Agent skill

Panel Composition

by revfactory in revfactory/harness-100

스토리보더(storyboarder)와 이미지생성자(image-generator)가 사용하는 패널 구도 전문 스킬.

Apache-2.0Auto-check passedMedia & Creative

Install Panel Composition

skills CLI
$ npx skills add revfactory/harness-100 --skill panel-composition -a claude-code

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

GitHub CLI
$ gh skill install revfactory/harness-100 panel-composition --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/revfactory/harness-100.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ko/07-comic-creator/.claude/skills/panel-composition .claude/skills/panel-composition && 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
panel-composition
GitHub stars
1.3k
Token cost
~756 tokens
SKILL.md length
373 words
Files
1
Skills in repo
464
Repo updated
First seen
Licence
Apache-2.0

At a glance

스토리보더(storyboarder)와 이미지생성자(image-generator)가 사용하는 패널 구도 전문 스킬.

  • Works in 4 steps: 진입점 (Entry Point): 각 페이지에서 독자의 시선이 처음 닿는… → 시선 경로 (Gaze Path): 캐릭터의 시선 방향이 다음 패널을… → 말풍선 순서: 위→아래, 왼쪽→오른쪽 순으로 배치 (한국어 가로쓰기 기준) → …
  • Tasks that involve Image generation
  • SKILL.md covers 왜 구도가 만화를 결정하는가, 기본 패널 레이아웃 패턴, 카메라 앵글별 감정 효과 and 패널 크기와 시간의 관계, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Panel Composition is an agent skill from revfactory/harness-100. 스토리보더(storyboarder)와 이미지생성자(image-generator)가 사용하는 패널 구도 전문 스킬. 만화 패널 레이아웃 패턴, 카메라 앵글, 시선 유도, 페이지 리듬 설계 방법론을 제공한다. '패널 레이아웃', '구도', '콘티 설계', '시선 유도' 등에 활용한다.

Its SKILL.md is about 760 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 Image generation. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Image generation

Example prompts

  • “/panel-composition”

Workflow steps

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

  1. 진입점 (Entry Point): 각 페이지에서 독자의 시선이 처음 닿는 곳 — 가장 중요한 정보 배치
  2. 시선 경로 (Gaze Path): 캐릭터의 시선 방향이 다음 패널을 가리키도록
  3. 말풍선 순서: 위→아래, 왼쪽→오른쪽 순으로 배치 (한국어 가로쓰기 기준)
  4. 액션 방향: 오른쪽을 향하는 동작 = 전진/진행, 왼쪽 = 후퇴/회상

What it can do on your machine

Read from SKILL.md and the folder at commit 8e8d35c. 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

Panel Composition loads about 756 tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 373 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~756

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 revfactory/harness-100 at commit 8e8d35c, republished under its Apache-2.0 licence (© revfactory). 373 words, ~756 tokens.

Download SKILL.mdSave it as .claude/skills/panel-composition/SKILL.md (or your agent's skills folder).
name
panel-composition
description
스토리보더(storyboarder)와 이미지생성자(image-generator)가 사용하는 패널 구도 전문 스킬. 만화 패널 레이아웃 패턴, 카메라 앵글, 시선 유도, 페이지 리듬 설계 방법론을 제공한다. '패널 레이아웃', '구도', '콘티 설계', '시선 유도' 등에 활용한다.

Panel Composition — 패널 구도 전문 방법론

storyboarder와 image-generator 에이전트가 만화 패널을 설계하고 이미지를 생성할 때 활용하는 구도 전문 지식.

왜 구도가 만화를 결정하는가

만화는 시간을 공간으로 변환하는 매체다. 영화는 시간이 흐르지만, 만화는 독자가 시선을 이동하며 시간을 만든다. 패널의 크기, 형태, 배치가 곧 시간과 감정의 연출이다.

기본 패널 레이아웃 패턴

4컷 만화 레이아웃
패턴구조적합한 이야기
기승전결동일 크기 4칸 세로코미디, 일상 관찰
와이드 클로즈와이드→표준→표준→클로즈업드라마, 감정 강조
줌 인원경→중경→근경→클로즈업긴장 고조, 발견
시간 점프과거→현재→현재→결과대비, 성장
웹툰 레이아웃 (세로 스크롤)
연출 기법패널 구성효과
여백 확장패널 사이 여백을 2~3배로시간 경과, 여운
풀폭 패널화면 전체 너비 사용임팩트, 장면 전환
긴 세로 패널높이가 긴 패널낙하, 고도, 압도감
연속 컷작은 패널 3~5개 연속빠른 액션, 긴장
무음 패널대사 없는 풍경/표정감정 여백, 독자 해석 유도

카메라 앵글별 감정 효과

앵글감정 효과사용 상황프롬프트 키워드
로우앵글 (올려다봄)위압, 권위, 영웅적등장인물 소개, 대립"low angle shot, looking up"
하이앵글 (내려다봄)나약, 고립, 전체상위기, 고독"high angle shot, bird's eye"
아이레벨 (눈높이)동등, 객관적대화, 일상"eye level shot"
더치앵글 (기울임)불안, 긴장, 혼란심리 불안, 위험"dutch angle, tilted frame"
오버숄더 (어깨 너머)대화의 긴장, 시점대화, 대립"over the shoulder shot"
POV (1인칭)몰입, 독자=캐릭터공포, 발견"POV shot, first person"

패널 크기와 시간의 관계

작은 패널 = 짧은 시간 (빠른 액션, 순간)
큰 패널 = 긴 시간 (여유, 감정, 풍경)
테두리 없는 패널 = 시간 정지 (몽상, 플래시백)
Show full SKILL.md (154 more words)Show less
크기별 사용 가이드
크기비율용도
소 (1/6 페이지)15%리액션, 효과음, 순간 포착
중 (1/4 페이지)25%표준 대화, 일반 행동
대 (1/2 페이지)50%감정적 순간, 액션 하이라이트
풀 (전체 페이지)100%에스타블리싱 샷, 클라이맥스
더블 스프레드 (2페이지)200%최고 임팩트, 전투 파노라마

시선 유도 (Reading Flow)

Z-패턴 (서양식)
→ → → →
        ↓
← ← ← ←
↓
→ → → →
역Z-패턴 (한국 만화/웹툰)
← ← ← ←
↓
→ → → →
        ↓
← ← ← ←
시선 유도 규칙
  1. 진입점 (Entry Point): 각 페이지에서 독자의 시선이 처음 닿는 곳 — 가장 중요한 정보 배치
  2. 시선 경로 (Gaze Path): 캐릭터의 시선 방향이 다음 패널을 가리키도록
  3. 말풍선 순서: 위→아래, 왼쪽→오른쪽 순으로 배치 (한국어 가로쓰기 기준)
  4. 액션 방향: 오른쪽을 향하는 동작 = 전진/진행, 왼쪽 = 후퇴/회상

페이지 리듬 설계: 음악적 패턴

리듬 패턴패널 구성효과
강-약-강-약큰-작은-큰-작은안정적, 대화 장면
약-약-약-강!작은-작은-작은-풀페이지긴장 축적 → 폭발
강-약-약-약큰 도입 → 작은 진행장면 전환 후 디테일
균등모두 같은 크기시간의 균일한 흐름, 일상
점강큰→중→작→작줌인, 집중
점증작→작→중→큰줌아웃, 스케일 확대

이미지 생성 프롬프트 구조

[스타일] [앵글] [구도]. [인물 묘사]. [동작/표정].
[배경/환경]. [조명]. [감정/분위기].
[텍스트 지시: 한글 대사 또는 NO TEXT]
프롬프트 예시
Korean manhwa style, medium shot, slightly low angle.
A young woman with short black hair in a lab coat,
looking surprised with wide eyes, holding a broken test tube.
Modern laboratory background with blue LED lighting.
Dramatic side lighting, tense atmosphere.
Speech bubble text MUST be in Korean: '이건... 불가능한 결과야'

© revfactory, 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

Just SKILL.md in ko/07-comic-creator/.claude/skills/panel-composition of revfactory/harness-100.

Open the folder on GitHubat commit 8e8d35c

Compare with similar skills

Panel Composition 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.

Panel Composition compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Panel Composition this skillrevfactory/harness-1001.3k—~756Automated safety check: PassApache-2.0
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-Skill5.6k—~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 yesterday
    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.

    5.6k GitHub stars~2.5k tokensUpdated 7 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

More from revfactory/harness-100

All 464 skills in this repo
  • Anti Bot Analyzer

    revfactory/harness-100

    A skill for analyzing website anti-bot defense mechanisms and developing legitimate evasion strategies.

    1.3k GitHub stars~1.1k tokensUpdated 6 mo ago
    Auto-check passed
  • API Error Design Patterns

    revfactory/harness-100

    Reference for designing how an API reports failures: structured error codes, response shapes, client-friendly messages, an error catalog and retry or fallback advice.

    1.3k GitHub stars~1.6k tokensUpdated 6 mo ago
    Auto-check passed
  • API Security Checklist

    revfactory/harness-100

    Walks a backend-dev agent through OWASP API Top 10 checks, authentication and authorization patterns, and defense code during API design.

    1.3k GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed
  • Arg Parser Generator

    revfactory/harness-100

    Methodology for systematically designing and generating CLI tool argument parser structures.

    1.3k GitHub stars~1.2k tokensUpdated 6 mo ago
    Auto-check passed
  • Audience Segmentation

    revfactory/harness-100

    Audience segmentation skill used by the analyst and curator agents.

    1.3k GitHub stars~1.3k tokensUpdated 6 mo ago
    Auto-check passed
  • Audio Storytelling

    revfactory/harness-100

    Audio storytelling skill used by the podcast scriptwriter and show note editor.

    1.3k GitHub stars~1.6k tokensUpdated 6 mo ago
    Auto-check passed

Questions about Panel Composition

What does Panel Composition do?

스토리보더(storyboarder)와 이미지생성자(image-generator)가 사용하는 패널 구도 전문 스킬. Panel Composition is an agent skill from revfactory/harness-100. 스토리보더(storyboarder)와 이미지생성자(image-generator)가 사용하는 패널 구도 전문 스킬.

When should I use Panel Composition?

Panel Composition fits situations like: tasks that involve Image generation.

How do I install Panel Composition in Claude Code?

Run `npx skills add revfactory/harness-100 --skill panel-composition -a claude-code`. Or copy the skill folder (ko/07-comic-creator/.claude/skills/panel-composition in revfactory/harness-100) into .claude/skills/panel-composition in your project. Claude Code loads it when a task matches its description.

How do I install Panel Composition in Codex?

Run `npx skills add revfactory/harness-100 --skill panel-composition -a codex`. Or copy the skill folder (ko/07-comic-creator/.claude/skills/panel-composition in revfactory/harness-100) into .agents/skills/panel-composition in your project. Codex loads it when a task matches its description.

Can I use Panel Composition 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 revfactory/harness-100 --skill panel-composition -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/panel-composition, .gemini/skills/panel-composition, .github/skills/panel-composition and .opencode/skills/panel-composition in your project.

What does Panel Composition need to run?

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

Does Panel Composition 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 Panel Composition 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 Panel Composition use?

Panel Composition is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Panel Composition use?

About 756 tokens (SKILL.md is roughly 3k 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 Panel Composition?

Skills that share tags, products or a category with Panel Composition: 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 Panel Composition?

revfactory (a GitHub user) maintains it in revfactory/harness-100, which has 1,290 GitHub stars. The repository holds 464 skills in this directory. The repository was last updated on March 22, 2026.

Source: revfactory/harness-100 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.