/ 디렉터리 / 플레이그라운드 / banana-claude
← 모든 서버 ↗ GitHub
● 커뮤니티 AgriciDaniel ⚡ 바로 사용

banana-claude

제작: AgriciDaniel · AgriciDaniel/banana-claude

AI image generation skill for Claude Code — a creative director powered by Gemini that prompts the model so you don't have to.

Banana Claude turns Claude Code into a creative director for AI images. You describe the shot at a high level; the skill expands it into a Gemini-ready prompt with composition, lighting, and style directives, then calls Gemini to render. Good for hero images, social cards, and brand-consistent stills.

▶ 데모 보기 📦 설치 💡 사용 사례

왜 쓰나요

핵심 기능

라이브 데모

실제 사용 모습

banana-claude-skill.replay ▶ 준비됨
0/0

설치

작성자 저장소 · Claude Skills 공식 문서

사용 사례

실전 활용법: banana-claude

How to generate a hero image for a blog post

👤 Writers and marketers who want one-shot polished hero images ⏱ ~5 min beginner

언제 쓸까: You have a post title and a vibe in mind — you need one hero image in the next 2 minutes.

흐름
  1. Describe the shot
    Banana Claude: hero image for 'The 2AM Bug That Cost Us $40k' — moody, cinematic, developer at a laptop lit by monitor glow.✓ 복사됨
    → Expanded prompt with lens/lighting details echoed back
  2. Review and generate
    Generate 2 variants and save to assets/hero-2am-bug.png✓ 복사됨
    → Two PNGs with different takes on the brief

결과: A hero image that looks commissioned, not generated.

함정
  • All outputs share a 'Gemini look' — Add a style anchor — 'in the style of Annie Leibovitz portraits' — to break the default
함께 쓰기: smart-illustrator-skill

Generate a brand-consistent social image pack

👤 Solo marketers maintaining a consistent feed look ⏱ ~15 min beginner

언제 쓸까: You need 6-10 images that feel like they belong together.

사전 조건
  • Brand style notes (palette, mood) — Write 3-5 lines; skill uses as style guardrail
흐름
  1. Lock a style anchor
    My brand style: muted pastels, isometric, soft shadows. Lock that as the anchor for the session.✓ 복사됨
    → Skill confirms and echoes the anchor
  2. Iterate per post
    Now generate images for these 6 post titles using the anchor.✓ 복사됨
    → 6 on-brand images

결과: A cohesive image set ready for a week of posts.

함정
  • Drift after image 3 — Re-state the anchor every 2-3 generations; Gemini's context on image specifics is fuzzy
함께 쓰기: ai-marketing-claude-code-skill

조합

다른 MCP와 조합해 10배 효율

banana-claude-skill + smart-illustrator-skill

Banana for hero/brand images, Smart Illustrator for in-article diagrams

For posts/launch.md: banana-claude for the hero, smart-illustrator for the architecture diagrams inside.✓ 복사됨
banana-claude-skill + ai-marketing-claude-code-skill

Marketing skill plans the campaign; Banana renders the creative

Draft a 7-post launch campaign with the marketing skill, then generate hero images for each with banana-claude.✓ 복사됨

도구

이 MCP가 노출하는 것

도구입력언제 호출비용
expand_brief brief: str, style_anchor?: str Before generating, to build a rich prompt ~1k Claude tokens
generate_image prompt: str, variants?: int, out_path?: str After brief expansion approved 1 Gemini call per variant
save_template name, prompt When a prompt pattern produces consistent wins 0

비용 및 제한

운영 비용

API 쿼터
Gemini free tier: 15 req/min, 1500/day
호출당 토큰
1-3k Claude tokens for prompt expansion
금액
Free on Gemini free tier; ~$0.04/image on paid tier
팁
Save winning prompts as templates to avoid re-paying for expansion calls.

보안

권한, 시크릿, 파급범위

자격 증명 저장: GEMINI_API_KEY in env
데이터 외부 송신: All briefs and outputs go to Google Gemini

문제 해결

자주 발생하는 오류와 해결

Gemini returns blurry/low-quality image

Include a resolution and aspect-ratio hint in the brief; ask for 'photographic, high detail, 4K'

Safety filter blocks the generation

Simplify the brief; remove ambiguous references to people or brands

대안

banana-claude 다른 것과 비교

대안언제 쓰나단점/장점
smart-illustrator-skillYou need diagrams and covers with position detection, not just stillsLess hand-holding on the creative brief
Midjourney / SoraYou need higher-end fidelitySeparate UI, no Claude integration

더 보기

리소스

📖 GitHub에서 공식 README 읽기

🐙 열린 이슈 보기

🔍 400+ MCP 서버 및 Skills 전체 보기