Agent skill

Oriental Scene Lite

by Rylaispirit in Rylaispirit/cinematic-video-prompt-skill

Dùng khi viết prompt ảnh/video cảnh tiên hiệp, cổ phong, mỹ học phương Đông (thiên cung, biển mây, cung điện, kiếm khách) cho Midjourney/SD/Flux/Veo.

MITAuto-check passedMedia & Creative

Install Oriental Scene Lite

skills CLI
$ npx skills add Rylaispirit/cinematic-video-prompt-skill --skill oriental-scene-lite -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Rylaispirit/cinematic-video-prompt-skill oriental-scene-lite --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Rylaispirit/cinematic-video-prompt-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/bonus-skills/oriental-scene-lite .claude/skills/oriental-scene-lite && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
oriental-scene-lite
GitHub stars
147
Token cost
~858 tokens
SKILL.md length
366 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Dùng khi viết prompt ảnh/video cảnh tiên hiệp, cổ phong, mỹ học phương Đông (thiên cung, biển mây, cung điện, kiếm khách) cho Midjourney/SD/Flux/Veo.

  • Works in 4 steps: Công thức 6 lớp (theo thứ tự) → Khuôn mẫu vạn năng → Ví dụ → …
  • Tasks that involve AI video generation
  • SKILL.md covers 1. Công thức 6 lớp (theo thứ tự), 2. Khuôn mẫu vạn năng, 3. Ví dụ and 4. Theo công cụ
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Oriental Scene Lite is an agent skill from Rylaispirit/cinematic-video-prompt-skill. Dùng khi viết prompt ảnh/video cảnh tiên hiệp, cổ phong, mỹ học phương Đông (thiên cung, biển mây, cung điện, kiếm khách) cho Midjourney/SD/Flux/Veo. Bản Lite.

Its SKILL.md is about 860 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering AI video generation. It works with Midjourney. The repository describes itself as: AI video prompt cheat sheet & Claude Skill: cinematic camera angles, camera movement, lighting, composition, color grading for Veo 3, Kling, Sora, Runway, Midjourney. 700+ terms… The licence is MIT.

When your agent uses it

  • Tasks that involve AI video generation

Example prompts

  • “/oriental-scene-lite”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Công thức 6 lớp (theo thứ tự)
  2. Khuôn mẫu vạn năng
  3. Ví dụ
  4. Theo công cụ

What it can do on your machine

Read from SKILL.md and the folder at commit 389c193. 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

    Links to these hosts (documentation or services it may open):

    • github.com

    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

Oriental Scene Lite loads about 858 tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 366 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~858

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 Rylaispirit/cinematic-video-prompt-skill at commit 389c193, republished under its MIT licence (© Rylaispirit). 366 words, ~858 tokens.

Download SKILL.mdSave it as .claude/skills/oriental-scene-lite/SKILL.md (or your agent's skills folder).
name
oriental-scene-lite
description
Dùng khi viết prompt ảnh/video cảnh tiên hiệp, cổ phong, mỹ học phương Đông (thiên cung, biển mây, cung điện, kiếm khách) cho Midjourney/SD/Flux/Veo. Bản Lite.

Oriental Scene Lite — prompt cảnh mỹ học phương Đông

Viết prompt cảnh quốc phong / tiên hiệp đẹp như poster phim. Giải thích bằng tiếng Việt ngắn gọn; prompt gửi model viết bằng tiếng Anh, kèm 1 dòng tiếng Việt tóm ý để người dùng dễ sửa.

1. Công thức 6 lớp (theo thứ tự)

  1. Góc máy: epic wide shot · overhead shot · low angle wide-angle · symmetrical composition · long corridor depth shot
  2. Kiến trúc: ancient Chinese palace, multi-layered upturned eaves, white jade columns carved with dragons, moon gate arch, wooden lattice windows
  3. Một điểm nhấn (chỉ chọn 1): giant phoenix · bronze cauldron · stone dragon head with waterfall · ancient pine on cliff · floating scrolls
  4. Nhân vật nhỏ, quay lưng: back view, figure in flowing hanfu / white-robed swordsman, silk fluttering in wind
  5. Môi trường + ánh sáng: endless sea of clouds · mirror lake · golden dawn light · Tyndall light beams · soft morning haze · warm dusk backlight
  6. Chất lượng: delicate texture, volumetric light, depth of field, cinematic, 8K, Unreal Engine 5 rendering

Mẹo: nhân vật nhỏ + quay lưng làm cảnh hùng vĩ hơn và tránh lỗi mặt. Mỗi cảnh chỉ 1 điểm nhấn để không rối.

2. Khuôn mẫu vạn năng

Chinese xianxia concept art, [camera angle], [architecture], [one focal element], [small figure, back view, outfit], [environment], [lighting], volumetric light, atmospheric haze, delicate texture, depth of field, cinematic, 8K

3. Ví dụ

Hành lang trên mây (sáng sớm, thanh tịnh):

Chinese xianxia concept art, low angle long corridor depth shot, white jade colonnade carved with dragons and clouds, glossy stone floor reflecting the sky, a giant moon gate arch opening onto a sea of clouds, tiny figure in a crimson hanfu standing at the far end, back view, soft cool morning light, pale blue sky, atmospheric haze, clean architectural lines, depth of field, cinematic, 8K

Kiếm khách bên hồ gương (rạng đông, mơ màng):

Chinese xianxia concept art, symmetrical composition, floating palace mirrored in a still lake that merges with the clouds, lone white-robed swordsman standing on the water's edge holding a long sword, back view, hair tied and flowing, pale dawn sky, soft dreamy light, gentle ripples, ultra-wide lens, volumetric light, cinematic, 8K
Show full SKILL.md (146 more words)Show less

4. Theo công cụ

  • Midjourney: thêm --ar 16:9 (hoặc --ar 21:9 cho khổ rộng), --style raw, --no text, watermark, modern buildings.
  • SD / Flux: SD dùng ô prompt âm text, watermark, modern elements, blurry, deformed architecture; Flux viết loại trừ thành câu khẳng định.
  • Video (Veo, Kling...): thêm đúng 1 chuyển động máy (slow push-in / crane up revealing the palace) và 1 chuyển động môi trường (clouds drifting, silk fluttering). Tra thêm chuyển động camera trong skill cinematic-video-prompt.

Bản Full (VIP) có thêm: công thức 8 lớp với kho từ khóa đầy đủ, 9 cảnh mẫu hoàn chỉnh (thiên cung phượng hoàng, Lăng Tiêu, thác đầu rồng, tiên các, cổ quyển sa mạc...) kèm bản tiếng Việt, thông số SD chi tiết, hướng dẫn chuyển ảnh thành video, kết nối với skill tạo nhân vật để giữ mặt nhất quán. Liên hệ tác giả qua GitHub @Rylaispirit.

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

Files

Just SKILL.md in bonus-skills/oriental-scene-lite of Rylaispirit/cinematic-video-prompt-skill.

Open the folder on GitHubat commit 389c193

Compare with similar skills

Oriental Scene Lite next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Oriental Scene Lite compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Oriental Scene Lite this skillRylaispirit/cinematic-video-prompt-skill147—~858Automated safety check: PassMIT
Cinematic PromptLingyiChen-AI/image-prompts105—~920Automated safety check: PassNone
Painterly 3D2 Cinema Promptsliucongg/liucong-skills248—~1.8kAutomated safety check: PassApache-2.0
Libtv Videonexu-io/nexu3.3k—~3.5kAutomated safety check: PassMIT
Travel Skillkangarooking/director-skills175—~756Automated safety check: PassMIT
Seedance Storyboard in Shanghai Animation Styleliangdabiao/smy-seedance-storyboard137—~3kAutomated safety check: PassNone

Similar skills

  • Cinematic Prompt

    LingyiChen-AI/image-prompts

    电影级全流程提示词生成。用户给出故事主题,一键生成完整 markdown 文件,包含:角色设定提示词、场景提示词、完整剧本、分镜表、每个分镜的视频生成提示词。支持 Seedance 2.0 / 即梦 / Midjourney / SD。触发词:分镜、提示词、prompt、镜头、脚本、剧本、视频生成、电影风格、Seedance、生成剧本。

    105 GitHub stars~920 tokensUpdated 6 mo ago
    Media & CreativeAuto-check passed
  • Painterly 3D2 Cinema Prompts

    liucongg/liucong-skills

    Expands one sentence into a prompt package for painterly 3D-to-2D short films: story, 15-second segments, characters, scenes, Midjourney storyboards and Seedance video prompts.

    248 GitHub stars~1.8k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Libtv Video

    nexu-io/nexu

    Seedance 2.0 video & image generation via LibTV Gateway - AI text-to-video, image-to-video, video continuation, style transfer, and text-to-image using Seedance 2.0 model.

    3.3k GitHub stars~3.5k tokensUpdated 5 mo ago
    Media & CreativeAuto-check passed
  • Travel Skill

    kangarooking/director-skills

    规划、编写、审阅和修复由真实授权素材与 AI 生成镜头混合制作的电影级文旅宣传片。用于文旅短片创意简报、场景图筛选、首帧空间分析、分镜脚本、画面内容提示词、人物动作、导演级运镜、自然动机布光、转场与尾帧衔接、Seedance 2.0/可灵/Midjourney 提示词、生成结果诊断、时间线与合规风险检查;尤其适用于需要写实、辽阔、自由感和角色剧情连续性的项目。

    175 GitHub stars~756 tokensUpdated 2 days ago
    Media & CreativeAuto-check passed
  • Seedance Storyboard in Shanghai Animation Style

    liangdabiao/smy-seedance-storyboard

    Turns a story, novel or myth into a retro hand-drawn animation style short-drama script, episode breakdown, asset prompts and Seedance 2.0 storyboard prompts.

    137 GitHub stars~3k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • AI Media Generator

    Hao0321/ai-media-generator

    為使用者產生高品質的 AI 生圖、生影片、生音樂提示詞,並在需要時透過瀏覽器自動化實際送到目標平台。涵蓋 OiiOii、Kling 3.0/O-series、Seedance 2.0/2.5、Suno v5.5、Seedream 5.0/4.0、Vidu Q3、Midjourney V8.1、Flux 1.1 Pro / Kontext、Runway Gen-4.5 /…

    258 GitHub stars~5.6k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed

More from Rylaispirit/cinematic-video-prompt-skill

  • Cinematic Video Prompt Guide

    Rylaispirit/cinematic-video-prompt-skill

    Acts as a cinematography dictionary and prompt formula for writing AI video and image prompts about camera angles, movement, lighting and mood.

    147 GitHub stars~5k tokensUpdated 11 days ago
    Auto-check passed
  • Character Design Sheet Prompt

    Rylaispirit/cinematic-video-prompt-skill

    Writes one image prompt for a 16:9 character reference sheet, with three full-body views and a face close-up, so a character stays consistent across AI video clips.

    147 GitHub stars~941 tokensUpdated 11 days ago
    Auto-check passed

Works with

Questions about Oriental Scene Lite

What does Oriental Scene Lite do?

Dùng khi viết prompt ảnh/video cảnh tiên hiệp, cổ phong, mỹ học phương Đông (thiên cung, biển mây, cung điện, kiếm khách) cho Midjourney/SD/Flux/Veo. Oriental Scene Lite is an agent skill from Rylaispirit/cinematic-video-prompt-skill. Dùng khi viết prompt ảnh/video cảnh tiên hiệp, cổ phong, mỹ học phương Đông (thiên cung, biển mây, cung điện, kiếm khách) cho Midjourney/SD/Flux/Veo.

When should I use Oriental Scene Lite?

Oriental Scene Lite fits situations like: tasks that involve AI video generation.

How do I install Oriental Scene Lite in Claude Code?

Run `npx skills add Rylaispirit/cinematic-video-prompt-skill --skill oriental-scene-lite -a claude-code`. Or copy the skill folder (bonus-skills/oriental-scene-lite in Rylaispirit/cinematic-video-prompt-skill) into .claude/skills/oriental-scene-lite in your project. Claude Code loads it when a task matches its description.

How do I install Oriental Scene Lite in Codex?

Run `npx skills add Rylaispirit/cinematic-video-prompt-skill --skill oriental-scene-lite -a codex`. Or copy the skill folder (bonus-skills/oriental-scene-lite in Rylaispirit/cinematic-video-prompt-skill) into .agents/skills/oriental-scene-lite in your project. Codex loads it when a task matches its description.

Can I use Oriental Scene Lite in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Rylaispirit/cinematic-video-prompt-skill --skill oriental-scene-lite -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/oriental-scene-lite, .gemini/skills/oriental-scene-lite, .github/skills/oriental-scene-lite and .opencode/skills/oriental-scene-lite in your project.

What does Oriental Scene Lite need to run?

SKILL.md names no scripts, command-line tools or credentials: Oriental Scene Lite is instructions for the agent only.

Does Oriental Scene Lite access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Oriental Scene Lite safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Oriental Scene Lite use?

Oriental Scene Lite is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Oriental Scene Lite use?

About 858 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Oriental Scene Lite?

Skills that share tags, products or a category with Oriental Scene Lite: Cinematic Prompt (LingyiChen-AI/image-prompts, 105 stars), Painterly 3D2 Cinema Prompts (liucongg/liucong-skills, 248 stars), Libtv Video (nexu-io/nexu, 3.3k stars) and Travel Skill (kangarooking/director-skills, 175 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Oriental Scene Lite?

Rylaispirit (a GitHub user) maintains it in Rylaispirit/cinematic-video-prompt-skill, which has 147 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 27, 2026.

Source: Rylaispirit/cinematic-video-prompt-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.