@acedatacloud/skills 2026.818.1 → 2026.818.2
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": "2026.818.
|
|
3
|
+
"version": "2026.818.2",
|
|
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",
|
|
@@ -18,6 +18,18 @@ Read first:
|
|
|
18
18
|
- [brand kit](references/brand-kit.md)
|
|
19
19
|
- [topic registry](references/topic-registry.md)
|
|
20
20
|
|
|
21
|
+
## Phase gate — preview means planning only
|
|
22
|
+
|
|
23
|
+
When the caller says `preview-only`, this rule overrides every later production section:
|
|
24
|
+
|
|
25
|
+
- load only this Skill and the explicitly allowed AceDataCloud discovery MCP;
|
|
26
|
+
- query catalog/docs/OpenAPI/pricing only;
|
|
27
|
+
- never attempt to load Maestro or any capability/media-generation MCP;
|
|
28
|
+
- never generate media, call `publish_artifact`, or start a production task;
|
|
29
|
+
- output the three candidates, selected Blueprint, Creative History marker, completion marker, and a **text-only future handoff contract**, then stop.
|
|
30
|
+
|
|
31
|
+
The production sections below describe what a separately authorized future task must do. They are not actions for the preview run.
|
|
32
|
+
|
|
21
33
|
## 1. Discover live truth
|
|
22
34
|
|
|
23
35
|
Load the AceDataCloud MCP and verify candidates from live public sources:
|
|
@@ -52,6 +64,19 @@ Score live truth, sales specificity, hero strength, authorization, price proof,
|
|
|
52
64
|
- no recent 3 transition-system, voice-family, sound-world, or palette-family repeat;
|
|
53
65
|
- a returning service must change at least four of buyer, job, hero, archetype, visual world, and offer.
|
|
54
66
|
|
|
67
|
+
Use `run_count` to select one mandatory breadth lane before candidate scoring (`((run_count - 1) mod 8) + 1`). At least one candidate must be eligible for that lane, and the selected candidate must come from it unless live truth/material evidence makes the whole lane ineligible:
|
|
68
|
+
|
|
69
|
+
1. image craft / typography / edit fidelity;
|
|
70
|
+
2. cross-service workflow transformation;
|
|
71
|
+
3. video / motion / reference control;
|
|
72
|
+
4. Agent / MCP / artifact / scheduled lifecycle;
|
|
73
|
+
5. audio / music / voice with an audio-reactive world;
|
|
74
|
+
6. search / extraction / structured-data outcome;
|
|
75
|
+
7. platform brand anthem with three real surfaces/modalities;
|
|
76
|
+
8. deployment / bot / operational lifecycle with sanitized real status evidence.
|
|
77
|
+
|
|
78
|
+
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.
|
|
79
|
+
|
|
55
80
|
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:
|
|
56
81
|
|
|
57
82
|
- `auto-diverse`: maximize distance from recent work;
|