Agent skill

Eterna Image2image

by Cuimao777 in Cuimao777/eterna-image2image-skill

Apply a professional Fujifilm ETERNA-inspired cinema color and composition treatment to generated or edited raster images.

MITAuto-check passedMedia & Creative

Install Eterna Image2image

skills CLI
$ npx skills add Cuimao777/eterna-image2image-skill --skill eterna-image2image -a claude-code

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

GitHub CLI
$ gh skill install Cuimao777/eterna-image2image-skill eterna-image2image --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/Cuimao777/eterna-image2image-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill/eterna-image2image .claude/skills/eterna-image2image && 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
eterna-image2image
GitHub stars
185
Token cost
~1.4k tokens
SKILL.md length
468 words
Files
5 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Apply a professional Fujifilm ETERNA-inspired cinema color and composition treatment to generated or edited raster images.

  • The user asks for ETERNA
  • SKILL.md covers Core Behavior / 核心行为, Look Selection / 风格模式, Prompt Recipe / 提示词配方 and Composition Guidance / 构图指导, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Fujifilm ETERNA

What it does

Eterna Image2image is an agent skill from Cuimao777/eterna-image2image-skill. Apply a professional Fujifilm ETERNA-inspired cinema color and composition treatment to generated or edited raster images. Use when the user asks for ETERNA, Fujifilm ETERNA, ETERNA/CINEMA, ETERNA Bleach Bypass, muted cinema stills, filmic image-to-image color grading, cinematic composition, anti-AI image polish, movie screenshots, war/drama/romance/editorial frames, or restrained film color. 适用于用户要求富士 ETERNA、电影感图生图、电影截图、降低 AI 味、低饱和电影调色、电影构图、战争/爱情/剧情/时装片质感等场景。

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `agents/openai.yaml`, `references/composition-guide.md` and `references/eterna-color-spec.md`).

It sits in Media & Creative, covering Image generation. The repository describes itself as: Experimental bilingual Codex skill for ETERNA-inspired image2image cinematic color and composition. The licence is MIT.

When your agent uses it

  • The user asks for ETERNA
  • Fujifilm ETERNA
  • ETERNA Bleach Bypass
  • Muted cinema stills

Example prompts

  • “/eterna-image2image”

What it can do on your machine

Read from SKILL.md and the folder at commit ad6b852. 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

Eterna Image2image loads about 1.4k tokens when it runs, and up to ~4.3k if it reads all its reference files. Until then it costs about 121 tokens; SKILL.md has 468 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~121
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.3k

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

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 Cuimao777/eterna-image2image-skill at commit ad6b852, republished under its MIT licence (© Cuimao777). 468 words, ~1,444 tokens.

Download SKILL.mdSave it as .claude/skills/eterna-image2image/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
eterna-image2image
description
Apply a professional Fujifilm ETERNA-inspired cinema color and composition treatment to generated or edited raster images. Use when the user asks for ETERNA, Fujifilm ETERNA, ETERNA/CINEMA, ETERNA Bleach Bypass, muted cinema stills, filmic image-to-image color grading, cinematic composition, anti-AI image polish, movie screenshots, war/drama/romance/editorial frames, or restrained film color. 适用于用户要求富士 ETERNA、电影感图生图、电影截图、降低 AI 味、低饱和电影调色、电影构图、战争/爱情/剧情/时装片质感等场景。

ETERNA Image2Image / ETERNA 图生图电影化处理

Core Behavior / 核心行为

Use this skill to turn a source image or new image prompt into a professional ETERNA-inspired cinema still. Treat ETERNA as a restrained motion-picture color and tone language, not a generic retro filter.

使用这个 skill 时,要把源图或新图提示词引导成 ETERNA 启发的专业电影截图。把 ETERNA 理解为克制的电影色彩、影调和质感系统,而不是普通复古滤镜。

If raster image generation or editing is needed, use the normal image generation workflow available in the current environment. For an existing image, preserve subject identity, composition intent, perspective, and scene lighting unless the user explicitly asks for creative changes. For no input image, generate a new cinema still with the same color discipline.

如果需要生成或编辑位图,使用当前环境中的图像生成工作流。处理已有图片时,默认保留主体身份、构图意图、透视关系和场景光线;除非用户明确要求重写画面。没有输入图时,也要用同样的色彩纪律生成新的电影截图。

This is an experimental, evolving skill. Prefer practical, testable prompt language over claims of exact Fujifilm color science. Do not claim official LUT accuracy unless the user provides a licensed official workflow and source color-space details.

这是一个持续迭代的实验性 skill。优先使用可测试、可复现的提示词和质量检查,而不要声称精确复刻 Fujifilm 官方色彩科学。除非用户提供授权的官方流程和源色彩空间信息,否则不要承诺官方 LUT 级匹配。

Look Selection / 风格模式

Choose one mode:

  • standard-eterna: default. Muted color, low-to-medium contrast, rich detailed shadows, soft highlight roll-off, natural skin.
  • clean-cinema-eterna: slightly cleaner, less grain, production still or streaming-drama finish.
  • eterna-bleach-bypass: only when requested or strongly implied. Lower saturation, higher contrast, colder metallic feel, deeper blacks.

选择一种模式:

  • standard-eterna:默认模式。低饱和、低到中等反差、暗部丰富但可读、高光柔和、肤色自然。
  • clean-cinema-eterna:更干净、颗粒更少,适合剧照、现代剧集或商业片质感。
  • eterna-bleach-bypass:只在用户明确要求或强烈暗示时使用。更低饱和、更高反差、更冷的金属感、更深的黑位。

Do not mix ETERNA Bleach Bypass into the default look.

默认不要把 ETERNA Bleach Bypass 混入标准 ETERNA。

Prompt Recipe / 提示词配方

Start from the user's subject and add this color-grading block:

text
Apply a professional Fujifilm ETERNA-inspired cinema grade: muted color, low-to-medium contrast,
soft highlight roll-off, rich but detailed shadows, natural warm skin tones, restrained olive/sage greens,
subdued steel blues, neutral-warm highlights, gentle filmic grain, natural soft sharpness, Rec.709/sRGB finish.
Preserve realistic lighting and texture. Avoid HDR, neon saturation, crushed blacks, clipped highlights,
orange-teal blockbuster grading, plastic skin, heavy halation, fake scratches, watermarks, and text.

中文提示词块:

text
应用专业的 Fujifilm ETERNA 启发电影调色:低饱和、低到中等反差、
柔和高光过渡、丰富但可读的暗部、自然偏暖肤色、克制的橄榄绿/鼠尾草绿、
低调钢蓝色、中性偏暖高光、轻微电影颗粒、自然柔和锐度、Rec.709/sRGB 输出。
保留真实光线和材质。避免 HDR、霓虹饱和、死黑、过曝高光、
商业大片式橙青调色、塑料皮肤、重度光晕、假划痕、水印和文字。

For eterna-bleach-bypass, replace the first sentence with:

text
Apply an ETERNA Bleach Bypass-inspired cinema grade: very low saturation, higher contrast,
cool metallic shadows, restrained warm highlights, hard but controlled drama, deep blacks with recoverable detail.

中文:

text
应用 ETERNA Bleach Bypass 启发的电影调色:极低饱和、更高反差、
冷金属暗部、克制暖高光、强硬但受控的戏剧感、深黑但保留可恢复细节。
Show full SKILL.md (236 more words)Show less

Composition Guidance / 构图指导

Use references/composition-guide.md when the task needs cinematic framing, scene blocking, lens language, lighting motivation, or anti-AI composition polish.

当任务需要电影构图、调度、镜头语言、动机光或降低 AI 味时,读取 references/composition-guide.md。

Default composition preferences:

  • Favor story-driven framing over centered passport/photo-card composition.
  • Use foreground, midground, and background separation when the scene allows it.
  • Preserve identity references, but adapt pose and blocking into a believable film moment.
  • Use motivated light sources such as windows, street lamps, practical lamps, firelight, or overcast sky.
  • Leave controlled negative space when it adds tension, intimacy, loneliness, or scale.
  • Avoid over-clean symmetry, generic poster composition, floating props, impossible reflections, and text artifacts.

默认构图偏好:

  • 优先让画面像叙事中的一帧,而不是居中的证件照或人设卡。
  • 场景允许时,使用前景、中景、背景层次。
  • 保留参考人物/主体身份,但把姿态和调度转化为可信的电影瞬间。
  • 使用有动机的光源,例如窗光、路灯、实景台灯、火光或阴天自然光。
  • 在紧张、亲密、孤独或表现空间尺度时保留有控制的负空间。
  • 避免过度干净的对称、泛化海报构图、悬浮道具、不可能反射和文字伪影。

Color And Tone Rules / 色彩与影调规则

Use references/eterna-color-spec.md when the task needs exact palette guidance, negative constraints, scene defaults, or quality checks.

当任务需要具体色盘、负向约束、场景默认色彩或质量检查时,读取 references/eterna-color-spec.md。

Use references/lut-workflow.md only when the user asks for LUTs, exact Fujifilm matching, color-managed workflows, or how to compare output against official resources.

只有当用户询问 LUT、精确 Fujifilm 匹配、色彩管理流程或如何与官方资源比较时,才读取 references/lut-workflow.md。

Quality Check / 质量检查

Before finishing, check:

  • Skin stays natural, not orange, gray, waxy, or over-smoothed.
  • Greens are olive/sage, not neon or emerald.
  • Blues are steel/gray-blue, not electric cyan.
  • Blacks are deep but readable; highlights are soft and not clipped.
  • Grain is subtle and image texture stays photographic.
  • The frame reads as a plausible cinema still, not a social-media preset or AI promo image.
  • Composition supports story, mood, and spatial logic.

完成前检查:

  • 肤色自然,不橙、不灰、不蜡、不磨皮过度。
  • 绿色偏橄榄/鼠尾草,不霓虹、不祖母绿。
  • 蓝色偏钢蓝/灰蓝,不电光青。
  • 黑位深但可读;高光柔和且不过曝死白。
  • 颗粒轻微,整体质感仍像摄影。
  • 画面像可信的电影截图,而不是社交媒体滤镜或 AI 宣传图。
  • 构图服务于故事、情绪和空间逻辑。

© Cuimao777, MIT. 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 4 other files (references) in skill/eterna-image2image of Cuimao777/eterna-image2image-skill.

  • SKILL.md
  • agents/openai.yaml
  • references/composition-guide.md
  • references/eterna-color-spec.md
  • references/lut-workflow.md

Open the folder on GitHubat commit ad6b852

Compare with similar skills

Eterna Image2image 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.

Eterna Image2image compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Eterna Image2image this skillCuimao777/eterna-image2image-skill185—~1.4kAutomated safety check: PassMIT
Structured Image Generationbytedance/deer-flow83k5 repos~2.9kAutomated safety check: PassMIT
AI Image Generation and Editingzhayujie/CowAgent47k—~1.3kAutomated safety check: PassMIT
Canghe Comicfreestylefly/canghe-skills4618 repos~3.2kAutomated safety check: PassNone
Generate Imageynulihao/AgentSkillOS61710 repos~1.7kAutomated safety check: NotesNone
GPT Image Generation CLIwuyoscar/GPT-Image2-Skill5.7k—~2.5kAutomated safety check: NotesMIT

Similar skills

  • Structured Image Generation

    bytedance/deer-flow

    Turns an image request into a structured JSON prompt and runs a bundled Python script to generate the picture, optionally guided by reference images.

    83k GitHub starsUsed in 5 repos~2.9k tokens
    Media & CreativeAuto-check passed
  • Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.

    47k GitHub stars~1.3k tokensUpdated today
    Media & CreativeAuto-check passed
  • Canghe Comic

    freestylefly/canghe-skills

    Knowledge comic creator supporting multiple art styles and tones.

    461 GitHub starsUsed in 8 repos~3.2k tokens
    Media & CreativeAuto-check passed
  • Generate Image

    ynulihao/AgentSkillOS

    Generate or edit images using AI models (FLUX, Gemini). An agent skill from ynulihao/AgentSkillOS.

    617 GitHub starsUsed in 10 repos~1.7k tokens
    Media & CreativeAuto-check: notes
  • GPT Image Generation CLI

    wuyoscar/GPT-Image2-Skill

    Generates and edits images with GPT Image 2 or 2.5 through a packaged CLI and a prompt gallery, after settling which model fits the request.

    5.7k GitHub stars~2.5k tokensUpdated 8 days ago
    Media & CreativeAuto-check: notes
  • Minimal Zine Poster Generator

    LiamGvchi/gc-minimal-zine-poster

    Creates or analyzes quiet, paper-texture zine posters with big negative space, one color accent and experimental type, returning an image prompt and the generated poster.

    7.3k GitHub stars~2.9k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed

Questions about Eterna Image2image

What does Eterna Image2image do?

Apply a professional Fujifilm ETERNA-inspired cinema color and composition treatment to generated or edited raster images. Eterna Image2image is an agent skill from Cuimao777/eterna-image2image-skill. Apply a professional Fujifilm ETERNA-inspired cinema color and composition treatment to generated or edited raster images.

When should I use Eterna Image2image?

Eterna Image2image fits situations like: the user asks for ETERNA; fujifilm ETERNA; ETERNA Bleach Bypass; muted cinema stills.

How do I install Eterna Image2image in Claude Code?

Run `npx skills add Cuimao777/eterna-image2image-skill --skill eterna-image2image -a claude-code`. Or copy the skill folder (skill/eterna-image2image in Cuimao777/eterna-image2image-skill) into .claude/skills/eterna-image2image in your project. Claude Code loads it when a task matches its description.

How do I install Eterna Image2image in Codex?

Run `npx skills add Cuimao777/eterna-image2image-skill --skill eterna-image2image -a codex`. Or copy the skill folder (skill/eterna-image2image in Cuimao777/eterna-image2image-skill) into .agents/skills/eterna-image2image in your project. Codex loads it when a task matches its description.

Can I use Eterna Image2image 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 Cuimao777/eterna-image2image-skill --skill eterna-image2image -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/eterna-image2image, .gemini/skills/eterna-image2image, .github/skills/eterna-image2image and .opencode/skills/eterna-image2image in your project.

What does Eterna Image2image need to run?

SKILL.md names no scripts, command-line tools or credentials: Eterna Image2image is instructions for the agent only.

Does Eterna Image2image access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Eterna Image2image 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 Eterna Image2image use?

Eterna Image2image 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 Eterna Image2image use?

About 1.4k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.9k tokens, read only when the agent opens those files.

What are the alternatives to Eterna Image2image?

Skills that share tags, products or a category with Eterna Image2image: Structured Image Generation (bytedance/deer-flow, 83k stars), AI Image Generation and Editing (zhayujie/CowAgent, 47k stars), Canghe Comic (freestylefly/canghe-skills, 461 stars) and Generate Image (ynulihao/AgentSkillOS, 617 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Eterna Image2image?

Cuimao777 (a GitHub user) maintains it in Cuimao777/eterna-image2image-skill, which has 185 GitHub stars. The repository was last updated on June 26, 2026.

Source: Cuimao777/eterna-image2image-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.