@acedatacloud/skills 2026.819.0 → 2026.819.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@acedatacloud/skills",
|
|
3
|
-
"version": "2026.819.
|
|
3
|
+
"version": "2026.819.2",
|
|
4
4
|
"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.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"agent-skills",
|
|
@@ -116,7 +116,7 @@ For generated hero media, the first capability-specific call MUST be the provide
|
|
|
116
116
|
|
|
117
117
|
Poll according to the returned interval until terminal. For activation/source preparation, reserve up to two minutes (for example eight 15-second polls). If still pending, record one `ADC-SPOTLIGHT-SOURCE:v1` draft artifact with task ID and fingerprint, make no completion claim, and end without Maestro.
|
|
118
118
|
|
|
119
|
-
Inspect every selected asset at full resolution. Generated media MUST use a real accepted result. Product/Agent/deployment stories use faithful, sanitized screenshots or lifecycle evidence. Full request JSON is evidence-only; customer-facing frames never contain internal review or provenance language.
|
|
119
|
+
Inspect every selected asset at full resolution. Before Blueprint approval, perform a complete body download for every selected URL, require non-zero bytes, decode at full resolution, and inspect pixel-level semantic fit to `HERO_CASE` and its assigned material role. A metadata, filename, URL, or task status alone never proves availability, visual content, or semantic relevance. A failed download, decode, or semantic-fit check makes that asset ineligible: choose another asset or candidate and do not submit Maestro. Generated media MUST use a real accepted result. Product/Agent/deployment stories use faithful, sanitized screenshots or lifecycle evidence. Full request JSON is evidence-only; customer-facing frames never contain internal review or provenance language.
|
|
120
120
|
|
|
121
121
|
## 5. Require a rich material plan
|
|
122
122
|
|
|
@@ -201,6 +201,8 @@ It MUST NOT contain `ADC-SPOTLIGHT:v1`; that marker is reserved for the outer ar
|
|
|
201
201
|
|
|
202
202
|
Formal production uses **Pro**, never Standard as a quality proxy. Choose format from `{{format}}`; `auto-diverse` must also avoid the recent three formats and fit the content/channel.
|
|
203
203
|
|
|
204
|
+
Treat Pro turns as a delivery budget, not an invitation to explore: finish the initial render by turn 140; use only `check` plus a contact sheet and at most six targeted frames for each review; Do not run deprecated `validate` or `inspect`. The visual-review call MUST NOT launch an Agent or recursively inventory evidence—read the manifest, contact sheet, and targeted frames directly. Consolidate all blockers into one repair, run one final `check`, one final render, one final-byte review, and confirm delivery by turn 240. Stop optional inspection when any milestone is at risk.
|
|
205
|
+
|
|
204
206
|
Immediately after Maestro accepts the unique UUID task, call `publish_artifact` before waiting or polling. Exact-ID `task_already_exists` is a successful idempotent replay: do not generate another UUID or resubmit.
|
|
205
207
|
|
|
206
208
|
The artifact summary—not the Maestro prompt—begins:
|