qfai 1.7.13 → 1.7.15

package/assets/init/.qfai/assistant/skills/qfai-sdd/references/review-cycle-playbook.md

@@ -0,0 +1,30 @@
+# SDD Review Cycle Playbook
+
+Use this file when you need the detailed review-cycle mechanics for `/qfai-sdd`.
+
+## Inputs
+
+- `.qfai/assistant/steering/agent-routing.yml`
+- `.qfai/assistant/steering/review-profiles.yml`
+- `.qfai/assistant/skills/qfai-sdd/references/rcp_footer.md`
+
+## Review Cycle
+
+1. Select reviewers from routing and profile rules.
+2. Build one review pack for the current cycle only.
+3. Apply the footer SSOT without rewriting it locally.
+4. Collect verdicts.
+5. If any blocking reviewer returns `FAIL`, fix only the affected scope and rerun the failed reviewer plus any reviewer whose scope changed.
+6. Mark the cycle fixed only when all routed blocking reviewers return `PASS`.
+
+## Required Outputs
+
+- `review_request.md`
+- `Rxx_<reviewer>.md`
+- evidence updates showing what changed after each failed cycle
+
+## Guardrails
+
+- Do not self-approve.
+- Do not collapse `PASS` and `FAIL` into informal prose.
+- Do not rerun unrelated reviewers after a localized fix.

package/assets/init/.qfai/assistant/skills/qfai-sdd/references/sdd-execution-playbook.md

@@ -0,0 +1,29 @@
+# SDD Execution Playbook
+
+Use this file for the detailed sequencing rules behind `/qfai-sdd`.
+
+## Preflight
+
+1. Identify the latest discussion-pack.
+2. Stop if required files are missing.
+3. Stop if blocking OQ remain.
+4. Stop if the latest UI-bearing pack is missing valid `prototyping.yaml`.
+
+## Shared-before-Slice Rule
+
+- Contracts-first and Outline are shared work.
+- Slice, Plan, and Delta are target-spec work.
+- In no-argument mode, shared work runs once and per-spec work fans out after shared outputs stabilize.
+
+## Update Policy
+
+- Update existing artifacts in place when the current target already exists.
+- Create new spec artifacts only after approval.
+- Delete only after approval and after recording the rationale.
+
+## Stop Conditions
+
+- Missing or stale `_policies/11_Slice-Policy.md`
+- Missing Contract Index alignment
+- Unresolvable preflight blockers
+- Validate errors that point to unresolved source-layer gaps

package/assets/init/.qfai/assistant/skills/qfai-sdd/references/sdd-phase-checklists.md

@@ -0,0 +1,37 @@
+# SDD Phase Checklists
+
+Use these checklists as the detailed operational guide for `/qfai-sdd`.
+
+## Phase 0: Contracts-first
+
+- Confirm impacted contract kinds: API, DB, UI.
+- Create or update declared contract files.
+- Ensure each contract has `QFAI-CONTRACT-ID`.
+- Refresh `_policies/05_Contracts.md` Contract Index.
+- Stop if an indexed contract file is missing.
+
+## Phase 1: Outline
+
+- Refresh `_policies/01..11`.
+- Keep Mermaid inside fenced code blocks only.
+- Mirror every unresolved shared issue into `_policies/09_Open-questions.md`.
+- Record `0 items` explicitly when decisions or delta are empty.
+
+## Phase 2: Slice
+
+- Create or update `spec-XXXX/01..08`.
+- Check `US -> AC -> BR -> EX -> TC`.
+- Ensure `01_Spec.md` remains the execution Primary SSOT.
+- Stop if slice gate fails.
+
+## Phase 3: Plan finalize
+
+- Create or update `spec-XXXX/10_Plan.md`.
+- Keep the file How-only.
+- Do not finalize the plan before at least one slice gate passes.
+
+## Phase 4: Delta update
+
+- Update `09_delta.md` or `*_delta.md`.
+- Record adoption and rejection rationale.
+- When rejections exist, include `DO NOT` and `Temptation`.

package/assets/init/.qfai/assistant/skills/qfai-sdd/references/sdd-quality-gate.md

@@ -0,0 +1,32 @@
+# SDD Quality Gate
+
+Use this file for the full quality gate checklist behind `/qfai-sdd`.
+
+## Structural Checks
+
+- Required `_policies` files exist.
+- Required `spec-XXXX` files exist.
+- `_policies/11_Slice-Policy.md` matches the current repo slice model.
+- `_policies/04_Business-Flow.md` contains Mermaid `flowchart` or `sequenceDiagram`.
+- `10_Plan.md` exists and remains How-only.
+- `specs/plan.md` does not exist.
+
+## Traceability Checks
+
+- `US -> AC -> BR -> EX -> TC` edges exist.
+- `05_Examples.md` includes `EX-ID` and `BR-Ref`.
+- `06_Test-Cases.md` includes `TC-ID`, `EX-Ref`, `AC-Refs`, and `Type`.
+- Error or boundary coverage is present, not only normal-path coverage.
+
+## Validation Checks
+
+- `qfai validate --fail-on error --format github | tee .qfai/report/validate.log`
+- `error=0`
+- `.qfai/report/specs-coverage/spec-*.md` reviewed
+- Density-smell warnings triaged
+
+## Evidence Checks
+
+- Evidence file exists.
+- Work Orders Summary exists.
+- Reviewer result exists.

package/assets/init/.qfai/assistant/skills/qfai-sdd/references/spec-traceability-rules.md

@@ -0,0 +1,33 @@
+# Spec Traceability Rules
+
+Use this file when working on traceability-heavy parts of `/qfai-sdd`.
+
+## Required Edge Model (Conceptual Decomposition)
+
+Conceptual decomposition / realization hierarchy (how specs are _authored_, not how
+IDs reference each other):
+
+- `US` conceptually decomposes into `AC`
+- `AC` conceptually decomposes into `BR`
+- `BR` is conceptually concretized by `EX`
+- `EX` is conceptually realized by `TC`
+
+## Reference Direction (`Refs` ID fields)
+
+ID reference direction (the value of `Refs:` columns) must be lower-to-upper only:
+
+- Upper-to-lower ID references are forbidden (`US.Refs: AC-0001` is not allowed).
+- Lower-to-upper ID references are allowed (`AC.Refs: US-0001` is the canonical form).
+- The conceptual hierarchy above describes authoring direction; the `Refs` direction
+  is the _inverse_ so downstream specs cite upstream IDs, never the other way round.
+
+## Depth Expectations
+
+- `BR` captures decision-level rules.
+- `EX` demonstrates how `BR` behaves.
+- `TC` proves `EX` in executable terms.
+
+## When Sparse Coverage Is Intentional
+
+- State the reason explicitly.
+- Record the mitigation or next step in open questions or delta.

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

@@ -30,25 +30,22 @@ QFAI Skill Body (SSOT)
 
 ## User Questions (AskUserQuestion Protocol)
 
-- When a question to the user is needed (e.g., gate failure triage, fix approach confirmation),
-  the agent MUST use AskUserQuestion if the tool is available.
-- When AskUserQuestion supports structured choices (radio/multi-select),
-  the agent MUST prefer structured choices over free-text input.
-- If AskUserQuestion is technically unavailable, present the same question as a normal message
-  with explicit numbered choices.
-  The agent SHOULD preserve structured choice semantics (enumerated options, selection constraints).
-  The reason for unavailability MUST be stated.
+Follow `.qfai/assistant/instructions/shared-skill-operating-baseline.md#user-questions-askuserquestion-protocol`.
+
+Skill-specific examples:
+
+- gate failure triage
+- fix approach confirmation
 
 ## FORMAT SSOT (Mandatory)
 
-- **Before writing or editing any `.qfai/**` artifact\*\*, read and follow the relevant directory README template and sample:
+- Follow `.qfai/assistant/instructions/shared-skill-operating-baseline.md#format-ssot-mandatory`.
+
+- Before writing or editing any `.qfai/**` artifact, read and follow the relevant directory README template and sample:
   - `.qfai/discussion/README.md`
   - `.qfai/specs/README.md`
   - `.qfai/contracts/**/README.md`
   - `.qfai/evidence/README.md`
-- **Do NOT copy** templates/samples into this prompt or into other prompt markdown.
-- The generated artifacts must match the README-defined structure (headings, ordering, table columns).
-- Completion requires a **Format Self-Check** in the evidence: list each artifact and confirm “matches README template”.
 
 ## Inputs Priority (Preflight)
 
@@ -67,36 +64,24 @@ When unsure, read inputs in this order:
 
 ## Sub-agent Delegation (MANDATORY)
 
-This section is mandatory and overrides any conflicting fallback text in this file.
+Follow `.qfai/assistant/instructions/shared-skill-delegation-baseline.md`.
 
 ### Orchestrator Protocol (MUST)
 
-- Orchestrator may only create work orders, delegate tasks, integrate outputs, and present results to the user.
-- Orchestrator MUST NOT generate the primary artifact first draft.
-- Orchestrator MUST NOT serve as Reviewer or skip delegation for convenience.
+- No additional overrides.
 
 ### Capability Probe (MUST)
 
-1. Run one harmless Probe Task (for example: "reply with ok") once at stage start.
-2. If subagents are unavailable, explicitly ask the user for Simulation mode approval.
-3. Without explicit approval, stop the stage and do not continue.
+- No additional overrides.
 
-### Simulation mode (Opt-in only)
+### Delegation Failure (Hard Stop)
 
-- Allowed only when the user explicitly states `Simulation mode allowed`.
-- When used, record both of the following in outputs/evidence:
-  - `Subagents: simulated (reason: <why unavailable>)`
-  - `User approval: <quote or reference>`
+- No additional overrides.
+- Do not simulate roles. If the first required delegation fails, stop the stage and report remediation.
 
 ### Work Orders Summary (MANDATORY evidence)
 
-Every major artifact in this stage MUST include a `## Work Orders Summary` section with this fixed table schema:
-
-| Step | Role (sub-agent) | Task title | Input (refs) | Output (refs) | Status (PASS/REVISE) |
-| ---- | ---------------- | ---------- | ------------ | ------------- | -------------------- |
-| 1    | <role>           | <task>     | <refs>       | <refs>        | PASS/REVISE          |
-
-- `Output (refs)` must point to in-file anchors or relative evidence file paths.
+Use the shared schema.
 
 ### Stage Minimum Roles (MUST)
 
@@ -107,81 +92,36 @@ Every major artifact in this stage MUST include a `## Work Orders Summary` secti
 
 ### Reviewer Gate (MUST)
 
-- Final completion gate MUST be delegated to an independent `completion-reviewer`.
-- Reviewer checks (minimum):
-  - Required roles were delegated (no orchestrator self-authoring).
-  - DoD satisfied (validate gate, test-layer hard gate, evidence, DR-IDs).
-  - Validate gate evidence exists: `qfai validate --fail-on error` completed with `error=0`.
-  - **Drift Protocol enforced**:
-    - No upstream artifact edits were made without an explicit user-approved Change Request.
-    - If upstream changes exist, the correct owner skill was re-run after approval; downstream did not patch upstream directly.
-  - **Test-layer policy enforced**:
-    - E2E/API/Integration coverage aligns with `steering/test-layers.md` and the project’s plan.
-    - Do not use pyramid ratios as a gate; use floors/ratios only as signals. Coverage obligations are the gate.
+- Follow `.qfai/assistant/instructions/shared-skill-delegation-baseline.md#reviewer-gate-baseline`.
+- Reviewer checks:
+  - required roles were delegated;
+  - validate evidence exists: `qfai validate --fail-on error` completed with `error=0`;
+  - Drift Protocol enforced;
+  - test-layer policy enforced against `test-layers.md`.
 - Route specialist reviewers from `.qfai/assistant/steering/agent-routing.yml`.
 - Default verify review set:
   - `qa-gatekeeper`
   - `completion-reviewer`
 - Add `implementation-reviewer` only when code fixes are in scope.
 - Do not declare DONE or handoff until all routed blocking reviewers return `PASS`.
-- Every reviewer MUST provide a concrete alternative or fix proposal when returning FAIL.
 
 ### Work order template (copy/paste)
 
-```text
-Task title: <short>
-Role: <sub-agent role>
-Goal: <what to decide/produce>
-Inputs (refs):
-- <file/section>
-Constraints:
-- must: enforce Drift Protocol (no upstream edits without user approval + CR)
-- must: verify plan/test-layer adherence (`steering/test-layers.md` + plan)
-- must: check `qfai validate --fail-on error` passes with evidence (`error=0`)
-- must: enforce `.qfai/assistant/steering/test-layers.md` hard gates
-- must_not: accept test-volume ratios/floors as a hard gate
-- must_not: accept upstream edits made directly by downstream phase
-Output format:
-- <headings / bullet schema>
-Quality bar:
-- PASS if ...
-- REVISE if ...
-```
+Use the shared template.
 
 ### Reviewer response template
 
-```text
-Result: PASS | REVISE
-Findings:
-- <issue>
-Required fixes:
-- <action>
-Evidence checked:
-- <refs>
-```
-
-## Stage 0 — Steering completion refresh (mandatory)
-
-Before moving forward in this stage, refresh these files:
+Use the shared template.
 
-- `.qfai/assistant/steering/manifest.md`
-- `.qfai/assistant/steering/product.md`
-- `.qfai/assistant/steering/structure.md`
-- `.qfai/assistant/steering/tech.md`
+- Required field: `Status (PASS/REVISE)`.
 
-Rules:
+## Stage 0 — Steering completion refresh (mandatory)
 
-- Detect incomplete content (empty sections, placeholder-only lines, `<...>`, `TBD`, stale facts).
-- Fill what is verifiable from repository evidence (tree, docs, require/spec artifacts, package.json, CI definitions).
-- If something cannot be verified, record it as an Open Question and ask the user.
-- Even if steering is already complete, update it when new facts are discovered in this stage.
+Follow `.qfai/assistant/instructions/shared-skill-operating-baseline.md#stage-0---steering-completion-refresh-mandatory`.
 
 ## Delta Rejected Guard (Mandatory)
 
-- Do NOT reintroduce options marked as rejected in 09_delta.md.
-- If a rejected option must be reconsidered, create a **[RE-OPEN]** Decision
-  Record in 09_delta.md that references the prior DR-ID, states what changed +
-  new criteria, and includes explicit approval (user or instructions/steering).
+Follow `.qfai/assistant/instructions/shared-skill-operating-baseline.md#delta-rejected-guard-mandatory`.
 
 ## CRITICAL CONSTRAINTS (Read First)
 
@@ -197,19 +137,7 @@ Rules:
 
 ## Completion Contract (Shared)
 
-Before declaring completion, you MUST:
-
-- OQ / undefined resolution: detect undefined or ambiguous items; resolve them or explicitly defer them with documented rationale and (when required by this prompt) user approval.
-- Deliverable completeness: verify every expected artifact listed in this prompt (and required README templates) exists and is fully populated; no missing required sections.
-- OQ / placeholder scan: scan all generated artifacts (including evidence) for
-  placeholders such as "TBD", "TODO", "TBA", "TBC", "XXX", "???", "OQ",
-  "OPEN QUESTION", "UNDEFINED", "PLACEHOLDER", and localized equivalents in
-  the user's language. Resolve or explicitly defer; do not leave silent
-  placeholders.
-- Smoke check (if applicable): when the prompt produces runnable code, tests,
-  or configs, execute the smallest command that proves basic run/start/operate
-  and record evidence. If not applicable, state "not applicable" with a short
-  rationale.
+Follow `.qfai/assistant/instructions/shared-skill-operating-baseline.md#completion-contract-shared`.
 
 ## Goal
 
@@ -280,29 +208,36 @@ Do not edit any `.qfai/**/README.md` file; raise an Open Question instead.
 
 ## Multi‑Role Orchestration (Subagents)
 
-This workflow assumes the environment _may_ support subagents (e.g., Claude Code “Task” tool) or may not.
+Use the platform's native sub-agent delegation mechanism for Claude Code, GitHub Copilot, and Codex.
 
-### If subagents are supported
+### Delegation order
 
-Delegate to multiple roles and then merge the results. Use a “real‑world workflow” order:
+Use `.qfai/assistant/steering/agent-routing.yml` as the routing SSOT.
 
-- discovery-analyst -> requirements-analyst -> delivery-planner -> solution-architect -> test-design-analyst -> qa-strategist -> devops-ci-engineer -> completion-reviewer / qa-gatekeeper
+- First required delegation / Capability Probe: `delivery-planner` in the `plan` phase.
+- Then follow routed phases in order: `plan` (`delivery-planner`, `qa-strategist`) -> `execution` (`devops-ci-engineer`) -> `review` (`qa-gatekeeper`, `completion-reviewer`, optional `implementation-reviewer` when code fixes are in scope).
+- Do not prepend non-routed roles before the first required delegation attempt.
 
-**Pseudo‑invocation pattern** (adjust to your tool):
+### Delegation contract (tool-neutral)
 
 ```text
-Task(
-  subagent_type="planner",
-  description="Create an execution plan and DoD",
-  prompt="Context: ...\nGoal: ...\nConstraints: ...\nReturn: phases + risks + DoD"
-)
+Role: delivery-planner
+Task title: Create an execution plan and DoD
+Goal: sequence quality gates and evidence work
+Inputs:
+- current change context
+- required gates
+Constraints:
+- evidence-first
+- no self-approval
+Return:
+- phases + risks + DoD
 ```
 
-### If subagents are NOT supported
-
-Only with explicit user approval (`Simulation mode allowed`), simulate roles by running the same sequence yourself:
+### Failure rule
 
-- Write a short “role output” section per role, then consolidate into the final deliverable(s).
+- The first required delegation attempt doubles as the capability check.
+- If that delegation fails, stop immediately. Do not simulate roles or continue with self-execution.
 
 ## Completion Separation (mandatory)
 

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 direction, strategy, screen contracts, and product-surface decisions.
+    mission: Implement frontend behavior aligned with selected anchor, strategy, screen contracts, and product-surface decisions.
     owned_artifacts: [ui-implementation, surface-evidence]
     tool_profile: frontend
     permission_profile: authoring

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

@@ -16,10 +16,13 @@ routing:
         blocking_agents: [requirements-analyst]
         rerun_policy: changed-scope-dependents
       - id: review
+        # requirements-heavy always_required is
+        # [completion-reviewer, requirements-reviewer]; both must be blocking.
+        # See scripts/check-review-profile-consistency.mjs for the drift guard.
         mandatory_agents: [completion-reviewer, requirements-reviewer]
         conditional_agents: [architecture-reviewer, product-surface-reviewer]
         parallel_groups: []
-        blocking_agents: [completion-reviewer]
+        blocking_agents: [completion-reviewer, requirements-reviewer]
         rerun_policy: changed-scope-dependents
     review_profile: requirements-heavy
 
@@ -118,18 +121,27 @@ routing:
         blocking_agents: []
         rerun_policy: changed-scope-dependents
       - id: evidence
-        mandatory_agents: []
-        conditional_agents: [devops-ci-engineer, qa-gatekeeper]
+        # product-surface-reviewer is mandatory here (surface sign-off must
+        # be collected as part of evidence). Keep it blocking so a surface
+        # FAIL/REVISE blocks the phase — drops the mandatory+non-blocking
+        # drift flagged during PR review.
+        mandatory_agents: [product-surface-reviewer, qa-gatekeeper]
+        conditional_agents: [devops-ci-engineer, product-experience-architect]
         parallel_groups: []
-        blocking_agents: [qa-gatekeeper]
+        blocking_agents: [product-surface-reviewer, qa-gatekeeper]
         rerun_policy: changed-scope-dependents
       - id: review
-        mandatory_agents: [completion-reviewer]
-        conditional_agents: [product-surface-reviewer]
+        # full-harness always_required set (see review-profiles.yml →
+        # profiles.full-harness.always_required) is
+        # [completion-reviewer, product-surface-reviewer, qa-gatekeeper].
+        # Mirror that set as mandatory + blocking so agent-routing and
+        # review-profiles stay on one SSOT.
+        mandatory_agents: [completion-reviewer, product-surface-reviewer, qa-gatekeeper]
+        conditional_agents: []
         parallel_groups: []
-        blocking_agents: [completion-reviewer]
+        blocking_agents: [completion-reviewer, product-surface-reviewer, qa-gatekeeper]
         rerun_policy: changed-scope-dependents
-    review_profile: ui-bearing
+    review_profile: full-harness
 
   - skill: qfai-configure
     phases:

package/assets/init/.qfai/assistant/steering/manifest.md

@@ -19,9 +19,9 @@
 ## Compatibility vs Change Rubric
 
 - Criteria (Compatibility): validate.json is an internal contract (not a stable API). CLI command system follows semver.
-- Criteria (Change): Breaking changes deferred until v2.0. Migration guide required.
+- Criteria (Change): canonical consistency, validator alignment, and shipped SSOT alignment take priority. Breaking changes are allowed when required to restore canonical consistency.
 - Examples: `_shared/` -> `_policies/` rename (v1.5.3), spec-pack -> layered migration (v1.4.17)
-- Evidence: CHANGELOG.md, OQ-0003 (validate.json), OQ-0004 (legacy deprecation)
+- Evidence: CHANGELOG.md
 
 ## Governance (Ownership / Review / Evidence)
 
@@ -54,14 +54,11 @@
 ## Non-goals / Not-now (Optional)
 
 - IDE plugin / GUI development
-- Plugin architecture (to be reconsidered in v2.0)
+- Plugin architecture
 - Automated test generation
 - browser QA full audit / screenshot diff / repair loop / external critique adapter (v1.7.1)
 - auto-fix / rewrite for design findings (v1.7.2)
-- evidence schema versioning detail (deferred to v1.7.6, OQ-0001 of discussion-20260329130000123)
-- browser QA output normalization shape (deferred to v1.7.6, OQ-0002 of discussion-20260329130000123)
-- external critique provider / full-harness orchestration / calibration pack / cost observability / long-running handoff (v1.7.5 out of scope → v1.7.6 IN scope)
-- Evidence: 05_Scope.md (Out of Scope), OQ-0001, OQ-0002, discussion-20260329175059391
+- Evidence: 05_Scope.md (Out of Scope)
 
 ## References (Optional)
 

package/assets/init/.qfai/assistant/steering/product.md

@@ -37,8 +37,9 @@
 
 ## Release posture
 
-- Compatibility policy: semver. Maintain backward compatibility of the CLI command system.
-- Breaking change policy: Breaking changes deferred until v2.0. Migration guide (docs/migrations/) required.
+- Compatibility policy: current canonical contract only.
+- Breaking changes are allowed when required to restore canonical consistency.
+- CLI/skill/docs/validator must match current package semantics.
 - Evidence: CHANGELOG.md, 09_Constraints.md (DL-02)
 
 ## Milestones
@@ -64,11 +65,10 @@
 | v1.7.7 (完了)     | Remediation & Prototyping Readiness — static-first prototyping default + full-harness mode exposure + 3-layer eval reconciliation + strategy/contract upgrade + UI-bearing detection fix + render evidence wiring + browser QA findings + doc normalization + migration support                                                                                                |
 | v1.7.8 (完了)     | Canonical Convergence — design taste interview + trend research + 3-layer evaluation convergence + scoring-ready schema + strategy/screen contract upgrade + UI-bearing detection unification + static-first prototyping rewrite + full-harness mode convergence + render evidence wiring + browser QA MVP + reviewer extension + migration normalization + docs normalization |
 | v1.7.9 (完了)     | Convergence Correction Release — canonical validator registration, discussion completion convergence, honest render evidence/browser QA wiring, reviewer routing alignment, docs maturity normalization                                                                                                                                                                        |
-| v1.7.13 (進行中)  | Canonical Sidecar Convergence — selected direction SSOT moved to 31_selected_anchor_screen.md, option comparison remains in 30_option_comparison.md, sidecar-first read order, DDS/anchor vocabulary removal, validator semantics rewrite, template-validator self-consistency                                                                                                 |
+| v1.7.13 (完了)    | Canonical Sidecar Convergence — selected anchor SSOT moved to 31_selected_anchor_screen.md, option comparison remains in 30_option_comparison.md, sidecar-first read order, DDS/anchor vocabulary removal, validator semantics rewrite, template-validator self-consistency                                                                                                    |
+| v1.7.14 (進行中)  | Canonical Convergence Finalization — strict classification enforcement, namespaced-only prototyping.yaml, current-only shipped SSOT, regression net hardening                                                                                                                                                                                                                  |
 
 ## Open questions
 
 - Blocking: none
-- Non-blocking:
-  - OQ-0003: validate.json external API stability (deferred to v2.0)
-  - OQ-0004: Legacy spec-pack deprecation schedule (deferred to v2.0)
+- Non-blocking: none

package/assets/init/.qfai/assistant/steering/review-profiles.yml

@@ -16,6 +16,9 @@ profiles:
   runtime-heavy:
     always_required: [completion-reviewer, qa-gatekeeper]
     conditional_required: [implementation-reviewer]
+  full-harness:
+    always_required: [completion-reviewer, product-surface-reviewer, qa-gatekeeper]
+    conditional_required: []
 
 optional_modes:
   devils-advocate:

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

@@ -9,10 +9,10 @@ spec-0013 (CAP-0013) で定義された、下流 skill（prototyping / ATDD / TD
 
 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 direction の SSOT
+   - `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）
+   - `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。）
    - `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
 
@@ -47,8 +47,8 @@ spec-0013 (CAP-0013) で定義された、下流 skill（prototyping / ATDD / TD
 
 ## Priority and Override Semantics
 
-- sidecar artifacts（selected direction / strategy / contracts）が **primary truth**
-- 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
-- UI Contract の screen ID と sidecar contracts の対応がない場合は warning を発行
+- 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。
+- `.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。
+- UI Contract の screen ID と sidecar screen contracts の対応がない場合は warning を発行。

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

@@ -1,30 +1,37 @@
-# contracts
+# .qfai/contracts (contracts + supporting inputs)
 
 ## Purpose
 
-Contracts define the **stable surface** that specs and tests may reference.
-They are the boundary between "what we promise" and "how we implement".
+This directory holds two related categories of inputs:
 
-QFAI organizes contracts into four directories:
+- **Contracts** (`api/`, `db/`, `ui/`) define the **stable surface** that
+  specs and tests may reference. Each contract file requires a
+  `QFAI-CONTRACT-ID` header and participates in the traceability ledger.
+- **Supporting inputs** (`design/`) supplement contracts — they do **not**
+  carry contract IDs and are not directly cited by specs. Design tokens are
+  referenced indirectly from `ui/*.yaml` via token IDs.
+
+QFAI organizes this directory into four subdirectories:
 
 ```text
-contracts/
+.qfai/contracts/
 ├── api/      # OpenAPI YAML (endpoints, request/response)
 ├── db/       # SQL schema contracts (tables, columns, constraints)
 ├── design/   # Design token YAML — optional supporting input
 └── ui/       # UI contract YAML (screens, elements, user actions)
 ```
 
-> **Note:** `ui/` and `design/` are **supporting input** that supplements the discussion sidecar artifacts (`discussion-*/uiux/*`), which remain the primary truth. After `qfai init`, these directories may contain only placeholder READMEs — this is the normal initial state.
+> **Note:** `ui/` is a contract (QFAI-CONTRACT-ID required, cited by specs), but the **primary truth** for UI/UX definitions still lives in the discussion sidecar artifacts (`discussion-*/uiux/*`). UI contracts cite sidecar content by ID and exist specifically to make that sidecar machine-consumable for prototyping and selectors. `design/` is supporting input only (design tokens referenced indirectly from `ui/*.yaml`). After `qfai init`, these directories may contain only placeholder READMEs — this is the normal initial state.
 
 ## Directory rules
 
 - Contract files are **minimal**: only what specs actually need.
-- Each contract file must declare `QFAI-CONTRACT-ID` at the top (`CON-UI-*` / `CON-API-*` / `CON-DB-*`).
+- Each contract file in `api/`, `db/`, and `ui/` must declare `QFAI-CONTRACT-ID` at the top (`CON-UI-*` / `CON-API-*` / `CON-DB-*`).
+- `design/` (design token YAML) is a supporting input — **not** a contract in the traceability ledger. It does not require a `QFAI-CONTRACT-ID` header and is referenced indirectly from `ui/*.yaml` contracts via token IDs.
 - Prefer additive changes; breaking changes require delta notes.
 
 ```text
-contracts/
+.qfai/contracts/
 ├── README.md
 ├── api/
 │   ├── README.md