Individual skill
novel-art
给 AI 短剧出美术设定集(场景 + 叙事道具):场景的设计意图、一致性锚点、光照时段变体、 空景提示词;道具的戏剧功能、状态变体、尺度参照、白底无手提示词。 产出 art.json + Markdown + 单页评审报告(含导出 JSON)。 为 AI 生成而设计,不是实拍——环境和道具都是生成资产,交付的是让它们跨集长一样的一致性方案; 10 道质量门全部由脚本确定性检查(锚点 3–5、无人无手、白底可抠、尺度短语、提示词英文……)。 有 novel-outline 的 outline.json 就用 seed 预填场景清单与出现集。 零依赖、零 API key、不出图——交付的是提示词,出图在下游。 Use when asked to 场景设定、出场景、环境设定集、场景一致性、scene bibles for AI short drama。
skills/novel-art/SKILL.md
Source commit 8af10e0ea1a550e4575666884f4deef780bf38ff
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 11, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 6,474
- Repository last updated
- Nov 9, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
README.en.mddoc · 4,726 bytesREADME.mddoc · 5,761 bytesSKILL.mdcore · 8,297 bytesSKILL.mdcore · 8,297 bytesSKILL.mdcore · 8,297 bytesSKILL.mdcore · 8,297 bytesSKILL.mdcore · 8,297 bytesSKILL.mdcore · 8,297 bytesSKILL.mdcore · 8,297 bytesSKILL.mdcore · 8,297 bytesassets/report.webpasset · 154,436 bytesexamples/渡口-art.jsonasset · 16,839 bytesreferences/prop-pass.mddoc · 3,527 bytesreferences/report-style.mddoc · 2,512 bytesreferences/scene-pass.mddoc · 6,793 bytesreferences/schema.mddoc · 5,592 bytesreferences/sheet.mddoc · 3,858 bytesreferences/test-fixtures/upstream/README.mddoc · 481 bytesreferences/test-fixtures/upstream/渡口-cast.jsonasset · 42,544 bytesreferences/test-fixtures/upstream/渡口-outline.jsonasset · 9,659 bytesscripts/novel-art.mjsruns · 50,633 bytesscripts/selftest.mjsruns · 19,878 bytes
Read excerpt
## novel-art
给 AI 短剧出**美术设定集**:场景 + 叙事道具。**前提刻在骨子里:这是 AI 生成,不是实拍**——没有堪景搭景置景采买,环境和道具都是要被生成几十次还得长一样的资产,所以交付物全部围绕一致性:
| 交付 | 解决什么 |
| --- | --- |
| 一致性锚点(每景 3–5 个) | 观众靠它认场景,QC 靠它核对生成镜头有没有漂 |
| 光照时段变体 | AI 换时段是重新生成不是重新打灯,每个状态落成完整提示词 |
| 空景出图提示词 | 环境和角色是两层资产,参考图里混进人,一致性全毁 |
| 变体机制(variantOf) | 生成新景便宜,但变体复用母场景资产更一致 |
| 道具状态变体 | 皮箱的合上与打开是两张参考图——道具有状态弧,场景没有 |
| 道具尺度参照 | AI 经常把手持道具画成家具尺寸,提示词必须带尺度短语 |
| 道具白底无手 | 道具图要被贴进各种镜头,必须可抠;拿着道具的手是最常见污染 |