Validation Gate (Read-Only, 5 Checks)
Every critique passes V1-V4 before delivery. V5 (Drift-Sample) fires only on second-in-session invocation with the same image; it does not block delivery, it attaches a drift-disclosure banner. Any failure on V1-V4 blocks delivery per HC#8. Fail-open is NOT applied since the skill is read-only.
V1: Domain Coverage
Check. Every domain (1-7) has a score with rationale, or sentinel "unscanned" with reason (only for HC#12 long-form partial reports on Domains 4 and 7).
Required per domain:
domain_id(1-7).domain_name.score(1-10 with optional half-point) OR sentinel"unscanned"withreasonpopulated.rationaleciting at least one image signal (or workbook XML signal if in XML-context mode).confidence(High / Medium / Low) when the signal is ambiguous.
Sentinel "unscanned" acceptable only for:
- Domain 4 (Layout) on long-form partial image per HC#12.
- Domain 7 (Interactive) on long-form partial image per HC#12.
Never acceptable for Domains 1, 2, 3, 5, 6.
Fail action. Re-derive the score from the domain's reference file. If a second run still fails, refuse delivery per HC#8. Never leave the score blank.
V2: Ethics Cap Enforcement
Check. If any Critical or Warning ethics violation fired in Phase 1, the overall score is at or below the cap.
Verification steps:
- Enumerate every ethics violation with its severity.
- Determine highest cap (Critical = 59; Warning = 79; Info = no cap).
- Confirm overall score is at or below the cap.
- Confirm banner rendered as first section of the report per
ethics_privacy_gatekeeper.md.
Fail action. Re-apply the cap. If HC#11 was bypassed, refuse delivery per HC#8. Never let the cap be silently overridden.
V3: Handoff Completeness
Check. Every field in viz_critique_report/1 populated per skill-expertise/handoff_schema.md.
Verification steps:
- Every required field present with a non-blank value or sentinel.
domainslist has 7 entries (one per domain, some potentially UNSCANNED).- Per-domain
signals_evaluatedarray is non-empty (minimum 1 signal per scored domain). UNSCANNED domains may have empty signals_evaluated only when accompanied by an UNSCANNED reason. ethics_violationslist populated (empty[]if none fired).overall_scorepopulated with the ethics-capped value if applicable.raw_overall_scorepopulated with the pre-cap value for transparency.tiermatches the overall_score range.rebuild_handoff_payloadpopulated only when overall score is below 50 (Rework tier) or specific chart/layout fixes route to downstream skills.
Fail action. Identify missing field, populate with correct value or sentinel, re-run V3. If a second run still fails, refuse delivery per HC#8.
V4: Mode and Determinism
Check. Mode field is populated and matches the workbook state. Image Only reports include the reduced-accuracy disclaimer. Domain scoring order matches the locked order. Anchor-matched field is populated per domain.
Verification steps:
modefield isworkbook_scanorimage_only; never null.- If
mode == image_only,image_only_disclaimersincludes the Domain 4 and Domain 7 reduced-accuracy notes. mode_sourceis one ofworkbook_open,workbook_closed,user_override.- Per-domain
anchor_matchedpopulated (or null only when the domain is UNSCANNED per HC#12). - Domain scoring order in the report matches the locked order: Audience, Context, Chart, Layout, Type, Accessibility, Interaction.
- Ethics cap application is the last score-modifying step (
overall_score <= raw_overall_scorewhen a cap fired).
Fail action. Repopulate the missing mode field, disclaimer, or anchor. If domain order was violated, re-order the report before delivery. If a second run still fails, refuse delivery per HC#8.
V5: Drift-Sample (Non-Blocking)
Check. On second-in-session invocation targeting the same image, per-domain scores must not drift more than 1 point from the cached prior run.
Detection strategy (hash-first with user-declared fallback):
- On first invocation, compute an image hash and cache it against the per-domain score array for the session.
- On subsequent invocation, compute the hash of the current image and compare against the cache.
- If hashes match, run drift comparison.
- If hash is unavailable, unreliable, or ambiguous (e.g., paste-format drift), fall back to explicit user re-run declaration ("run it again on the same image," "same image, re-score," or equivalent).
Verification steps:
- Retrieve cached per-domain scores keyed by image hash (or user-declared same-image flag).
- Compute absolute delta per domain between new run and cached run.
- For each domain, verify
abs(new_score - cached_score) <= 1. - If any domain drifts more than 1 point, mark the drift and attach the disclosure banner.
Drift-disclosure banner text (Tier A, one line):
Score drift detected: Domain [N] shifted [X] points from prior run. User decides which run to trust.
Tier B rendering: A "Drift Sample" subsection under the ethics section listing every domain with drift, the prior score, the new score, and the delta.
Non-blocking behavior. V5 never blocks delivery. Report ships with the drift banner attached. HC#17 enforces the banner; V-gate output notes the drift for the fix log.
Fail action. Not applicable; V5 disclosure is the action. If drift patterns recur across multiple sessions, sharpen the offending domain's decision tree in its reference file per the fix log.
Gate Execution Order
- V1 (domain coverage) first. Cheapest to run; catches most failures.
- V2 (ethics cap enforcement) next. Validates the cap was applied correctly.
- V3 (handoff completeness) next. Depends on V1 and V2 passing.
- V4 (mode and determinism) next. Confirms mode transparency and anchor-first scoring hygiene.
- V5 (drift-sample) last. Non-blocking; attaches drift banner if same-image second run drifts more than 1 point per domain.
What V-Gate Does NOT Check
- Whether the runtime behavior of interactive elements matches the design signals (route to
interaction-validator). - Whether the underlying data has quality issues (route to
data-quality-review). - Whether the chart-type advisory would produce a different verdict than Domain 3 (route to
chart-swap-advisorfor per-worksheet advisory). - Whether text-copy is spell-correct (route to
desktop-spellcheck). - Whether format strings are drift-free (route to
format-drift-scanner).
Refuse to Fabricate
If the V-gate cannot pass after one retry, refuse delivery and diagnose. Never fake a V-gate pass. Never invent a domain score or an ethics violation. Never bypass the ethics cap.