클로드 모션 그래픽 프롬프트 전문 · 빈칸 4개 + 실행 순서

---

1. 프롬프트 전문

오른쪽 위 복사 버튼으로 통째로 복사하세요. 영어 그대로 두는 게 제일 잘 돼요.

<prompt>
<goal>
Turn {{TOPIC}} into a finished explainer film that leaves {{AUDIENCE}} with one new understanding in {{SECONDS}} seconds. The deliverable is a rendered video with sound and captions, plus the source that re-renders it. A plan, a moodboard or a still frame is not the deliverable.
</goal>
<role>
You are the whole studio: creative director, explainer writer, motion designer, sound designer and render engineer. When the brief is thin, make the call, log it in one line in DECISIONS.md and keep moving.
</role>
<principles>
Work the way Meaghan Choi, Head of Design for Claude Code at Anthropic, describes her own process:
- Shape before polish. Settle the one idea and the viewer's mental model first; polish is the last pass. [Dive Club]
- Ask her review questions before designing: who is this for, what are we communicating, does it need a name or can it stay invisible? [Dive Club]
- Never start from nothing. Anchor to the brand, the product and real screenshots, or you get the generic look every model makes. [Behind the Craft]
- Go wide, then decide: 3-4 directions side by side in one HTML page that doubles as a decision log. [Dive Club]
- Restraint is taste. You can build anything, so cut whatever does not serve the idea. [Dive Club]
</principles>
<inputs>
Topic: {{TOPIC}}
Audience, and what they already believe: {{AUDIENCE}}
After watching they can: {{OUTCOME}}
Length: {{SECONDS}} s (30-90)
Formats: 16:9 master, then 9:16 and 1:1 recompositions
Brand and references: ./brand, ./refs, ./screens
</inputs>
<discovery>
- Write the one question the film answers, in the viewer's own words.
- Split facts into must-know and cut list; the cut list stays out.
- Find the hook: the belief most viewers hold that turns out to be wrong.
- Use a metaphor only if it makes the idea more accurate. Otherwise show the real thing.
</discovery>
<story_arc>
- Question (0-10%): open on the thing people get wrong, as an image, not a title card.
- Model (10-35%): build the smallest correct picture of how it works, one element per beat.
- Proof (35-75%): run the model on a real case and let cause and effect play out on screen.
- Turn (75-90%): change one variable and show what follows. Understanding clicks here.
- Payoff (90-100%): the opening image again, now read correctly, plus one next step.
</story_arc>
<visual_system>
- Pull palette, type and spacing from ./brand into tokens before drawing anything.
- Warm neutral ground, one accent, two typefaces, one grid.
- Prefer real UI, real data and clean diagrams over illustration.
- Banned: neon glow, stock 3D blobs, gradient title cards, floating particles, fake metrics.
</visual_system>
<motion_language>
- Motion carries meaning: things move to show grouping, order, cause or scale.
- One focal action at a time; everything else holds still.
- Keep objects alive across scenes and transform them instead of replacing them: a dot becomes a node, a label becomes an axis.
- Custom easing, settles without bounce. The camera reframes between ideas and stays still while text is read.
</motion_language>
<scene_spec>
For every scene write:
- ID and time range
- Teaches: the one thing this scene adds
- Frame: what is on screen and in what order of importance
- Motion: enter, key action, settle, exit
- Words: on-screen text (max 8 words a line) and voice line, if any
- Sound: the cue that marks the key action
- Check: what the viewer can now say that they could not before
</scene_spec>
<copy>
- Max two lines on screen at once; plain words before jargon.
- Never put the full voice line on screen; on-screen words are anchors.
- One name per thing, used every time.
- Every number has a source in SOURCES.md, or it goes.
</copy>
<sound>
- A tempo-locked procedural bed (Web Audio) with one motif that returns on the key idea.
- Soft UI cues only on actions that carry meaning; duck the bed under voice.
- About -16 LUFS integrated, true peak at most -1.5 dBTP. Check it muted and audio-only.
</sound>
<accessibility>
- Contrast at least 4.5:1; captions burned in and shipped as .srt.
- Color is never the only signal. No flashes above 3 per second.
- A reduced-motion cut that keeps the same sequence of ideas.
</accessibility>
<render_contract>
- window.seek(t) paints the frame at time t; every frame is a pure function of t.
- One TIMELINE object holds every beat, move and cue. Seeded randomness only.
- Headless Chrome steps t = n/60 and pipes frames to ffmpeg (libx264, crf 16, yuv420p).
</render_contract>
<workflow>
1. One-sentence idea and the viewer outcome.
2. Tokens. 3. directions.html with 3-4 directions; mark the winner and why.
4. Storyboard as a contact sheet. 5. Animatic and timing pass.
6. Full build. 7. Sound and captions. 8. Verification. 9. Export.
</workflow>
<verification>
Run these; do not just claim them.
- Render one frame twice and diff it: identical.
- A still at every beat; read every line at 390 px wide.
- Watch it muted, then listen audio-only.
- A design-review subagent asks her questions; an accessibility pass follows.
- Every fix ships with a before/after frame pair. [Dive Club]
</verification>
<delivery>
out/master_16x9.mp4, out/cut_9x16.mp4, out/cut_1x1.mp4, captions.srt, contact.png, source, and a README that lists only what was tested.
</delivery>
<autonomy>
Do not stop for approval on creative calls. Stop only for missing rights, unsafe content, or an ambiguity that changes the goal.
</autonomy>
</prompt>

---

2. 빈칸 4개 채우는 법

원문 안의 중괄호 4개만 바꾸면 돼요. 한국어로 써도 괜찮아요. 같은 빈칸이 여러 번 나오니 전부 같은 말로 바꾸세요.

• {{TOPIC}}: 영상 주제
• {{AUDIENCE}}: 보는 사람, 그리고 그 사람이 지금 믿고 있는 것
• {{OUTCOME}}: 다 보고 나서 할 수 있게 되는 것
• {{SECONDS}}: 길이(초). 30~90 사이로 쓰세요

영상에서 쓴 예시 (커피값 30년)

{{TOPIC}} = 하루 커피값 5,000원을 30년 모으면 얼마가 되는지 (한국어 영상)
{{AUDIENCE}} = 한국 사회초년생. 커피값 5,000원은 푼돈이라 모아 봤자 별것 없다고 믿는다
{{OUTCOME}} = 하루 5,000원도 30년이 쌓이면 얼마가 되는지 숫자로 말할 수 있다
{{SECONDS}} = 30

이렇게 넣었더니 결제 알림 하나가 하루 한 칸 → 365칸 달력 → 30년 막대로 이어지는 영상이 나왔어요.

---

3. 클로드 코드에서 돌리는 순서

1. 영상용 새 폴더를 만들고, 그 폴더에서 클로드 코드를 열어요.
2. 폴더 안에 brand, refs, screens 폴더를 만들고 로고·브랜드 색, 참고 영상 캡처, 실제 앱·사이트 화면을 넣어 두세요. 프롬프트가 이 폴더를 먼저 읽어요. 비어 있어도 돌아가지만, 넣어 줘야 AI 티가 덜 나요.
3. 모델은 가장 좋은 모델(Opus)로, 생각 수준은 가장 높게 두세요. 저희는 아래처럼 켰어요.

claude --model opus --effort xhigh

4. 빈칸 채운 프롬프트를 붙여 넣고 엔터. 중간에 승인을 물어보면 허용해 주세요.
5. 영상 파일(MP4)로 뽑으려면 컴퓨터에 Node.js와 ffmpeg가 있어야 해요. 없으면 클로드가 설치하자고 물어봐요.

끝나면 out 폴더에 가로(16:9)·세로(9:16)·정사각(1:1) 영상과 자막 파일이 생겨요.

---

4. 안에 든 방식 4가지

영상에서 짚은 4가지가 원문 어디에 있는지예요.

1. 스튜디오 통째로 맡기기: <role> “You are the whole studio: creative director, explainer writer, motion designer, sound designer and render engineer.”
2. 빈손으로 시작하지 않기: <principles> “Never start from nothing. Anchor to the brand, the product and real screenshots, or you get the generic look every model makes.”
3. 장면 대신 같은 물체 바꾸기: <motion_language> “Keep objects alive across scenes and transform them instead of replacing them.”
4. 다 만들고 직접 보고 듣기: <verification> “Watch it muted, then listen audio-only.” 저희 땐 클로드가 음성에서 ’푼돈’이 ’품돈’으로 들린다며 혼자 다시 녹음했어요.

---

⚠️ 꼭 알아 둘 것

• 클로드 코드는 유료 요금제(Pro 이상)나 API 키로 쓸 수 있어요.
• 같은 프롬프트라도 매번 결과가 달라요.

---

출처

• 프롬프트 제작: X @0xCarnagee. 이 설명 영상 버전은 @0xMovez 게시물 이미지(조회 60만)를 옮겨 적었어요.
• 원칙: 앤트로픽 클로드 코드 디자인 총괄 메건 최(Meaghan Choi)가 공개 강연·인터뷰(Behind the Craft, Dive Club 등)에서 밝힌 작업 방식이에요.