Painterly 3D2 Cinema Prompts

What it does

When your agent uses it

• Planning a short animated fight or story from a single sentence
• Writing Midjourney character and scene prompts in a thick-paint cel-shaded look
• Splitting a video idea into 15-second segments for Seedance
• Building a hand-drawn storyboard prompt set for an action sequence

Example prompts

• “Turn this idea into a 30-second short: a lone hunter faces a wolf pack in a snow valley.”
• “Write only the Midjourney character prompt for a young archer in this painterly style.”
• “Make the Seedance prompts for segment two, following the storyboard we agreed on.”

Requirements

• Midjourney and Seedance access, since you generate the media yourself

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

1. 1一句话种子 → 给 3 个方向卡，等用户选 A/B/C 或混合。
2. 2剧情锁定 → logline、主题、冲突、结尾画面、总时长、15秒分段表，等确认。必须先把整条片子按 15 秒切成 Segment 01/02/03，再进入角色和故事版。
3. 3角色前提问 → 问 2-4 个关键选择：主角身份、对手/障碍、情绪、武器/道具。
4. 4角色设计 → 直接输出 Midjourney V8.1 短提示词，等用户外部生成并回传。
5. 5角色细化询问 → 角色设计确认后，问是否制作角色人物信息画板；若确认，直接输出 Midjourney V8.1 提示词，不问模型。
6. 6场景设计 → 场景方案确认后直接输出 Midjourney V8.1 提示词，等用户外部生成并回传。
7. 7手绘动作故事版 → 人物、场景和剧情确认后，问是否制作故事板；若确认，直接逐张输出 Midjourney V8.1 提示词。每个 Segment 固定 15 秒以内，对应一张 15 格 storyboard。
8. 8分镜关键帧 → 需要时直接输出 Midjourney V8.1 提示词，不调用生成工具。
9. 9视频提示词 → 默认按 Seedance 模板严格引用 storyboard，直接输出提示词，不问视频模型。
10. 10最后提示用户手动把提示词和参考图放入对应工具，并在生成后上传结果以继续检查或进入下一阶段。

What it can do on your machine

Read from SKILL.md and the folder at commit d08416a. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Painterly 3D2 Cinema Prompts loads about 1.8k tokens when it runs, and up to ~8.3k if it reads all its reference files. Until then it costs about 92 tokens; SKILL.md has 401 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~92

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~8.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from liucongg/liucong-skills at commit d08416a, republished under its Apache-2.0 licence (© liucongg). 401 words, ~1,805 tokens.

name

painterly-3d2-cinema

description

Create prompt-only painterly 3D-to-2D cinematic animation packages: 三渲二、厚涂赛璐璐、美漫角色、魔幻打斗短片、剧情、角色、场景、Midjourney V8.1角色/场景/手绘故事板提示词、Seedance分段视频提示词。Use when the user wants one-sentence-to-video workflows, 角色展示, 场景设计, storyboard, action shots, 15s/30s segmented video planning, or full short-film prompt pipelines without Codex generating the media.

总时长：[15s/30s/45s...]
Segment 01 / 0-15s：[本段剧情目标]；动作起点：[ ]；动作终点：[ ]；必须生成 Storyboard Ref 01
Segment 02 / 15-30s：[本段剧情目标]；动作起点：承接 Segment 01 终点；动作终点：[ ]；必须生成 Storyboard Ref 02
Segment 03 / 30-45s：[本段剧情目标]；动作起点：承接 Segment 02 终点；动作终点：[ ]；必须生成 Storyboard Ref 03

A. [方向名]
主角：[角色]
场景：[地点/天气]
冲突：[动作问题]
视觉钩子：[颜色/道具/魔法/构图]
分段节奏：Segment 01[0-15s]；若>15s继续写 Segment 02[15-30s]、Segment 03[30-45s]
结尾：[最终画面]

白底全身人物概念设定图，[地域/世界观][身份]，[年龄]，[叙事功能]。粗粝厚涂美漫角色设计，3D体块基础结合2D手绘笔触，强块面光影，低饱和电影色彩，[服饰]朋克化剪影。比例夸张，高瘦但有少年感，长腿，小头，窄肩，手脚偏大。脸型瘦长，五官不用清楚，眼神[情绪]。[外层大色块]，[内层大色块]，[下装/鞋]。配件少而明确：[橘色视觉钩子]、[身份物]、[工具]。白色背景，脚下粗糙手绘阴影。不要写实摄影、Q版、道具堆叠、可读文字、logo

Segment 01 / 0-15s: Use @[Storyboard Ref 01] only; follow panel order exactly.
Segment 02 / 15-30s: Use @[Storyboard Ref 02] only; begin from Segment 01 final state.
Segment 03 / 30-45s: Use @[Storyboard Ref 03] only; begin from Segment 02 final state.
Use @[Char ref] as C1 reference.
Use @[Opponent/Scene ref] if available.
EMOTIONAL GUIDANCE: [valence / arousal curve]
AUDIO: [diegetic ambience, foley, impacts, silence]
BEATS: [panel-by-panel sequence]
LIMITS: no alternative coverage, no extra characters, no logos, no subtitles.

© liucongg, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 12 other files (references, assets) in skills/painterly-3d2-cinema of liucongg/liucong-skills.

• SKILL.md
• agents/openai.yaml
• assets/reference-frames/01-wide-snow-valley.jpg
• assets/reference-frames/02-close-fur-portrait.jpg
• assets/reference-frames/03-panic-snow-action.jpg
• assets/reference-frames/04-wolf-attack-silhouette.jpg
• assets/reference-frames/05-warm-interior-portrait.jpg
• assets/reference-frames/06-wolf-eye-closeup.jpg
• assets/reference-frames/07-youth-winter-closeup.jpg
• references/director-methods.md
• references/frame-index.md
• references/prompt-templates.md
• references/style-system.md

Open the folder on GitHubat commit d08416a