Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add liucongg/liucong-skills --skill painterly-3d2-cinemagit clone --depth 1 https://github.com/liucongg/liucong-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/liucongg/liucong-skills/painterly-3d2-cinema)<a href="https://agentmods.dev/skills/liucongg/liucong-skills/painterly-3d2-cinema"><img src="https://agentmods.dev/badge/skills/liucongg/liucong-skills/painterly-3d2-cinema/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/liucongg/liucong-skills/painterly-3d2-cinema"><img src="https://agentmods.dev/badge/skills/liucongg/liucong-skills/painterly-3d2-cinema.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00133 | $0.04239 |
| Opus 5 | $0.00067 | $0.02119 |
| Sonnet 5 | $0.00027 | $0.00848 |
| Haiku 4.5 | $0.00013 | $0.00424 |
Grade A, and why
painterly-3d2-cinema scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Painterly 3D2 Cinema
定位
把用户一句话扩展成三渲二短片提示词生产包:剧情方向 → 15秒时长分割 → 角色 → 场景 → Midjourney V8.1 手绘动作故事版 → 分镜 → Seedance 分段视频提示词。若用户只要角色/场景/提示词,就只做对应部分。
默认中文输出;最终可复制提示词只用中文。所有图片资产默认使用 Midjourney V8.1,视频阶段默认使用 Seedance;不要询问或确认模型,除非用户主动指定其他模型。只交付提示词,禁止调用任何图片或视频生成工具,禁止替用户点击生成。Midjourney 提示词里不写 --v/--ar/--sref/--sw/--stylize/--raw/--no 等参数,单条提示词必须小于 1000 字符,角色提示词目标 350-500 字符,硬上限 700 字符。
必须按需读取:
references/style-system.md:风格锁、颜色、失败规避。references/prompt-templates.md:角色、角色身份画板、手绘动作故事版、场景、Seedance视频模板。references/director-methods.md:剧情/动作/镜头方法。references/frame-index.md:只有用户要求参考内置帧/像原视频时读取。
核心风格锁
角色默认视觉 DNA:
3渲2厚涂赛璐璐运动动画,大色块设计,整块整块的平涂色面,3D转2D动画质感,硬朗图形化明暗切面,粗粝干刷笔触,轻微颜料颗粒感,避免碎乱AI噪点;不是写实真人摄影,不是光滑CGI,不要塑料玩具质感。
角色要点:
- 白底/浅灰底人物概念设定图;默认单人全身展示,除非用户明确要三视图。
- 比例严肃夸张:小头、长腿、窄肩或宽肩、大手大脚,6.5-8头身,不Q版。
- 服装用 2-4 个大色块组织;少道具,最多 3 件。
- 头部/动物/怪物必须面具化、雕塑化、几何化;避免真实动物头、真实毛发、湿眼、毛孔、碎羽毛。
- 强视觉钩子优先用一处橘色/暗红/金色,不要一身灰。
场景默认视觉 DNA:
粗粝厚涂三渲二动画,可信三维空间结合二维手绘表面,强块面光影,边缘粗糙,低饱和电影色彩,清晰剪影,前中后景分层,哑光磨损材质。
阶段确认与提示词交付
默认在剧情方向、剧情锁定、角色选择等创作决策点给选项并暂停,不自动替用户决定。模型不是决策点,不得为模型选择暂停。
全局模型与交付规则
角色概念图、角色人物信息画板、场景图、手绘故事板和分镜关键帧统一输出 Midjourney V8.1 提示词。视频阶段统一输出 Seedance 提示词。用户主动点名其他模型时才按其要求适配;不要主动列模型选项。
每次图片提示词交付必须包含:模型:Midjourney V8.1、用途、一条可直接复制的中文提示词,以及一句明确的下一步:请用户在 Midjourney 外部生成并上传成图或回复“已生成”。不得调用 image_gen、浏览器、API 或其他生成工具。
用户上传成图后,先检查角色/场景身份、构图、风格锁和明显错误。合格时主动说明下一阶段是什么并给出选项;不合格时给一条针对性修订提示词,再请用户生成新版。不得在交付图片提示词后无提示地结束流程。
- 一句话种子 → 给 3 个方向卡,等用户选 A/B/C 或混合。
- 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。
- 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。
- 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。
- 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。
- 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。
- 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。
- 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。
- 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。
- 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 ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 344 B
- assets/reference-frames/01-wide-snow-valley.jpg 177 KB
- assets/reference-frames/02-close-fur-portrait.jpg 145 KB
- assets/reference-frames/03-panic-snow-action.jpg 123 KB
- assets/reference-frames/04-wolf-attack-silhouette.jpg 100 KB
- assets/reference-frames/05-warm-interior-portrait.jpg 121 KB
- assets/reference-frames/06-wolf-eye-closeup.jpg 98 KB
- assets/reference-frames/07-youth-winter-closeup.jpg 100 KB
- references/director-methods.md 1.2 KB
- references/frame-index.md 507 B
- references/prompt-templates.md 22 KB
- references/style-system.md 1.9 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 170 lines · 133 tokens per session scan A 77c7dc554fec
painterly-3d2-cinema is a skill published in the GitHub repository liucongg/liucong-skills (246 stars, last pushed 4d ago), licensed Apache-2.0. It adds 133 tokens to every session and 4,239 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…