@acedatacloud/skills 2026.818.2 → 2026.819.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@acedatacloud/skills",
-  "version": "2026.818.2",
+  "version": "2026.819.0",
   "description": "Agent Skills for AceDataCloud AI services — music, image, video generation, LLM chat, web search. Compatible with Claude Code, GitHub Copilot, Gemini CLI, OpenAI Codex, and 30+ AI coding agents.",
   "keywords": [
     "agent-skills",

package/skills/capability-spotlight-video/SKILL.md

@@ -75,7 +75,16 @@ Use `run_count` to select one mandatory breadth lane before candidate scoring (`
 7. platform brand anthem with three real surfaces/modalities;
 8. deployment / bot / operational lifecycle with sanitized real status evidence.
 
-If the mandatory lane is ineligible, record `LANE_BLOCKED=<reason>` in Creative History and choose the highest-scoring candidate from the least-recent eligible family. Never silently collapse back to image. The recent-history exclusions still apply inside each lane.
+The mandatory lane is a hard selection lock, not a score bonus. Candidate A/B/C labels are not a global ranking: first identify the lane candidate, then compare creative treatments inside that lane. A higher score from another lane cannot override it.
+
+Before final output, run this mechanical lane preflight:
+
+- write `MANDATORY_LANE=<1-8>:<lane-name>` in Creative History;
+- if the selected topic belongs to it, write `LANE_RESULT=selected`;
+- otherwise the entire lane must be ineligible, write `LANE_RESULT=blocked` and `LANE_BLOCKED=<specific live-truth/material reason>`, then select the least-recent eligible family;
+- never emit a selected topic from another lane with `LANE_RESULT=selected`.
+
+The completion marker repeats `lane=<1-8> | lane_result=selected|blocked`. Never silently collapse back to image. Recent-history exclusions still apply inside each lane.
 
 Use `date_iso:run_count` only as a deterministic tiebreaker; do not use unconstrained randomness. `creative_policy` influences scoring but never becomes a fixed shot template:
 
@@ -205,10 +214,11 @@ Follow it with the complete Blueprint and role→asset provenance. The outer tas
 The Blueprint defines archetype-specific gates plus these invariants:
 
 - decoded frame 0 contains clear brand or product desire—not blank/loading/disclaimer;
-- real hero material is visually dominant, not reduced to evidence cards;
+- for a 30-second format, final-byte `ffprobe` duration is 29.95–30.05 seconds; any other requested format uses the same ±0.05-second tolerance;
+- the selected real hero occupies a visually primary region for at least 40% of runtime, including one near-full-frame hold of at least 3 continuous seconds; authored type/UI may support it but never substitute for it;
 - composition variety and pacing match this run's genome;
 - no static material is dragged beyond the limit appropriate to the archetype;
 - customer copy contains no internal review language, private sourcing facts or invented claims;
 - narration/audio are complete and the CTA is readable.
 
-Make an actual `Skill` call with `skill="visual-review"` against complete initial evidence. Fix blockers in one concentrated pass. Rebuild evidence from the exact final MP4 bytes and make a second actual confirmation call even when no initial blocker exists. The Reviewer receives the Blueprint, Creative Genome, role map, and evidence and judges whether this film fulfilled **its chosen director language**, not whether it resembles previous episodes.
+Make an actual `Skill` call with `skill="visual-review"` against complete initial evidence. Fix blockers in one concentrated pass. Rebuild evidence from the exact final MP4 bytes, measure duration with `ffprobe`, verify hero runtime from the final contact sheet, and make a second actual confirmation call even when no initial blocker exists. If duration, hero-share, audio, CTA, or either review fails, Maestro MUST NOT return an accepted submission. The Reviewer receives the Blueprint, Creative Genome, role map, and evidence and judges whether this film fulfilled **its chosen director language**, not whether it resembles previous episodes.