git:20261013.04f1830 to git:20261014.8e18b74

16 added, 17 removed. Audit A to A.

---
name: game-art-production
- description: 读取主美分发的美术项目包,把角色、场景状态、道具、UI、动作与效果组织成可追溯的生成批次和组合交付;用于继续制作游戏素材、验证场景变化、导出 Compositor 分层文件或排查资产版本漂移。
+ description: Continue game-art production from a director's project pack. Assign and create related characters, environments, props, UI and animation, review them in context, and export optional Compositor scenes without inventing another visual style.
---
- # Game Art Production · 游戏美术制作
+ # Game Art Production
- **一个团队/项目,一份视觉记忆。** 本 Skill 负责把同一份规范用在持续制作与组合交付中。`art-director` 负责建立和迭代专业规范;这里读取其项目包,不另写一套审美标准。已有项目包可独立使用本 Skill;缺少方向时先补方向,不能套用潮灯案例的画风。
+ Use the direction established in the project pack to make consistent components, whoever creates them. `art-director` establishes and revises the shared judgment; this Skill applies it to production and assembly. A received project pack is sufficient to start. If direction is missing, resolve that gap before making a batch; do not inherit Tidekeeper's look by default.
- 先读完整项目包的 `SKILL.md`、`style-pack.json` 与当前任务,验证包内 manifest。冻结项目版本、fingerprint 和 manifest 哈希。用户用设计语言提出目标,Agent 整理清单、调用绘图工具和检查结果;不要求设计师先填 JSON。
+ Read the pack's `SKILL.md`, `style-pack.json`, manifest and current task. Verify the files and pin its version, fingerprint and manifest hash. Work in the user's language. The agent handles records and tools; designers should not need to fill JSON before creating art.
- ## 从已有工作继续
+ ## Continue the work
- 1. 把使用情境写清:玩家在做什么、屏幕要表达什么、哪些资产同时出现。将目标拆成首件、家族扩展、场景状态、动作、效果和交付文件。功能需要多少资产就做多少,不用装饰数量充当完整性。
- 2. 为每件记录资产 ID、来源、身份/画风/构图参考、适用规则、允许变化、依赖、输出要求和检查状态。依赖先做首件,再做变体。已存在且哈希未变的合格文件复用;缺失、拒收、旧版本不得悄悄换成占位图。
- 3. 用当前可用图像工具实际生成/编辑。每次带上相关原图;保留实际提示、工具、输入和新输出。脚本只做确定性检查和导出,不生成美术,也不伪造一次没有执行的生成。
- 4. 在真实使用尺度组合:角色落脚、场景机位与地标、UI 遮挡、透明边、层级与效果强度。状态图对齐后再转场;动作与效果绑定事件和接触点。切换背景不能掩盖建筑漂移,立绘轻移不能冒充骨骼动画。方法见 [组合与状态验收](references/assembly-review.md)。
- 5. 把共性问题返回 `art-director` 的候选新版;单件返修留在任务里。首次交付候选用 `--allow-candidate` 明确标记,不将技术通过写成主美批准。现有用户授权继续有效。
+ 1. Establish the player action, intended feeling and actual display context. Split the work into necessary assets, states and assemblies. Richness comes from meaningful relationships and behavior, not a count of decorative objects.
+ 2. Assign each asset to a person or agent and identify its upstream first article, shared rules, identity references, permitted changes and destination composition. Designate who assembles the result. Record these in the task brief or existing batch record; assignment is not completion. Reuse verified unchanged outputs, and keep missing, rejected or obsolete inputs visible.
+ 3. Actually attach relevant images to generation or editing tools. Save the prompt, tool, inputs and returned files. Check a representative result before extending its family. The scripts provide deterministic checks and exports; they do not call a model or certify aesthetics.
+ 4. Compose at the intended scale. Review shape language, edges, material, lighting and type together with character contact, contrast, layering and UI priority. A matching palette alone is insufficient. Typography should belong to the pictured world while gameplay text remains readable. Remove repeated copy that the artwork already communicates.
+ 5. For movement, choose an appropriate method and inspect actual playback. A short action may use 6–20 distinct drawn/generated poses or deformation frames, a rig, or generated animation when a suitable tool exists. This range is a production option, not a frame-count gate for every effect. Repeating one displaced image does not provide the missing poses. Follow [assembly and animation review](references/assembly-review.md).
+ 6. Return recurring direction gaps to a candidate revision of the project pack; keep single-asset fixes in their tasks. Use `--allow-candidate` for candidate handoffs without turning a technical pass into director approval. Existing user authorization remains valid.
- ## 两条交付路径
+ ## Delivery paths
- **常规制作:** 项目包 → 首件 → 同族扩展 → 使用尺度组合 → 评审与交付。适用于任何支持的图像工具和引擎,不要求安装 Compositor。
+ **Standard production:** project pack → representative asset → related assets → actual composition and playback → review and delivery. Use the available tools and target engine; Compositor is optional.
- **分层编辑:** 在常规制作后,把同一场景配方导出为 `.comp`。Compositor 是可选的图层编辑出口;不承担生成、游戏逻辑或视频动画。先读 [Compositor 适配](references/compositor.md)。Windows 可以生成和检查格式;只有实际在支持的 Mac 中打开、检查与回存,才能记录原生验收通过。
+ **Layered editing:** export the same scene recipe to `.comp` after asset production. Read [Compositor support](references/compositor.md). It is a layered editing destination, not a generation service, game engine or animation renderer. Windows can export and inspect the format. Record native acceptance only after opening, inspecting and saving on a supported Mac.
- 随本 Skill 的 `scripts/production.py` 使用 Python 3.10+。`check`、`tasks`、`verify` 使用标准库;PNG 转换与 Compositor 导出需要 Pillow。通过 `--help` 获取参数。所有输出要求新目录,禁止覆盖成员正在编辑的内容。
+ `scripts/production.py` requires Python 3.10+. `check`, `tasks` and `verify` use the standard library; PNG conversion and Compositor export require Pillow. Outputs must use new directories, preserving members' working files.
```text
python scripts/production.py check PLAN.json --pack RECEIVED_PACK --allow-candidate
python scripts/production.py tasks PLAN.json --pack RECEIVED_PACK --out NEW_TASKS
python scripts/production.py build PLAN.json --pack RECEIVED_PACK --out NEW_DELIVERY --allow-candidate
python scripts/production.py verify NEW_DELIVERY
```
- 计划字段和批次恢复见 [制作协议](references/production-contract.md)。先整理真实资料,Agent 再写计划;示例 JSON 是工具契约,不是用户入门问卷。
-
- 交付摘要用人能读懂的语言说明:完成了哪些内容、共用了什么规范、实际检查结果、文件入口和仍未解决的问题。清楚区分原创候选、技术检查、视觉自查、主美批准和引擎验收。
+ Use the [production contract](references/production-contract.md) for plan fields and recovery. Report what was made, the shared direction used, actual observations, file entry points and unresolved work. Keep candidate art, technical validation, self-review, director decisions and native or engine acceptance distinct.