qfai 1.7.13 → 1.7.15

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

@@ -49,14 +49,12 @@ When no explicit argument is given, detect the candidate spec and constrain exec
 
 ## User Questions (AskUserQuestion Protocol)
 
-- When a question to the user is needed (e.g., exception handling, scope 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:
+
+- exception handling
+- scope confirmation
 
 ## CRITICAL CONSTRAINTS (Read First)
 
@@ -77,8 +75,12 @@ Execute the TDD micro-cycle for each pending item in `test-list.md`, transitioni
 ## Visual Review Guard
 
 - Review rendered output, screenshot evidence, or HTML output before closing any UI-affecting item.
-- Read the sidecar family first (selected direction, strategy, screen contracts) whenever implementation touches UI or critique-driven behavior.
-- Read order: option comparison (30_option_comparison.md) → selected anchor screen (31_selected_anchor_screen.md) → strategy (10_implementation_strategy.md) → taste interview (11_design_taste_interview.md) → trend scan (04_Sources.md) → 3-layer evaluation family (20/21/22/23 + optional 24) → screen contracts (40_screen_contracts.md) → review input bundle (50_review_input_bundle.md) → optional design tokens → optional fallback mock → mermaid flows.
+- Read the sidecar family first (selected anchor, strategy, screen contracts) whenever implementation touches UI or critique-driven behavior.
+- Read order: option comparison (30_option_comparison.md) → selected anchor screen (31_selected_anchor_screen.md) →
+  strategy (10_implementation_strategy.md) → taste interview (11_design_taste_interview.md) →
+  trend scan (04_Sources.md#Trend Scan) → 3-layer evaluation family (20/21/22/23 + optional 24) →
+  screen contracts (40_screen_contracts.md) → review input bundle (50_review_input_bundle.md) →
+  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.
 
 ## Non-goals
@@ -158,18 +160,21 @@ When transitioning to `exception`:
 
 ## Sub-agent Delegation (MANDATORY)
 
+Follow `.qfai/assistant/instructions/shared-skill-delegation-baseline.md`.
+
 ### Orchestrator Protocol (MUST)
 
-- Orchestrator reads `test-list.md`, determines the next pending item, and delegates each TDD phase.
-- Orchestrator MUST NOT write test or production code directly.
-- Orchestrator updates `test-list.md` status after each phase completes.
+- Orchestrator MUST NOT write test or production code directly; delegate every TDD phase to the routed implementation agents.
+- Additional implement-specific overrides:
+  - read `test-list.md`, determine the next pending item, and delegate each TDD phase;
+  - update `test-list.md` status after each phase completes.
 
 ### Formal Sub-agent Roster
 
 This skill delegates through the centralized routing policy in `.qfai/assistant/steering/agent-routing.yml`.
 
 - `delivery-planner`
-  - reads `test-list.md`, selects the next pending item, enforces Red-Green-Refactor ordering, and decides parallel safety
+  - reads `test-list.md`, selects the next pending item, enforces Red-Green-Refactor ordering, and is the sole authority for parallel dispatch decisions
 - `frontend-engineer` / `backend-engineer`
   - implement the selected item only, write the failing test first, write minimal passing code, and refactor without unrelated changes
 - `qa-gatekeeper`
@@ -194,28 +199,21 @@ All agent-to-agent transitions follow these contracts:
 
 ### Capability Probe (MUST)
 
-1. Run one harmless Probe Task once at stage start.
-2. If subagents are unavailable, explicitly ask for Simulation mode approval.
-3. Without explicit approval, stop the stage.
+- No additional overrides.
 
-### Simulation mode (Opt-in only)
+### Delegation Failure (Hard Stop)
 
-- Allowed only when user explicitly states `Simulation mode allowed`.
-- Record both:
-  - `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
 
-Every major artifact in this stage MUST include this table schema:
-
-| Step | Role (sub-agent) | Task title | Input (refs) | Output (refs) | Status (PASS/REVISE) |
-| ---- | ---------------- | ---------- | ------------ | ------------- | -------------------- |
-| 1    | `role`           | `task`     | `refs`       | `refs`        | PASS/REVISE          |
+Use the shared schema (per-row `Status (PASS/REVISE)` column, reviewer response `Result: PASS | REVISE`).
 
 ### Reviewer Gate (MUST)
 
 - Delegate final completion gate to an independent Reviewer.
+- Reviewer response must include `Result: PASS | REVISE` (matching shared-skill-delegation-baseline.md#reviewer-response-template).
 - Reviewer checks Drift Protocol compliance and alignment with `.qfai/assistant/steering/test-layers.md`.
 - Test volume floors/ratios are not gates; they are signals.
 - Do not declare DONE until Reviewer returns `PASS`; otherwise apply `REVISE`.
@@ -252,6 +250,8 @@ Every major artifact in this stage MUST include this table schema:
 
 ## Completion Contract (Shared)
 
+Follow `.qfai/assistant/instructions/shared-skill-operating-baseline.md#completion-contract-shared`.
+
 ### Item completion checklist (10-point gate)
 
 An item in `test-list.md` may transition to `done` only when ALL of the following are satisfied:

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

@@ -1,7 +1,7 @@
 ---
 name: qfai-prototyping
-title: QFAI Prototyping (All-spec runnable skeleton gate)
-description: "Implement a minimum runnable skeleton for ALL specs and block DONE until evidence + validate gate pass."
+title: QFAI Prototyping (Full-Harness Only)
+description: "Build a contract-aligned UI prototype and block completion until full-harness evidence and validate gate pass."
 argument-hint: "[--auto]"
 allowed-tools: [Read, Glob, Write, TodoWrite, Task, Bash]
 roles:
@@ -16,235 +16,225 @@ roles:
     product-surface-reviewer,
     qa-gatekeeper,
   ]
-routing-profile: ui-bearing
+routing-profile: ui-surface-aware
 mode: execution-focused
 ---
 
-<!-- QFAI Skill Body (SSOT) -->
-
 ## /qfai-prototyping
 
 [DRIFT-PROTOCOL:MANDATORY]
 
-This skill is **static-first**. File-based checks and evidence are the default. Runtime-heavy verification is reserved for **explicit full-harness** runs only.
+This skill is static-first for planning and file review, but the package execution contract is `full-harness` only.
+Do not default or downgrade prototyping modes.
 
 ## CRITICAL CONSTRAINTS (Read First)
 
-- Scope is **ALL specs** from `.qfai/specs/spec-*`.
-- Evidence is mandatory in **markdown + json** under `.qfai/evidence/`.
-- `DONE is forbidden` until prototyping evidence, reviewer gate, and `qfai validate --fail-on error` pass.
-- `qfai prototyping run` is available as an auxiliary generate-side command, not the primary surface for this skill.
-- Defaulting to full-harness is prohibited.
-- If a required API endpoint still returns `404`, the run is incomplete.
-- `L1` and `L2` critique findings must be reflected in the evidence pack or justified as `REVISE`.
-- `uiFidelity` is the canonical UI evidence block for UI-bearing surfaces.
-- non-ui skip semantics must be preserved. UI-only placeholders are not required when the surface is non-ui.
-- Review rendered output, screenshot evidence, HTML snapshots, or preview artifacts before closing any UI-affecting run.
-- Read the canonical sidecar family first: option comparison / `30_option_comparison.md` -> selected anchor screen / `31_selected_anchor_screen.md` -> strategy / `10_implementation_strategy.md` -> taste interview / `11_design_taste_interview.md` -> trend scan / `04_Sources.md` -> 3-layer evaluation family (`20/21/22/23` + optional `24`) -> screen contracts / `40_screen_contracts.md` -> review input bundle / `50_review_input_bundle.md`.
+- Scope is all specs from `.qfai/specs/spec-*`.
+- Evidence is mandatory in markdown + json under `.qfai/evidence/`.
+- DONE is forbidden until prototyping evidence, reviewer gate, and `qfai validate --fail-on error` pass.
+- Supported prototyping surfaces are `web`, `mobile`, `desktop`, and `mixed`.
+- `cli`, API-only, backend-only, and `ui_bearing: false` classifications are not prototyping execution targets.
+- Canonical screen contracts in `discussion-*/uiux/40_screen_contracts.md` are mandatory.
+- Browser QA, render evidence, runtimeGate, uiFidelity, specCoverage, and `fullHarness` are mandatory.
+- `uiFidelity` is screen-level and must be built from real render/browser evidence.
+- `mockPaths` is a negative-only issue ledger with `fail|finding` only.
+- Calibration pack is the SSOT. Runtime and validator both resolve from `calibrationRef.packPath`.
+- `--reviewer <id>` is mandatory and placeholder reviewer ids are rejected.
+- L1 and L2 findings must be fixed or dispositioned before PASS.
 
 ## Goal
 
-Build the minimum runnable vertical slice for **ALL specs** and produce canonical prototyping evidence under `.qfai/evidence/`.
+Build the minimum runnable slice for all specs and produce canonical `full-harness` evidence under `.qfai/evidence/`.
 
-## Non-goals
+## Mode
 
-- Acceptance test automation (`/qfai-atdd`)
-- Contract redesign
-- Public CLI surface expansion
+### Full-harness
 
-## Mode Selection Protocol
+- Full-harness is the package default when prototyping execution is valid.
+- Each `qfai prototyping run --mode full-harness --reviewer <id>` invocation records exactly one measured iteration.
+- Multiple iterations are formed only by real code changes between runs.
+- The runtime does not self-modify code and does not fabricate evidence.
 
-Mode selection precedence:
+## Obligation matrix
 
-1. explicit request (`mode=low-cost|standard|full-harness`)
-2. discussion recommendation from `prototyping.yaml`
-3. default `standard`
+| surface / mode         | specs    | runtimeGate | uiFidelity | render evidence | browser QA | fullHarness |
+| ---------------------- | -------- | ----------- | ---------- | --------------- | ---------- | ----------- |
+| web / full-harness     | required | required    | required   | required        | required   | required    |
+| mobile / full-harness  | required | required    | required   | required        | required   | required    |
+| desktop / full-harness | required | required    | required   | required        | required   | required    |
+| mixed / full-harness   | required | required    | required   | required        | required   | required    |
 
-Record in `prototyping.json`:
+## Required evidence
 
-- `mode.requested` (optional)
-- `mode.effective` (required)
-- `mode.source` (required)
-- `mode.rationale` (required)
-- `mode.discussionRecommendation` (optional)
+## Evidence (MANDATORY)
 
-## Surface Semantics
+- `.qfai/evidence/prototyping.md`
+- `.qfai/evidence/prototyping.json`
+- `.qfai/evidence/render.json`
+- `.qfai/evidence/browser-qa.json`
+- `.qfai/evidence/fullHarness.exit.json`
+- `.qfai/evidence/fullHarness.handoff.json`
+- `.qfai/evidence/fullHarness.fakeUiDetection.json`
 
-- `surface: non-ui` means UI-specific evidence is `n/a`.
-- For non-ui projects, `uiFidelity`, render evidence, browser QA, and `runtimeGate.ui` may be absent.
-- Absent is normal for non-ui. Do not force skipped placeholders unless the project intentionally emits them.
-- For UI-bearing projects, route/contract fidelity must be captured when `uiFidelity` is required by mode.
+## Truthfulness rules
 
-## Prototyping Modes
+- `mode.effective` must be `full-harness`.
+- `runtimeGate` is observed-only. Synthetic status codes are invalid.
+- `runtimeGate.evidenceRefs` must contain concrete render/browser QA/spec refs only.
+- `specCoverage` must use concrete declared refs and concrete observed refs only.
+- Browser QA evidence must be preserved per screen.
+- `actionsWired` must reflect actionable control coverage, not finding counts.
+- `reviewerSignoff.status` represents final decision, not mere completion.
+- `reviewerLogs[].verdict` must align with decision/termination semantics.
 
-### Low-cost
+## Review semantics
 
-- Static checks only.
-- Suitable for early skeleton work.
-- UI-bearing projects may include `uiFidelity` and render/browser artifacts, but they are optional.
-- `skeleton` mode is allowed for lightweight UI proof.
+- `accepted` -> `approved`
+- `rejected` -> `rejected`
+- `abandoned` -> `abandoned`
+- Plateau stop or max-iterations stop must not produce `approved`.
 
-### Standard
+## Delegation Scope Table
 
-- Static checks plus optional light validation.
-- This is the default mode.
-- UI-bearing projects require `uiFidelity`.
-- Runtime gate, render bundle, and browser QA bundle are optional.
+All sub-agent delegation in this skill MUST follow the category-to-role mapping below.
+Assigning a task to a role not listed for the category is a violation and MUST be flagged.
 
-### Full-harness
+| Category           | Allowed Role(s)                                        |
+| ------------------ | ------------------------------------------------------ |
+| UI implementation  | frontend-engineer, product-experience-architect        |
+| Screenshot capture | devops-ci-engineer                                     |
+| Evaluation L1-L2   | product-surface-reviewer, product-experience-architect |
+| Build              | devops-ci-engineer, backend-engineer                   |
 
-- Explicit opt-in only. Never auto-activate.
-- Adds runtime-heavy obligations and full-harness audit metadata.
-- UI-bearing projects require runtime gate, render bundle, browser QA bundle, and `fullHarness`.
-- Non-ui projects require `fullHarness`, but UI-specific bundles remain n/a.
+Any delegation map entry that assigns a category to an undefined or unlisted role (e.g., `"generic-code-writer"`) MUST produce a violation finding naming the undefined role and the category.
 
-## Obligation Matrix
+## Required process
 
-### surface / mode
+### Step 0 — Execution Plan (executionPlan)
 
-| surface / mode            | specs    | runtimeGate | uiFidelity                        | render evidence                      | browser QA   | fullHarness  |
-| ------------------------- | -------- | ----------- | --------------------------------- | ------------------------------------ | ------------ | ------------ |
-| non-ui / low-cost         | required | optional    | n/a                               | n/a                                  | n/a          | absent       |
-| non-ui / standard         | required | optional    | n/a                               | n/a                                  | n/a          | absent       |
-| non-ui / full-harness     | required | optional    | n/a                               | n/a                                  | n/a          | required     |
-| ui-bearing / low-cost     | required | optional    | optional (`skeleton` allowed)     | optional (`captured/skipped/failed`) | optional     | absent       |
-| ui-bearing / standard     | required | optional    | **required** (`interactive` only) | optional (`captured/skipped/failed`) | optional     | absent       |
-| ui-bearing / full-harness | required | required    | **required** (`interactive` only) | **required**                         | **required** | **required** |
+Before any code is written, create an `executionPlan` record with the following fields:
 
-`uiFidelity.mode` policy:
+- `targetIterations`: integer; minimum 2 for full-harness
+- `evaluationAxesSource`: reference to the discussion pack evaluation-family files (20/21/22/23)
+- `delegationMap`: category-to-role assignments per Delegation Scope Table above
+- `plannedAt`: ISO-8601 timestamp
 
-- `low-cost`: `skeleton` or `interactive`
-- `standard`: `interactive` only — `skeleton` is rejected by the validator
-- `full-harness`: `interactive` only — `skeleton` is rejected; render evidence, Browser QA, runtimeGate, and fullHarness block are all required
-- `non-ui`: `uiFidelity` is not emitted
+The executionPlan MUST be present in `prototyping.json` when `mode=full-harness`. A validator MUST reject any full-harness record without an executionPlan.
 
-Interpretation:
+### Iteration Gate
 
-- `required`: validator enforces presence and completeness
-- `optional`: if present, schema must be valid; if absent, no issue
-- `n/a`: absent is normal success
+- full-harness convergence requires a minimum of 2 iterations.
+- A single-iteration run that reports `converged=true` is invalid; the iteration gate MUST raise an error with message "minimum 2 iterations required before convergence".
+- The phase transition from iteration N to N+1 is blocked until `terminationCondition` is met or the gate explicitly authorizes continuation.
 
-## Required Evidence
+### 5-Step Iteration Cycle
 
-### Evidence (MANDATORY)
+Each full-harness iteration follows this fixed sequence:
 
-- `.qfai/evidence/prototyping.md`
-- `.qfai/evidence/prototyping.json`
-- `.qfai/evidence/render.json` when render evidence is emitted or required by mode
-- `.qfai/evidence/browser-qa.json` when browser QA evidence is emitted or required by mode
-- `Coverage Matrix` covering all specs
-- critique summary with `L1` / `L2` findings and disposition
+1. **Capture** — Run `packages/qfai/assets/scripts/capture-screenshots.js --url <url> --out <dir>` and record screenshot paths with timestamps under `scoringTrace[i].screenshotDir`.
+2. **Evaluate** — Launch L1 and L2 evaluator sub-agents with full context bundle: (a) screenshots from Step 1, (b) axisDefs from evaluation-family 20/21/22/23, (c) previousScore from prior iteration, (d) designSystemChecklist from `uiux/12_design_system.md`.
+3. **Identify** — Aggregate L1 + L2 findings; flag immediate-fix items.
+4. **Fix** — Apply fixes per finding disposition; do not close items without evidence.
+5. **Re-evaluate** — Re-run Steps 1–4; compare new score to prior score to check plateau.
 
-### low-cost obligations
+The sequence MUST NOT be permuted. Parallel execution of Capture+Evaluate is prohibited.
 
-- always: `specs[]`, `meta.generatedAt`, `meta.toolVersion`, `meta.commands[]`, `mode.*`
-- ui-bearing: `uiFidelity` optional, render/browser optional
-- non-ui: UI-specific evidence is n/a
+### Evaluator Input — 4 Required Elements
 
-### standard obligations
+When launching any L1 or L2 evaluator sub-agent, all 4 elements MUST be present in the input:
 
-- always: `specs[]`, `meta.*`, `mode.*`
-- ui-bearing: `uiFidelity` required
-- non-ui: UI-specific evidence is n/a
-- runtime gate and browser QA remain optional
+(a) screenshots — paths produced by capture-screenshots.js for the current iteration
+(b) axisDefs — scoring axes from discussion-pack evaluation-family (20/21/22/23)
+(c) previousScore — aggregate score from the prior iteration (null for iteration 1)
+(d) designSystemChecklist — the compliance checklist derived from `uiux/12_design_system.md`
 
-### full-harness obligations
+If any element is missing, a reviewer check MUST raise a finding naming the missing element.
+Missing element (d) is a common error when `uiux/12_design_system.md` is absent; the reviewer MUST still flag it.
 
-- always: `specs[]`, `meta.*`, `mode.*`, `fullHarness`
-- ui-bearing: `runtimeGate`, `.qfai/evidence/render.json`, `.qfai/evidence/browser-qa.json`, `uiFidelity`
-- non-ui: UI-specific evidence remains n/a
+### Visual Quality Structural Checklist
 
-## Full-harness minimum completeness
+Each iteration evaluation MUST score all 6 visual categories:
 
-When `mode.effective = full-harness`, record:
+1. Color — color palette adherence to design system tokens
+2. Typography — type scale, weight, line-height compliance
+3. Spacing — spacing scale and grid alignment
+4. Border radius — border-radius consistency across components
+5. Shadow — shadow elevation and opacity standards
+6. Do's&Don'ts — adherence to explicit do/don't rules from `uiux/12_design_system.md`
 
-- `fullHarness.enabled = true`
-- `fullHarness.available`
-- `fullHarness.runId`
-- `fullHarness.iterationCount >= 1`
-- `fullHarness.bestIteration >= 1`
-- `fullHarness.terminationReason`
-- `fullHarness.reviewerSignoff`
-- `fullHarness.scoringTrace`
+### Lighthouse Gate (MUST for web full-harness)
 
-## Canonical Bundles
+When `surface=web` and `mode=full-harness`, a Lighthouse performance/accessibility report MUST be captured and attached to the evidence. The reviewer gate MUST raise an error "Lighthouse Gate is MUST for full-harness + web surface" when the report is absent.
 
-- render bundle: `.qfai/evidence/render.json`
-- browser QA bundle: `.qfai/evidence/browser-qa.json`
+### Steps (continued)
 
-Render bundle uses `captured | skipped | failed`.
-Browser QA bundle uses `completed | skipped | failed`.
+1. Read the latest discussion pack and verify `prototyping.yaml`, `04_Sources.md`, `20/21/22/23`, and `40_screen_contracts.md`.
+   Read order: option comparison / `30_option_comparison.md` -> selected anchor screen / `31_selected_anchor_screen.md` -> strategy / `10_implementation_strategy.md` -> taste interview / `11_design_taste_interview.md` -> trend scan / `04_Sources.md` -> 3-layer evaluation family (`20/21/22/23`) -> screen contracts / `40_screen_contracts.md`.
+2. Verify the classification is UI-bearing and the surface is `web`, `mobile`, `desktop`, or `mixed`.
+3. Create the executionPlan (Step 0 above).
+4. Implement the minimum runnable slice for all specs.
+5. Run `qfai prototyping run --mode full-harness --reviewer <id>` — this executes the 5-Step Iteration Cycle per iteration.
+6. Review render evidence, HTML snapshots, Browser QA, runtimeGate, uiFidelity, and specCoverage for every declared screen.
+7. Fix findings and rerun until the evidence is coherent.
+8. Run `qfai validate --fail-on error`.
+9. Route an independent reviewer and do not declare completion until the result is `PASS`.
 
-## Required Process
+## Reviewer gate
 
-1. Read `.qfai/specs/spec-*` and determine the surface and requested mode.
-2. Build the minimum runnable slice across **ALL specs**.
-3. Produce `prototyping.md` and `prototyping.json` with a complete Coverage Matrix.
-4. If UI-bearing, capture `uiFidelity`; if full-harness, capture runtime gate, render bundle, and browser QA bundle.
-5. Review rendered output, screenshot evidence, HTML snapshots, or preview artifacts against the canonical sidecar family.
-6. Record critique findings, classify each as `L1` or `L2`, and either fix or mark the result `REVISE`.
-7. Use the read order `option comparison (30_option_comparison.md) -> selected anchor screen (31_selected_anchor_screen.md) -> strategy (10_implementation_strategy.md) -> taste interview (11_design_taste_interview.md) -> trend scan (04_Sources.md) -> 3-layer evaluation family (20/21/22/23 + optional 24) -> screen contracts (40_screen_contracts.md) -> review input bundle (50_review_input_bundle.md)` when the project is UI-bearing.
-8. Run `qfai validate --fail-on error`.
-9. Route reviewer gate and do not declare completion until the result is `PASS`.
+### Reviewer Gate (MUST)
+
+- Reviewer must verify full-harness evidence completeness.
+- Reviewer response must include `Result: PASS | REVISE` (matching shared-skill-delegation-baseline.md#reviewer-response-template).
+- Reviewer must verify calibration pack usage via `calibrationRef`.
+- Reviewer must reject self-reference, synthetic refs, and `mockPaths.status="pass"`.
+- Reviewer must verify `reviewerSignoff`, `reviewerLogs`, `terminationReason`, and `finalDecision` are semantically aligned.
+- Reviewer must verify Drift Protocol compliance and alignment with `test-layers.md`.
+- Review volume guidance remains signals, not gates.
+- Reviewer returns PASS or REVISE only.
 
 ## Sub-agent Delegation (MANDATORY)
 
+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.
-- Orchestrator MUST NOT self-approve.
-- Orchestrator MUST keep evidence paths canonical and ensure outputs stay under `.qfai/evidence/`.
+- Additional prototyping-specific overrides:
+- do not self-approve;
+- keep evidence paths canonical and integrate delegated results only.
 
 ### Capability Probe (MUST)
 
-1. Run one harmless Probe Task once at stage start.
-2. If subagents are unavailable, explicitly ask for Simulation mode approval.
-3. Without explicit approval, stop the stage.
+- No additional overrides.
 
-### Simulation mode (Opt-in only)
+### Delegation Failure (Hard Stop)
 
-- Simulation mode allowed only when user explicitly states `Simulation mode allowed`.
-- Record both:
-  - `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
 
-Every major artifact in this stage MUST include this table schema:
-
-| Step | Role (sub-agent) | Task title | Input (refs) | Output (refs) | Status (PASS/REVISE) |
-| ---- | ---------------- | ---------- | ------------ | ------------- | -------------------- |
-| 1    | `role`           | `task`     | `refs`       | `refs`        | PASS/REVISE          |
-
-### Reviewer Gate (MUST)
-
-- Delegate final completion gate to an independent Reviewer.
-- Reviewer checks Drift Protocol compliance and alignment with `.qfai/assistant/steering/test-layers.md`.
-- Test volume floors/ratios are not gates; they are signals.
-- Reviewer must verify evidence obligations for the chosen `surface / mode`.
-- Do not declare DONE until Reviewer returns `PASS`; otherwise apply `REVISE`.
+Use the shared schema (per-row `Status (PASS/REVISE)` column, reviewer response `Result: PASS | REVISE`).
 
 ## Completion Contract (Shared)
 
-Before DONE:
+Follow `.qfai/assistant/instructions/shared-skill-operating-baseline.md#completion-contract-shared`.
+
+Prototyping-specific additions:
 
-- package assets and generated evidence must match the obligation matrix
-- `qfai validate --fail-on error` must pass
-- reviewer gate must return PASS
-- UI-bearing runs must reconcile `uiFidelity`, render evidence, and critique outputs
-- non-ui runs must preserve `n/a` semantics without fake placeholders
+- all specs are covered;
+- full-harness evidence is complete and truthful;
+- `qfai validate --fail-on error` passes;
+- reviewer returns `PASS`.
 
 ## FINAL CHECKLIST (Check Last)
 
 ### Completion Checklist (MUST)
 
 - All specs are covered in the Coverage Matrix.
-- `prototyping.md` and `prototyping.json` are both updated.
-- Required mode/surface evidence is present.
-- `404` findings are resolved or the run is not complete.
-- `L1` / `L2` critique findings are documented and dispositioned.
-- `uiFidelity` is present when required.
-- Reviewer returned `PASS`; otherwise status is `REVISE`.
+- Required full-harness evidence is present.
+- 404 findings are resolved or the run is not complete.
+- uiFidelity is present when required.
+- Reviewer returned PASS; otherwise status is REVISE.
 
 ## Completion Message & Next Actions (MUST)