qfai 1.8.1 → 1.8.2

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/uiux/30_exploration_brief.md

@@ -0,0 +1,29 @@
+# 30 Exploration Brief
+
+## Product Intent
+
+- What the product should feel like:
+- What users should immediately understand:
+
+## Must-preserve Interactions
+
+- Primary task:
+- Secondary task:
+- Critical state changes:
+
+## Brand Signals
+
+- Desired tone:
+- Desired visual character:
+- Must-avoid brand signals:
+
+## Differentiation Targets
+
+- How this surface should avoid generic layouts:
+- Where deliberate originality should show up:
+
+## Implementation Constraints
+
+- Technical constraints:
+- Accessibility constraints:
+- Operational constraints:

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/uiux/31_reference_pool.md

@@ -0,0 +1,13 @@
+# 31 Reference Pool
+
+## Exploration References
+
+| Ref     | Type    | Why it matters | Adopted points | Rejected points | Local translation |
+| ------- | ------- | -------------- | -------------- | --------------- | ----------------- |
+| REF-001 | Product | [why]          | [adopted]      | [rejected]      | [translation]     |
+
+## Design Guideline Research
+
+| Ref    | Guideline   | Rule refs   | Why it matters | Local translation |
+| ------ | ----------- | ----------- | -------------- | ----------------- |
+| GL-001 | [guideline] | [rule refs] | [why]          | [translation]     |

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/uiux/32_design_anti_goals.md

@@ -0,0 +1,10 @@
+# 32 Design Anti-goals
+
+## Anti-goals
+
+- Avoid generic library-default dashboards with no product character.
+- Avoid AI-slop patterns such as purple gradients over white cards without product rationale.
+
+## Recurrence Prevention
+
+- If a later iteration drifts toward a rejected direction, log the trigger and explicitly restate why the pattern is banned.

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/uiux/33_exploration_rubric.md

@@ -0,0 +1,27 @@
+# 33 Exploration Rubric
+
+## Design Quality
+
+- What counts as coherent:
+- What breaks coherence:
+
+## Originality
+
+- What counts as deliberate design:
+- What counts as generic or AI-slop:
+
+## Craft
+
+- Typography, spacing, color, and contrast competence:
+
+## Functionality
+
+- Whether users can understand and complete the core task:
+
+## Accessibility Risk
+
+- Which issues are hard fails:
+
+## Implementation Plausibility
+
+- What level of complexity is acceptable for the current slice:

package/assets/init/.qfai/assistant/skills/qfai-discussion/templates/uiux/34_evaluator_calibration.md

@@ -0,0 +1,17 @@
+# 34 Evaluator Calibration
+
+## Good Critique
+
+- Example of a skeptical but actionable critique:
+
+## Too Lenient
+
+- Example of praise that should be rejected because it ignores obvious blandness or usability issues:
+
+## Blandness Fail
+
+- Example of a design that is technically competent but too generic to pass:
+
+## Originality Fail
+
+- Example of a design that copies defaults without deliberate product-specific choices:

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

@@ -6,33 +6,27 @@ Consolidate all sidecar artifacts into a review-ready bundle for design reviewer
 
 ## Bundle Contents
 
-| Artifact                   | Path                                       | Status                    |
-| -------------------------- | ------------------------------------------ | ------------------------- |
-| Strategy                   | `uiux/10_implementation_strategy.md`       | [draft/reviewed/approved] |
-| Taste interview            | `uiux/11_design_taste_interview.md`        | [draft/reviewed/approved] |
-| Trend scan                 | `04_Sources.md#Trend Scan`                 | [draft/reviewed/approved] |
-| Invariant layer            | `uiux/20_design_eval_invariant.md`         | [draft/reviewed/approved] |
-| Trend-derived layer        | `uiux/21_design_eval_trend_derived.md`     | [draft/reviewed/approved] |
-| Product-specific layer     | `uiux/22_design_eval_product_specific.md`  | [draft/reviewed/approved] |
-| Aggregate layer            | `uiux/23_design_eval_aggregate.md`         | [draft/reviewed/approved] |
-| Dynamic overrides          | `uiux/24_design_eval_dynamic_overrides.md` | [optional]                |
-| Option comparison          | `uiux/30_option_comparison.md`             | [draft/reviewed/approved] |
-| Selected anchor            | `uiux/31_selected_anchor_screen.md`        | [draft/reviewed/approved] |
-| Screen contracts           | `uiux/40_screen_contracts.md`              | [draft/reviewed/approved] |
-| Prototyping recommendation | `../prototyping.yaml`                      | [draft/reviewed/approved] |
+| Artifact                   | Path                               | Status                    |
+| -------------------------- | ---------------------------------- | ------------------------- |
+| Exploration brief          | `uiux/30_exploration_brief.md`     | [draft/reviewed/approved] |
+| Reference pool             | `uiux/31_reference_pool.md`        | [draft/reviewed/approved] |
+| Design anti-goals          | `uiux/32_design_anti_goals.md`     | [draft/reviewed/approved] |
+| Exploration rubric         | `uiux/33_exploration_rubric.md`    | [draft/reviewed/approved] |
+| Evaluator calibration      | `uiux/34_evaluator_calibration.md` | [draft/reviewed/approved] |
+| Screen contracts           | `uiux/40_screen_contracts.md`      | [draft/reviewed/approved] |
+| Prototyping recommendation | `../prototyping.yaml`              | [draft/reviewed/approved] |
 
 ## Trend-derived review focus
 
-- Required trend categories are all present and complete.
+- Required references 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`.
+- Reference research is translated into exploration and evaluator calibration inputs.
+- Later iterations are not automatically preferred over stronger middle iterations.
 
 ## 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
+- [ ] Exploration brief aligns with surface type and project constraints
+- [ ] Reference pool is complete and translated into local design decisions
+- [ ] Evaluator calibration includes skeptical critique examples
+- [ ] Best-of-history handling is explicit
 - [ ] Screen contracts cover all required states

package/assets/init/.qfai/assistant/skills/qfai-implement/SKILL.md

@@ -77,8 +77,11 @@ Execute the TDD micro-cycle for each pending item in `test-list.md`, transitioni
 - Review rendered output, screenshot evidence, or HTML output before closing any UI-affecting item.
 - Read spec + contract inputs first whenever implementation touches UI or critique-driven behavior.
 - Read order: `01_Spec.md` → `03_Acceptance-Criteria.md` → `05_Examples.md` →
-  `.qfai/contracts/design/anchor-selection.yaml` → `.qfai/contracts/design/evaluation-axes.yaml` →
-  `.qfai/contracts/design/design-system.yaml` → `.qfai/contracts/ui/*.yaml` →
+  `.qfai/contracts/design/exploration-brief.yaml` →
+  `.qfai/contracts/design/anchor-selection.yaml` (legacy alias, when present) →
+  `.qfai/contracts/design/evaluation-axes.yaml` (legacy alias, when present) →
+  `.qfai/contracts/design/evaluation-rubric.yaml` → `.qfai/contracts/design/evaluator-calibration.yaml` →
+  `.qfai/contracts/design/selected-direction.yaml` → `.qfai/contracts/design/design-system.yaml` → `.qfai/contracts/ui/*.yaml` →
   optional design tokens → optional fallback mock → mermaid flows.
 - If code intent and rendered output diverge, treat the rendered/HTML result as the blocking review input and reconcile before DONE.
 

package/assets/init/.qfai/assistant/skills/qfai-prototyping/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: qfai-prototyping
-title: QFAI Prototyping (Skill-Orchestrated)
-description: "Build a contract-aligned UI prototype, run agent-led visual evaluation, and gate completion through validate/verify."
+title: QFAI Prototyping (Exploration-First Harness)
+description: "Run a planner/generator/evaluator UI harness with a 5→3→2→1 direction funnel, breakthrough detection, and final design-system extraction."
 argument-hint: "[--auto]"
 allowed-tools: [Read, Glob, Write, TodoWrite, Task, Bash]
 roles:
@@ -39,14 +39,13 @@ Do not rely on a CLI entrypoint or package runtime loop.
 - Supported UI prototyping surfaces are `web`, `mobile`, `desktop`, and `mixed`.
 - `cli`, API-only, backend-only, and `ui_bearing: false` classifications are not prototyping execution targets.
 - `cli` is not supported and is not an execution target for prototyping.
-- Canonical screen contracts in `.qfai/contracts/ui/*.yaml` are mandatory.
-- Evaluation is performed by sub-agents; machine checks are limited to schema/evidence validation.
-- Evaluation reviewer findings must be fixed or explicitly dispositioned before PASS.
-- Shared evidence vocabulary includes `render.json` and `browser-qa.json` alongside screenshot and HTML evidence.
+- Evaluation is performed by sub-agents; machine checks are limited to schema/evidence validation and breakthrough trigger detection.
+- Shared evidence vocabulary includes `render.json`, `browser-qa.json`, `prototyping.json`, and `breakthrough.json`.
+- static-first evidence capture remains mandatory even when interactive review is used.
 
 ## Goal
 
-Build the minimum runnable slice for all specs and produce reviewable screenshot/HTML evidence for every declared screen.
+Generate multiple design directions, converge on a winner, extract the selected direction and final design system, and keep the winner open to breakthrough pivots during later polish iterations.
 
 ## Surface / Mode
 
@@ -62,8 +61,11 @@ Read and follow these references before execution:
 - `.qfai/assistant/skills/qfai-prototyping/references/iteration-cycle.md`
 - `.qfai/assistant/skills/qfai-prototyping/references/l1-review-guide.md`
 - `.qfai/assistant/skills/qfai-prototyping/references/l2-review-guide.md`
+- `.qfai/contracts/design/anchor-selection.yaml` when legacy validator slices are exercised
+- `.qfai/contracts/design/evaluation-axes.yaml` when legacy validator slices are exercised
 - `.qfai/assistant/skills/qfai-prototyping/references/design-system-compliance.md`
 - `.qfai/assistant/skills/qfai-prototyping/references/reviewer-gate.md`
+- `.qfai/assistant/steering/test-layers.md`
 
 ## Delegation Scope Table
 
@@ -71,12 +73,13 @@ All sub-agent delegation in this skill MUST follow the category-to-role mapping
 Assigning a task to a role not listed for the category is a violation and MUST be flagged.
 Evaluation scoring and screenshot capture must use only the allowed roles below.
 
-| Category           | Allowed Role(s)                                        |
-| ------------------ | ------------------------------------------------------ |
-| UI implementation  | frontend-engineer, product-experience-architect        |
-| Screenshot capture | devops-ci-engineer                                     |
-| Evaluation review  | product-surface-reviewer, product-experience-architect |
-| Build              | devops-ci-engineer, backend-engineer                   |
+| Category              | Allowed Role(s)                                        |
+| --------------------- | ------------------------------------------------------ |
+| UI implementation     | frontend-engineer, product-experience-architect        |
+| Screenshot capture    | devops-ci-engineer                                     |
+| Evaluation scoring    | product-surface-reviewer, product-experience-architect |
+| Build                 | devops-ci-engineer, backend-engineer                   |
+| Breakthrough planning | product-experience-architect, frontend-engineer        |
 
 Any delegation map entry that assigns a category to an undefined or unlisted role MUST produce a violation finding naming the undefined role and the category.
 
@@ -89,7 +92,8 @@ Before any code is written, create an execution plan record in the work evidence
 Required fields:
 
 - `targetIterations`: integer; minimum 2
-- `evaluationAxesSource`: ref to `.qfai/contracts/design/evaluation-axes.yaml`
+- `funnelPolicy`: `5->3->2->1`
+- `evaluationAxesSource`: ref to `.qfai/contracts/design/evaluation-rubric.yaml`
 - `delegationMap`: category-to-role assignments per Delegation Scope Table
 - `plannedAt`: ISO-8601 timestamp
 
@@ -99,19 +103,27 @@ Read the downstream-ready spec/contract inputs and verify:
 
 - `.qfai/specs/<spec-id>/01_Spec.md`
 - `.qfai/specs/<spec-id>/03_Acceptance-Criteria.md`
-- `.qfai/contracts/design/evaluation-axes.yaml`
-- `.qfai/contracts/design/anchor-selection.yaml`
-- `.qfai/contracts/design/design-system.yaml` when required by the spec
+- `.qfai/contracts/design/exploration-brief.yaml`
+- `.qfai/contracts/design/evaluation-rubric.yaml`
+- `.qfai/contracts/design/evaluator-calibration.yaml`
+- `.qfai/contracts/design/anchor-selection.yaml` when legacy validator slices are exercised
+- `.qfai/contracts/design/evaluation-axes.yaml` when legacy validator slices are exercised
+- `.qfai/contracts/design/selected-direction.yaml` when already created
+- `.qfai/contracts/design/design-system.yaml` when already created
 - `.qfai/contracts/ui/*.yaml`
 
 Read order:
 
 1. `.qfai/specs/<spec-id>/01_Spec.md`
 2. `.qfai/specs/<spec-id>/03_Acceptance-Criteria.md`
-3. `.qfai/contracts/design/anchor-selection.yaml`
-4. `.qfai/contracts/design/evaluation-axes.yaml`
-5. `.qfai/contracts/design/design-system.yaml`
-6. `.qfai/contracts/ui/*.yaml`
+3. `.qfai/contracts/design/exploration-brief.yaml`
+4. `.qfai/contracts/design/evaluation-rubric.yaml`
+5. `.qfai/contracts/design/evaluator-calibration.yaml`
+6. `.qfai/contracts/design/anchor-selection.yaml` (legacy validator alias, when present)
+7. `.qfai/contracts/design/evaluation-axes.yaml` (legacy validator alias, when present)
+8. `.qfai/contracts/design/selected-direction.yaml`
+9. `.qfai/contracts/design/design-system.yaml`
+10. `.qfai/contracts/ui/*.yaml`
 
 ### Step 2 — Verify Execution Preconditions
 
@@ -120,16 +132,16 @@ Confirm all of the following before any evaluation:
 - classification is UI-bearing
 - surface is `web`, `mobile`, `desktop`, or `mixed`
 - every declared screen has a stable `screen-id`
-- the design evaluation contract satisfies the required schema
-- the design system checklist is available when required
+- the exploration brief, evaluation rubric, and evaluator calibration contracts satisfy the required schema
 
-### Step 3 — Implement the Minimum Runnable Slice
+### Step 3 — Generate Divergent Directions
 
-Implement the smallest UI slice that covers all declared screens and primary interactions.
+Generate 5 clearly distinct design directions before selecting a winner.
+Do not begin with a single incumbent direction.
 
 ### Step 4 — Capture Mandatory Evidence
 
-For every declared screen:
+For every declared screen and every active direction:
 
 - capture one screenshot and store it at the canonical screenshot path
 - capture one HTML snapshot and store it at the canonical HTML path
@@ -141,57 +153,52 @@ Launch evaluation reviewer sub-agents with the full context bundle:
 
 - screenshots from Step 4
 - HTML snapshots from Step 4
-- `axisDefs` from `.qfai/contracts/design/evaluation-axes.yaml`
+- `axisDefs` from `.qfai/contracts/design/evaluation-rubric.yaml`
 - `previousScore` from the prior iteration (`null` for iteration 1)
 - `designSystemChecklist` from `.qfai/contracts/design/design-system.yaml`
 
-If any required input is missing, stop the evaluation and classify the screen as `0` points with rerun required.
+### Step 6 — Direction Funnel
 
-### Step 6 — Aggregate Findings
+Run the mandatory convergence funnel:
 
-Aggregate reviewer findings and classify them as:
+- 5 directions -> top 3
+- top 3 remixed -> top 2
+- top 2 -> selected winner 1
 
-- blocking
-- immediate-fix
-- revise
-- manual-review
+### Step 7 — Extract Winner Contracts
 
-### Step 7 — Fix and Re-capture
+After the first winner is selected:
 
-Apply fixes per finding disposition, then re-capture screenshot and HTML evidence for every changed screen.
-Do not close a finding without fresh evidence.
+- write `.qfai/contracts/design/selected-direction.yaml`
+- extract `.qfai/contracts/design/design-system.yaml`
 
-### Step 8 — Re-evaluate
+### Step 8 — Polish the Winner
 
-Repeat Steps 4–7 until:
-
-- at least 2 iterations have completed
-- all declared screens have screenshot + HTML evidence
-- blocking findings are closed or dispositioned
-- validate can pass on required schema/evidence gates
+Iterate on the selected winner with normal critique/rework loops.
+Do not assume the latest iteration is automatically best; keep best-of-history in evidence.
 
 ## Iteration Gate
 
-- minimum 2 iterations are required before phase transition to validation or review.
-- if the iteration gate is not satisfied, phase transition is blocked.
-- terminationCondition cannot bypass the minimum 2 iterations rule.
+- Minimum 2 iterations are required before any terminal phase transition is allowed.
+- Do not mark the run as converged or complete after a single iteration.
+- Any phase transition to completion must pass through the iteration gate and reviewer gate.
+
+### Step 9 — Breakthrough Detection
 
-## Full-harness
+After each polish iteration, run the mechanical breakthrough detector.
+If `allItemsPass95` is false and score improvement is below the configured plateau threshold and code change is below the configured diff threshold, trigger breakthrough branching.
 
-- `full-harness` applies only after explicit escalation from the default `standard` path.
-- `full-harness` carries review-heavy obligations and stricter evidence checks.
+### Step 10 — Breakthrough Branch Loop
 
-## Obligation matrix
+When breakthrough is triggered:
 
-| surface / mode          | obligation profile                  |
-| ----------------------- | ----------------------------------- |
-| web / default route     | static-first obligations (standard) |
-| web / full-harness      | review-heavy obligations            |
-| mobile / default route  | static-first obligations (standard) |
-| desktop / default route | static-first obligations (standard) |
-| mixed / full-harness    | review-heavy obligations            |
+- generate exactly 2 branch directions
+- compare incumbent + 2 branches
+- replace the mainline if a branch wins
+- refresh selected-direction/design-system if the winner changes
+- record the decision in `.qfai/evidence/breakthrough.json`
 
-### Step 9 — Validate and Verify
+### Step 11 — Validate and Verify
 
 - Run `qfai validate --fail-on error`.
 - Route `/qfai-verify` or its equivalent gate workflow for final quality approval.
@@ -211,26 +218,29 @@ When launching any evaluation reviewer sub-agent, all 5 elements MUST be present
 
 Each iteration evaluation MUST score all 6 visual categories:
 
-1. Color
-2. Typography
-3. Spacing
-4. Border radius
-5. Shadow
-6. Do's&Don'ts
+1. Design quality
+2. Originality
+3. Craft
+4. Functionality
+5. Accessibility risk
+6. Implementation plausibility
 
 ### Reviewer Gate (MUST)
 
 Reviewer checks are defined in:
 
 - `.qfai/assistant/skills/qfai-prototyping/references/reviewer-gate.md`
+- `.qfai/assistant/steering/test-layers.md`
 
 Minimum reviewer responsibilities:
 
+- enforce the Drift Protocol before approving a completion transition
 - verify mandatory screenshot/HTML evidence exists for every declared screen
-- verify 3-layer evaluation references were used
+- verify exploration brief, evaluation rubric, and evaluator calibration were used
 - verify missing evidence caused rerun rather than waiver
 - verify `qfai validate --fail-on error` completed successfully
-- verify Drift Protocol compliance and alignment with `.qfai/assistant/steering/test-layers.md`
+- verify breakthrough trigger evidence is present
+- verify best-of-history handling is documented
 - treat score/volume heuristics as signals, not gates
 - return `Result: PASS | REVISE`
 
@@ -265,6 +275,9 @@ Prototyping-specific additions:
 
 - all specs are covered
 - all declared screens have screenshot + HTML evidence
+- `selected-direction.yaml` exists
+- `design-system.yaml` exists
+- `breakthrough.json` exists
 - `qfai validate --fail-on error` passes
 - reviewer returns `PASS`
 
@@ -274,6 +287,8 @@ Prototyping-specific additions:
 - Every declared screen has screenshot evidence.
 - Every declared screen has HTML evidence.
 - Missing evidence triggered rerun instead of waiver.
+- Direction funnel `5->3->2->1` completed.
+- Breakthrough detector ran after polish iterations.
 - Reviewer returned PASS; otherwise status is REVISE.
 
 ## Completion Message & Next Actions (MUST)

package/assets/init/.qfai/assistant/skills/qfai-sdd/SKILL.md

@@ -223,9 +223,11 @@ Create or update layered SDD artifacts in one run so downstream execution phases
 - Target `spec-XXXX/01..10` layered files
 - Updated contracts under `.qfai/contracts/**`
 - UI-bearing normalized contracts:
+  - `.qfai/contracts/design/exploration-brief.yaml`
+  - `.qfai/contracts/design/evaluation-rubric.yaml`
+  - `.qfai/contracts/design/evaluator-calibration.yaml`
+  - `.qfai/contracts/design/selected-direction.yaml`
   - `.qfai/contracts/design/design-system.yaml`
-  - `.qfai/contracts/design/evaluation-axes.yaml`
-  - `.qfai/contracts/design/anchor-selection.yaml`
   - `.qfai/contracts/ui/*.yaml`
 - `.qfai/report/preflight_summary.md`
 - Evidence file: `.qfai/evidence/sdd-spec-XXXX.md`

package/assets/init/.qfai/assistant/skills/qfai-sdd/templates/contracts/design-system.sample.yaml

@@ -16,3 +16,7 @@ checklist:
   dos_and_donts:
     - do: maintain clear hierarchy on the primary screen
     - dont: mix multiple accent palettes on one screen
+  component_tone:
+    - keep components visibly related to the chosen direction
+  motion_rules:
+    - use motion to clarify hierarchy and state change

package/assets/init/.qfai/assistant/skills/qfai-sdd/templates/contracts/evaluation-rubric.sample.yaml

@@ -0,0 +1,16 @@
+# Downstream evaluation rubric generated by /qfai-sdd
+axes:
+  - id: design-quality
+    weight: 3
+  - id: originality
+    weight: 3
+  - id: craft
+    weight: 1
+  - id: functionality
+    weight: 1
+hard_floors:
+  - functionality
+  - accessibility-risk
+weighted_axes:
+  - design-quality
+  - originality

package/assets/init/.qfai/assistant/skills/qfai-sdd/templates/contracts/evaluator-calibration.sample.yaml

@@ -0,0 +1,9 @@
+# Downstream evaluator calibration generated by /qfai-sdd
+good_critique_examples:
+  - Skeptical, specific, and actionable feedback
+too_lenient_examples:
+  - Praise that ignores blandness
+blandness_fail_examples:
+  - Technically correct but generic
+originality_fail_examples:
+  - Library defaults with no product-specific decisions

package/assets/init/.qfai/assistant/skills/qfai-sdd/templates/contracts/exploration-brief.sample.yaml

@@ -0,0 +1,10 @@
+# Downstream exploration brief generated by /qfai-sdd
+product_intent: Create a deliberate, non-generic product surface.
+target_users:
+  - Primary end users
+must_preserve_interactions:
+  - Primary task remains obvious
+brand_signals:
+  - Confident
+differentiation_targets:
+  - Avoid generic dashboard defaults

package/assets/init/.qfai/assistant/skills/qfai-sdd/templates/contracts/selected-direction.sample.yaml

@@ -0,0 +1,7 @@
+# Downstream selected direction generated by /qfai-prototyping
+chosen_direction_id: DIR-001
+winning_rationale: Strongest balance of originality and clarity.
+carry_forward_rules:
+  - Preserve hierarchy strategy
+rejected_summary:
+  - DIR-002: too generic

package/assets/init/.qfai/assistant/skills/qfai-verify/SKILL.md

@@ -99,6 +99,7 @@ Use the shared schema.
   - declared screens have mandatory screenshot and HTML evidence under `.qfai/evidence/prototyping/`;
   - Drift Protocol enforced;
   - test-layer policy enforced against `test-layers.md`.
+  - gate counts and ratios are signals, not gates.
 - Route specialist reviewers from `.qfai/assistant/steering/agent-routing.yml`.
 - Default verify review set:
   - `qa-gatekeeper`

package/assets/init/.qfai/assistant/steering/agent-catalog.yml

@@ -65,7 +65,7 @@ agents:
   - id: frontend-engineer
     kind: worker
     domain: frontend
-    mission: Implement frontend behavior aligned with selected anchor, strategy, screen contracts, and product-surface decisions.
+    mission: Implement frontend behavior aligned with selected direction, finalized design system, screen contracts, and product-surface decisions.
     owned_artifacts: [ui-implementation, surface-evidence]
     tool_profile: frontend
     permission_profile: authoring

package/assets/init/.qfai/assistant/steering/ui-definition-protocol.md

@@ -8,11 +8,11 @@ spec-0013 (CAP-0013) で定義された、下流 skill（prototyping / ATDD / TD
 **Primary truth** は step 1 の discussion sidecar artifacts にある。step 2 以降は **存在する場合のみ読む supporting input / fallback** であり、init 直後に未作成でも正常である。
 
 1. **Discussion-side UI/UX Sidecar Artifacts** (`discussion-*/uiux/`) — **primary source of truth**
-   - `30_option_comparison.md` — オプション比較（比較 artifact）
-   - `31_selected_anchor_screen.md` — 選定結果 + selected anchor の SSOT
-   - `10_implementation_strategy.md` — 実装戦略（strict canonical schema）
-   - `11_design_taste_interview.md` — デザインテイストインタビュー
-   - `20-24` — 3-layer 評価ファミリー（**invariant / trend-derived / product-specific / aggregate / dynamic overrides** の 5 sidecar のみ。`20` は invariant axes, **Trend Scan は sidecar ではなく `04_Sources.md#Trend Scan` が正本**。旧 `uiux/20_trend_scan.md` は廃止。）
+   - `30_exploration_brief.md` — 探索ブリーフ（product intent / brand signals / must-preserve interactions）
+   - `31_reference_pool.md` — 参照プール（reference registry + local translation）
+   - `32_design_anti_goals.md` — 避けるべきデザイン方向
+   - `33_exploration_rubric.md` — 探索評価基準
+   - `34_evaluator_calibration.md` — evaluator 較正用 examples
    - `40_screen_contracts.md` — スクリーンコントラクト（strong schema）
    - `50_review_input_bundle.md` — レビュー入力バンドル
 
@@ -47,7 +47,7 @@ spec-0013 (CAP-0013) で定義された、下流 skill（prototyping / ATDD / TD
 
 ## Priority and Override Semantics
 
-- discussion sidecar artifacts が **primary truth**。具体的には (a) `uiux/30_option_comparison.md`（option comparison）、(b) `uiux/31_selected_anchor_screen.md`（selected anchor）、(c) `uiux/10_implementation_strategy.md`（implementation strategy）、(d) `uiux/40_screen_contracts.md`（screen contracts / 強スキーマ）の順で読む。
+- discussion sidecar artifacts が **primary truth**。具体的には (a) `uiux/30_exploration_brief.md`、(b) `uiux/31_reference_pool.md`、(c) `uiux/33_exploration_rubric.md`、(d) `uiux/34_evaluator_calibration.md`、(e) `uiux/40_screen_contracts.md` の順で読む。
 - `.qfai/contracts/ui/` の UI Contracts と Design Token は **存在する場合のみ読む supporting input**（primary truth ではない）。
 - Optional fallback mock はさらに後順位の **fallback**。
 - Design Token の値と HTML Mock の fallback 値が矛盾する場合は warning を発行。

package/assets/init/.qfai/contracts/README.md

@@ -18,7 +18,7 @@ QFAI organizes this directory into four subdirectories:
 .qfai/contracts/
 ├── api/      # OpenAPI YAML (endpoints, request/response)
 ├── db/       # SQL schema contracts (tables, columns, constraints)
-├── design/   # Design system / axes / anchor YAML
+├── design/   # Exploration brief / rubric / selected direction / design system YAML
 └── ui/       # UI contract YAML (screens, elements, user actions)
 ```
 
@@ -42,9 +42,11 @@ QFAI organizes this directory into four subdirectories:
 │   └── db-0001-<slug>.sql
 ├── design/
 │   ├── README.md
+│   ├── exploration-brief.yaml
+│   ├── evaluation-rubric.yaml
+│   ├── evaluator-calibration.yaml
+│   ├── selected-direction.yaml
 │   ├── design-system.yaml
-│   ├── evaluation-axes.yaml
-│   ├── anchor-selection.yaml
 │   └── design-tokens.yaml          (optional)
 └── ui/
     ├── README.md

package/assets/init/.qfai/contracts/design/README.md

@@ -1,8 +1,8 @@
-# contracts/design (Design Execution Inputs)
+# contracts/design (Exploration + Design Execution Inputs)
 
 ## Purpose
 
-Provide the downstream execution truth for design-system and design-evaluation inputs that `/qfai-sdd` normalizes from UI-bearing discussion packs.
+Provide the downstream execution truth for exploration-first prototyping and final design-system extraction that `/qfai-sdd` and `/qfai-prototyping` normalize from UI-bearing discussion packs.
 
 These files are version-managed and may be read directly by `/qfai-prototyping`, `/qfai-implement`, `/qfai-atdd`, and `qfai validate`.
 
@@ -12,20 +12,24 @@ After `qfai init`, this directory contains only this README. This is the normal
 
 The absence of design files is not a defect for non-UI capabilities. For UI-bearing capabilities, missing required design files should be resolved in `/qfai-sdd`.
 
-## When Design Tokens Are Used
+## Typical Exploration-first Files
 
 Typical files:
 
-- `design-system.yaml` — normalized checklist for color, typography, spacing, radius, shadow, and do/don't rules
-- `evaluation-axes.yaml` — normalized invariant / trend-derived / product-specific / aggregate axes
-- `anchor-selection.yaml` — selected anchor and adoption rationale needed by downstream review
+- `exploration-brief.yaml` — machine-readable exploration brief generated from discussion
+- `evaluation-rubric.yaml` — machine-readable evaluator rubric with weighted originality/design criteria
+- `evaluator-calibration.yaml` — evaluator alignment examples and anti-leniency guidance
+- `selected-direction.yaml` — current winning direction, rationale, and carry-forward rules
+- `design-system.yaml` — extracted final design system produced after direction convergence
 - `design-tokens*.yaml` — optional token definitions
 
 ## Expected File Names
 
+- `exploration-brief.yaml`
+- `evaluation-rubric.yaml`
+- `evaluator-calibration.yaml`
+- `selected-direction.yaml`
 - `design-system.yaml`
-- `evaluation-axes.yaml`
-- `anchor-selection.yaml`
 - `design-tokens.yaml`
 - `design-tokens.mobile.yaml`
 
@@ -33,4 +37,4 @@ Typical files:
 
 - **Not** a replacement for specs or UI contracts
 - **Not** an excuse for downstream skills to read discussion-side artifacts directly
-- **Not** limited to optional token files only
+- **Not** a place to finalize a winner before prototyping convergence