Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add modu-ai/moai-cowork/plugin install moai-mediaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/modu-ai/moai-cowork/media-gemini-3-image-prompt)<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/media-gemini-3-image-prompt"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/media-gemini-3-image-prompt/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/media-gemini-3-image-prompt"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/media-gemini-3-image-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00307 | $0.03684 |
| Opus 5 | $0.00153 | $0.01842 |
| Sonnet 5 | $0.00061 | $0.00737 |
| Haiku 4.5 | $0.00031 | $0.00368 |
Grade A, and why
media-gemini-3-image-prompt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini 3 Pro Image Prompt Builder — 5-Component + 3-모델 동시 출력
moai-coworker | 이미지 프롬프트 빌더 (텍스트 산출 전용)
개요
Gemini 3 Pro Image (Nano Banana Pro)는 Google DeepMind의 reasoning-driven 이미지 생성·편집 모델로, Thinking Mode, Perfect Text Rendering, Search Grounding (Google Search 연동), Few-Shot Design (최대 14개 reference 이미지)을 지원합니다. 자연어 프롬프트 어조는 Creative Director가 장면을 지시하는 톤이 가장 잘 동작합니다.
본 스킬은 사용자 한 줄 요청을 Google AI for Developers 공식 가이드의 5-component 구조로 변환합니다:
[Subject + Adjectives] doing [Action] in [Location/Context].
[Composition/Camera]. [Lighting/Atmosphere]. [Style/Media].
[Specific Constraint/Text]
각 component는 영문 문장으로 끝나며 마침표로 구분합니다. 키워드 나열식은 동작하지만 결과 품질이 떨어집니다.
특히 본 스킬은:
- 3개 모델 동시 출력: Gemini 5-component 메인 + GPT-image-2(6-Block) + Midjourney v8.1(키워드+파라미터)
- 프리셋 + 미세조정: 4개 프리셋(제품샷·인물·일러스트·풍경) × 4 슬롯
- Thinking vs Fast 모드 안내: 복잡 구도·텍스트는 Thinking, 빠른 탐색은 Fast (Gemini 3.1 Flash Image)
- 카메라 하드웨어 지정: GoPro · Fujifilm · disposable · iPhone 등 시각적 DNA를 결정하는 하드웨어 지시
페어 스킬 media-higgsfield-image(Higgsfield MCP — Nano Banana Pro 포함 11개 이미지 모델)가 실제 이미지를 생성하고, 본 스킬은 프롬프트 텍스트만 산출합니다.
트리거 키워드
Gemini 이미지 프롬프트 나노바나나 프롬프트 Nano Banana Pro 프롬프트 Gemini 3 Pro Image 프롬프트 Google AI Studio 이미지 Vertex AI 이미지 프롬프트 SynthID
워크플로우
사용자 자연어 한 줄
↓
[Round 1] AskUserQuestion — 프리셋 선택 (제품샷·인물·일러스트·풍경)
↓
[Round 2] AskUserQuestion — 프리셋별 미세조정 (3~4 슬롯)
↓
[Round 3] AskUserQuestion — 화면비 + 이미지 내 텍스트 유무 + 카메라 하드웨어(선택)
↓
[내부] 슬롯 → 5-component 매핑
↓
[내부] 같은 슬롯 → GPT 6-Block + MJ 키워드+파라미터 변환
↓
출력: 3개 모델 프롬프트 코드블록 + 권장 파라미터 + 한국어 해설
실행 규칙
Round 1 — 프리셋 선택 (필수)
AskUserQuestion을 호출해 4개 프리셋 중 1개를 선택받습니다.
프리셋 슬롯 정의는 3개 이미지 프롬프트 빌더(gpt-image-2·gemini·midjourney)가 공유하는 단일 원본을 사용합니다. 원본은 media-gpt-image-2-prompt 스킬에 있으며, 각 프리셋 파일 안에 GPT·Gemini·Midjourney 세 모델의 어조 변환 가이드가 모두 포함되어 있습니다.
| 프리셋 | 적용 케이스 | 공유 슬롯 원본 |
|---|---|---|
| 제품샷 (권장) | 커머스 상품, 패키지 컷, 보석·시계 클로즈업 | ${CLAUDE_PLUGIN_ROOT}/skills/media-gpt-image-2-prompt/presets/product-shot.md |
| 인물·캐릭터 | 인물 포트레이트, 페르소나, 광고 모델 | ${CLAUDE_PLUGIN_ROOT}/skills/media-gpt-image-2-prompt/presets/portrait.md |
| 일러스트·아트 | 카드뉴스 일러스트, 책 표지, 컨셉 아트 | ${CLAUDE_PLUGIN_ROOT}/skills/media-gpt-image-2-prompt/presets/illustration.md |
| 풍경·환경 | 배경 이미지, 시네마틱 배경, 여행 컷 | ${CLAUDE_PLUGIN_ROOT}/skills/media-gpt-image-2-prompt/presets/landscape.md |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 234 lines · 307 tokens per session scan A b09702686439
media-gemini-3-image-prompt is a skill published in the GitHub repository modu-ai/moai-cowork (300 stars, last pushed 9d ago), licensed Apache-2.0. It adds 307 tokens to every session and 3,684 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
market-intelligence-report
Produce a Market Intelligence Report — YouTube competitive research, channel analysis, content gap discovery, idea generation, daily scanning, and AI trend scouting — then render it as a BenAI-branded HTML dashboard in the instant-ui design language. Use this skill whenever the user says "market intelligence report"…
linkedin-writer-vault
Vault-aware LinkedIn writer. Same step-by-step LinkedIn post process as linkedin-writer, but ICP, voice, and offer context come from the vault's Context/ folder instead of being bundled inside the skill. Update one file in the vault and every skill pointing to it inherits the change. TRIGGERS: LinkedIn post, LinkedIn…
marketing-os-carousel
Build an image-first social carousel from an asset already filed in the Marketing OS, export it as a PDF, and record it back as a real channel asset. Brand palette, typography, the logo pointer and the never-black-background rule all resolve from Context/brand/brand-kit.md. Source is a filed newsletter edition…
operator
Build and schedule a personalized Operator prompt that runs a Baalda vault as a second brain on a recurring cadence. Run it from inside the vault: it reads Context/ and CLAUDE.md first to infer org, team, brand voice and paths, then asks only the gaps (cadence, connectors, DM recipient, budgets, signature), writes the…
crm-prospect-mining
Mine high-value prospects from CRM pipeline stages (Lost, No Show, Churned, Stalled) by cross-referencing records with LinkedIn company data and comms history. Connects to any CRM, pulls records from target stages, filters out personal email domains, finds company LinkedIn pages via web research, bulk-scrapes company…
seo-hreflang
Hreflang and international SEO audit, validation, and generation. Detects common mistakes, validates language/region codes, and generates correct hreflang implementations for HTML, HTTP headers, and XML sitemaps. Use when user says "hreflang", "i18n SEO", "international SEO", "multi-language", "multi-region"…