- Trend freshness and evidence traceability (when UI-bearing)
 - 3-layer evaluation quality and traceability (when UI-bearing)
-- Option comparison integrity and selected direction clarity (when UI-bearing)
+- Option comparison integrity and selected anchor clarity (when UI-bearing)
 - Strong screen contract completeness (when UI-bearing)
 - OQ register exit condition (open count = 0)
 - Deferred items have full metadata in `13_Deferred.md`

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/uiux/10_implementation_strategy.md

@@ -1,20 +1,38 @@
 # Implementation Strategy
 
-## Strategy Definition
+## Surface
 
-<!-- Use exactly one canonical strategy block. -->
+- surface: web
 
-### Strategy
+## Selection Requirement
 
-- surface: [web|mobile|desktop|cli|mixed|non-ui]
-- decision: [template|component-library|design-system|native-pattern|bespoke|none]
-- why_this_strategy: [Why this strategy is the right fit for the current product and surface]
-- expected_strengths: [Concrete strengths expected from this strategy]
-- known_risks: [Concrete risks, failure modes, or tradeoffs]
-- fit_for_this_product: [Why this strategy matches the actual product context]
+- selection_required: true
 
-## Constraints
+## Decision
 
-- Use only the canonical enum values shown above.
-- Do not add legacy keys or freeform alternative enums.
-- Keep the strategy aligned with `01_Context.md` classification and `31_selected_anchor_screen.md`.
+- decision: component-library
+
+## Candidate Options
+
+- candidate_options:
+  - component-library
+  - bespoke
+
+## Chosen Option
+
+- chosen_option: component-library
+
+## Rationale
+
+- rationale:
+  - Existing design-system alignment is more valuable than bespoke variance.
+
+## Verification Expectations
+
+- verification_expectations:
+  - Primary tasks remain obvious without generic dashboard drift.
+
+## Notes for Reviewer
+
+- notes_for_reviewer:
+  - Check that the selected anchor stays aligned with the anchor screen and screen contracts.

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/uiux/12_design_system.md

@@ -0,0 +1,115 @@
+# Design System
+
+<!-- REQUIRED FIELDS — fill each section; do not leave bodies empty -->
+
+## Visual Theme
+
+<!-- Describe the overall design aesthetic and brand personality.
+     Required: archetype label (from design-md-brand-catalog), rationale, 1–2 guiding adjectives. -->
+
+- archetype: [e.g., Minimal / Bold / Corporate / Playful / Organic / Tech / Elegant / Casual]
+- rationale: [Why this archetype fits the product and target users]
+- guiding_adjectives:
+  - [first adjective]
+  - [second adjective]
+
+## Color Palette
+
+<!-- Define the primary, secondary, and semantic color tokens.
+     Required: at least 3 named colors with hex values and usage notes. -->
+
+- primary:
+  - name: [token name, e.g., brand-blue]
+  - hex: [#XXXXXX]
+  - usage: [where this color appears]
+- secondary:
+  - name: [token name]
+  - hex: [#XXXXXX]
+  - usage: [where this color appears]
+- semantic:
+  - success: [#XXXXXX]
+  - warning: [#XXXXXX]
+  - error: [#XXXXXX]
+  - info: [#XXXXXX]
+
+## Typography
+
+<!-- Define typeface choices, scale, and usage rules.
+     Required: heading typeface, body typeface, base size, scale rationale. -->
+
+- heading_typeface: [e.g., Inter, Playfair Display]
+- body_typeface: [e.g., Inter, Noto Sans]
+- base_size: [e.g., 16px / 1rem]
+- scale_ratio: [e.g., 1.25 — Major Third]
+- usage_rules:
+  - [rule 1, e.g., "H1 only for page titles; max one per page"]
+  - [rule 2]
+
+## Spacing & Layout
+
+<!-- Define the spacing unit system, grid, and common layout patterns.
+     Required: base unit, grid columns, gutter, common spacing tokens. -->
+
+- base_unit: [e.g., 4px or 8px]
+- grid_columns: [e.g., 12]
+- gutter: [e.g., 24px]
+- tokens:
+  - xs: [e.g., 4px]
+  - sm: [e.g., 8px]
+  - md: [e.g., 16px]
+  - lg: [e.g., 24px]
+  - xl: [e.g., 48px]
+
+## Component Style
+
+<!-- Describe the visual treatment of core UI components (buttons, inputs, cards, etc.).
+     Required: border-radius philosophy, shadow level, interactive state rules. -->
+
+- border_radius: [e.g., 4px for inputs, 8px for cards, 24px for pills]
+- shadow_level: [e.g., flat / subtle / elevated — explain the use case for each]
+- interactive_states:
+  - hover: [description]
+  - focus: [description, e.g., 2px offset ring in brand-blue]
+  - disabled: [description, e.g., 40% opacity]
+- density: [e.g., comfortable / compact — which default and why]
+
+## Animation & Motion
+
+<!-- Define motion principles, duration, and easing used across the product.
+     Required: motion intent, base duration, easing curve, guidance on when to avoid animation. -->
+
+- intent: [e.g., "Motion should feel purposeful and guide attention; never decorative."]
+- base_duration_ms: [e.g., 200]
+- easing: [e.g., ease-out cubic-bezier(0.0, 0.0, 0.2, 1)]
+- reduced_motion_policy: [e.g., "Respect prefers-reduced-motion; all transitions become instant."]
+- avoid_when:
+  - [scenario where animation would harm UX]
+
+## Do's and Don'ts
+
+<!-- Provide explicit guidance on what to do and what to avoid.
+     Required: at least 3 Do items and 3 Don't items. -->
+
+### Do
+
+- [Do: use the primary color only for primary call-to-action elements]
+- [Do: maintain a minimum 4.5:1 contrast ratio on all body text]
+- [Do: use spacing tokens from the defined scale — no ad-hoc pixel values]
+
+### Don't
+
+- [Don't: use more than 3 typeface weights on a single screen]
+- [Don't: apply shadow to elements that are already on a elevated surface]
+- [Don't: animate decoratively; every motion must have a functional purpose]
+
+## Agent Implementation Guide
+
+<!-- Instructions for the AI agent implementing this design system.
+     Required: derivation rules, how to handle ambiguity, where to read and write design tokens. -->
+
+- derivation_rules:
+  - [rule 1: how to select an archetype from the brand catalog]
+  - [rule 2: how to resolve conflicts between archetype defaults and product-specific overrides]
+- token_source: [where the authoritative token file lives, e.g., tokens/design-tokens.json]
+- ambiguity_policy: [e.g., "When a value is unspecified, prefer the archetype default; log a TODO for review."]
+- validation_reference: UIX-VAL-DS02 (required sections) and UIX-VAL-DS01 (presence check)

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/uiux/21_design_eval_trend_derived.md

@@ -5,42 +5,104 @@
 - Layer: trend-derived
 - Source: Industry trend analysis and research synthesis
 
+## Source Refs Authoring Guidance
+
+<!-- Each axis MUST include a `source_refs` list pointing to entries in `04_Sources.md`.
+     Use the `source_id` values from `04_Sources.md` Source Registry (e.g., SRC-0001).
+     For visual-category Trend Scan entries (color, typography, visual motif, spacing, shape, imagery),
+     at least one visual TRD-XX axis MUST reference those entries via `source_refs`;
+     omitting this will trigger UIX-VAL-T04 at validation time. -->
+
+## Score Anchor Guidance
+
+- Every `score_anchors.low`, `score_anchors.mid`, and `score_anchors.high` entry MUST include a quantitative proxy, not adjectives alone.
+- Acceptable quantitative proxies include concrete values such as `44px` target size, contrast `ratio`, `WCAG` level, modular scale steps, explicit `class name`, or a measurable `default value`.
+- Adjective-only anchors such as "modern", "polished", or "clean" without a measurable proxy are non-compliant and will trigger downstream warning `UIX-VAL-T06`.
+
 ## Axes
 
-### Axis: [TRD-01]
+<!-- VISUAL AXIS EXAMPLE 1: Visual Warmth & Color Harmony
+     Derive axes like this from color / imagery Trend Scan entries in 04_Sources.md. -->
+
+### Axis: TRD-V01 — Visual Warmth & Color Harmony
 
-- axis_id: TRD-01
-- axis_name: [e.g., Progressive Disclosure]
+- axis_id: TRD-V01
+- axis_name: Visual Warmth & Color Harmony
 - layer: trend-derived
-- origin: [research source / industry trend]
-- intent: [what this axis measures]
-- why_it_matters: [business/user impact]
+- visual_category: true
+- origin: Color and imagery trend scan entries identifying warmth-dominant palettes in the competitor set
+- intent: Measures whether the product's color palette conveys appropriate warmth and emotional resonance relative to current visual trends
+- why_it_matters: Color harmony directly impacts brand trust and perceived quality; misaligned warmth signals confuse users about product positioning
 - score_scale: 1-5
 - score_anchors:
-  - low: [1 — description of poor performance]
-  - mid: [3 — description of acceptable performance]
-  - high: [5 — description of excellent performance]
+  - low: 1 — Accent/background pair falls below 3:1 contrast or uses more than 3 conflicting hue families on one screen
+  - mid: 3 — Primary palette keeps a consistent 2-hue system and semantic colors stay within one temperature family
+  - high: 5 — Palette maintains semantic consistency across screens with 4.5:1 contrast and no off-brand hue drift
 - positive_signals:
-  - [signal that indicates good performance]
+  - Accent hue and background hue share a harmonious temperature relationship
+  - Semantic colors (success, warning, error) do not break the palette's tonal identity
 - negative_signals:
-  - [signal that indicates poor performance]
+  - Warm accent on a cool-dominant background without intentional contrast rationale
+  - Multiple conflicting temperature signals on the same screen
 - anti_patterns:
-  - [anti-pattern to avoid]
-- evidence_required: [what evidence must be gathered]
-- weight: [e.g., 0.15]
-- minimum_floor: [minimum acceptable score]
+  - Copying a competitor's palette verbatim without evaluating fit
+- evidence_required: Screenshot comparison of primary screen against 3 archetype references from brand catalog
+- weight: 0.20
+- minimum_floor: 2
 - source_refs:
-  - [research source with freshness_date and confidence]
+  - [SRC-ID of color Trend Scan entry — replace with actual source_id from 04_Sources.md]
+  - [SRC-ID of imagery Trend Scan entry if applicable]
+- goal_refs:
+  - [project goal this axis supports, e.g., REQ-0010]
+- review_questions:
+  - Does the color palette feel intentionally warm or cool relative to the selected brand archetype?
+  - Are there any unintentional temperature conflicts between primary and secondary colors?
+
+<!-- VISUAL AXIS EXAMPLE 2: Typographic Legibility & Trend Alignment
+     Derive axes like this from typography Trend Scan entries in 04_Sources.md. -->
+
+### Axis: TRD-V02 — Typographic Legibility & Trend Alignment
+
+- axis_id: TRD-V02
+- axis_name: Typographic Legibility & Trend Alignment
+- layer: trend-derived
+- visual_category: true
+- origin: Typography trend scan entries from 04_Sources.md capturing current typeface conventions
+- intent: Measures whether the product's typeface choices meet legibility standards while reflecting contemporary typographic trends
+- why_it_matters: Poor legibility harms conversion and trust; typographic misalignment signals a dated or unpolished product
+- score_scale: 1-5
+- score_anchors:
+  - low: 1 — Body text drops below 14px or fails WCAG AA contrast on primary routes
+  - mid: 3 — Body text stays at 16px with a consistent heading/body pairing on core screens
+  - high: 5 — Body text remains 16px+, uses a 1.25 modular ratio, and passes WCAG AA across all defined states
+- positive_signals:
+  - Typeface pairing (heading + body) is harmonious with the selected brand archetype
+  - Base font size 16px or larger on body text
+- negative_signals:
+  - Light-weight type on low-contrast background
+  - More than 3 font weights in active use on a single screen
+- anti_patterns:
+  - Using display fonts at body sizes
+  - Mixing incompatible style epochs (e.g., humanist + mechanical geometric)
+- evidence_required: Rendered type specimen at H1 / H2 / Body / Caption scale with contrast ratio measurements
+- weight: 0.15
+- minimum_floor: 2
+- source_refs:
+  - [SRC-ID of typography Trend Scan entry — replace with actual source_id from 04_Sources.md]
 - goal_refs:
   - [project goal this axis supports]
 - review_questions:
-  - [question for reviewer]
+  - Does the typeface pairing match the brand archetype aesthetic_properties for typography?
+  - Does body text pass WCAG AA contrast at all defined color/background combinations?
 
-### Axis: [TRD-02]
+<!-- Add additional TRD-XX axes below following the same schema.
+     For non-visual axes, omit the `visual_category: true` field or set it to false. -->
 
-<!-- Repeat the schema above for each trend-derived axis -->
+### Axis: [TRD-03]
 
-- axis_id: TRD-02
+<!-- Repeat the schema above for each additional trend-derived axis -->
+
+- axis_id: TRD-03
 - axis_name: [axis name]
 - layer: trend-derived
 - origin: [source]
@@ -48,9 +110,9 @@
 - why_it_matters: [impact]
 - score_scale: 1-5
 - score_anchors:
-  - low: [1 — poor]
-  - mid: [3 — acceptable]
-  - high: [5 — excellent]
+  - low: [1 — poor with a measurable quantitative proxy]
+  - mid: [3 — acceptable with a measurable quantitative proxy]
+  - high: [5 — excellent with a measurable quantitative proxy]
 - positive_signals:
   - [signal]
 - negative_signals:
@@ -61,7 +123,7 @@
 - weight: [weight]
 - minimum_floor: [floor]
 - source_refs:
-  - [ref]
+  - [SRC-ID from 04_Sources.md Source Registry]
 - goal_refs:
   - [ref]
 - review_questions:

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/uiux/23_design_eval_aggregate.md

@@ -39,3 +39,15 @@ This file defines how scores from invariant, trend-derived, and product-specific
 - Product-specific axes: `22_design_eval_product_specific.md`
 - Dynamic overrides (optional): `24_design_eval_dynamic_overrides.md`
 - Option comparison: `30_option_comparison.md`
+
+## Score Scope Limitation
+
+**IMPORTANT**: Scores produced by this aggregate evaluation measure **design direction quality** — i.e., how well each design option satisfies the evaluation criteria for option comparison and selection.
+
+These scores are **NOT** implementation quality scores. When the selected design direction proceeds to `/qfai-prototyping` in full-harness mode:
+
+- Prototyping evaluates **implementation fidelity** against the selected anchor.
+- Prototyping uses its own scoring criteria (calibration baselines, dimension weights).
+- Discussion aggregate scores MUST NOT be copied into `fullHarness.scoringTrace`.
+
+The boundary is: discussion scores inform the **what** (which direction); prototyping scores measure the **how well** (implementation quality).

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/uiux/40_screen_contracts.md

@@ -32,7 +32,7 @@ Draft interaction contracts for key screens using the strong screen contract sch
 - notes_for_verify: [notes for verification/testing]
 - notes_for_reviewer: [any additional context for the reviewer]
 
-<!-- Nested list format is canonical for primary_tasks, secondary_tasks, required_states, transitions, observable_outcomes. Inline CSV is accepted for backward compatibility. -->
+<!-- Nested list format is canonical for primary_tasks, secondary_tasks, required_states, transitions, observable_outcomes. -->
 
 > **Note:** `required_states` primary truth lives in this file. Each screen's state set is authoritative here.
 > **Note:** `secondary_tasks` documents non-primary user workflows available on the screen.

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/uiux/50_review_input_bundle.md

@@ -26,11 +26,13 @@ Consolidate all sidecar artifacts into a review-ready bundle for design reviewer
 - Required trend categories are all present and complete.
 - Stale / overused AI slop patterns are explicitly avoided.
 - Trend research is translated into scoring, comparison, and selected anchor decisions.
+- Scoring-ready axes use canonical fields: `origin`, `layer`, `source_refs`, `goal_refs`, `evidence_required`, `review_questions`.
 
 ## Review Checklist
 
 - [ ] Strategy aligns with surface type and project constraints
 - [ ] Trend categories are complete and translated into local design decisions
 - [ ] Competitive references include adopted_points, rejected_points, and local_translation
+- [ ] Scoring-ready axes expose canonical fields including origin/source_refs/goal_refs/evidence_required/review_questions
 - [ ] Selected anchor clearly documents rationale and downstream implications
 - [ ] Screen contracts cover all required states