Image Prompt
图像提示词工程师——专为 GPT Image 和 Nano Banana Pro 两款模型生成、编辑和反推图像提示词。当用户提到以下任何情形时立即触发:需要生成图片提示词、出图、反推图片/提示词、图像编辑提示词、帮我改图、image prompt、generate prompt、reverse prompt、edit image prompt。即使用户只是说"帮我出一张图的提示词"或"这张图的提示词是什么",也应立即介入。支持三条路径:(1) 生成——根据用户描述生成对应模型格式的英文提示词;(2) 编辑——结合用户提供的图像与修改需求,生成图像编辑提示词;(3) 反推——分析用户提供的图像,输出结构化解读与对应提示词。所有提示词用英文输出,附简短中文使用建议。
Install
npx skills add GAGAA-HUE/ASHUO-claude-skills --skill image-promptgit clone --depth 1 https://github.com/GAGAA-HUE/ASHUO-claude-skills.git /tmp/ASHUO-claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/ASHUO-claude-skills/image-prompt ~/.claude/skills/image-promptPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# 图像提示词工程师(Image Prompt Engineer) ## 角色定位 你是专注于 GPT Image 和 Nano Banana Pro 两款模型的提示词专家。你的任务是根据用户需求,输出**可直接复制使用的英文提示词**,并附上针对目标模型的简短中文使用建议。 所有输出提示词必须是完全自洽的独立文本——脱离当前对话也能直接使用,禁止出现"比刚才更亮""延续前面的风格"等依赖上下文的表述。 --- ## 第一步:判断路径与目标模型 收到用户请求后,先确认两件事: **路径判断(按以下优先级):** - 用户提供了图像 + 有修改需求 → **编辑路径** - 用户提供了图像 + 无修改需求(或说"反推")→ **反推路径** - 用户描述需求但无图像 → **生成路径** **模型判断:** - 用户在请求中提到了 GPT Image / GPT / nano banana / nano banana pro 等 → 直接使用该模型 - 未提及目标模型 → 主动询问:"你要用 GPT Image 还是 Nano Banana Pro?" --- ## 路径一:生成提示词 用户给出想要的图像描述,你据此生成对应格式的英文提示词。 ### GPT Image 格式 GPT Image 是指令跟随型模型,用完整的英文句子描述,不堆砌 tag。结构顺序: ``` [Subject + key attributes] [Action/Pose] in [Scene/Environment]. [Composition/Camera angle]. [Lighting & atmosphere]. [Style/Medium]. [Exact on-image text if any]. [Aspect ratio]. ``` **要点:** - 主体描述要具体:不写"beautiful woman",写"a woman in her 30s wearing a cream-colored wool coat" - 场景交代清楚时间、地点、天气/光线 - 风格词放在主体和场景之后 - 复杂场景注意控制细节层数,避免触发噪点/脏乱笔触(GPT Image 在超复杂场景下容易出现此类问题) - 如画面需要文字,直接写入提示词,GPT Image 对文字渲染支持好 ### Nano Banana Pro 格式 Nano Banana Pro 使用 art director brief 风格,按以下 6 层顺序组织:
Details
- Skill name
image-prompt- Repository
- GAGAA-HUE/ASHUO-claude-skills
- Path
image-prompt/SKILL.md- Repo updated
- 3 November 2026
FAQ
What does the Image Prompt skill do?
图像提示词工程师——专为 GPT Image 和 Nano Banana Pro 两款模型生成、编辑和反推图像提示词。当用户提到以下任何情形时立即触发:需要生成图片提示词、出图、反推图片/提示词、图像编辑提示词、帮我改图、image prompt、generate prompt、reverse prompt、edit image prompt。即使用户只是说"帮我出一张图的提示词"或"这张图的提示词是什么",也应立即介入。支持三条路径:(1) 生成——根据用户描述生成对应模型格式的英文提示词;(2) 编辑——结合用户提供的图像与修改需求,生成图像编辑提示词;(3) 反推——分析用户提供的图像,输出结构化解读与对应提示词。所有提示词用英文输出,附简短中文使用建议。
How do I install the Image Prompt skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add GAGAA-HUE/ASHUO-claude-skills --skill image-prompt. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Image Prompt popular?
It lives in GAGAA-HUE/ASHUO-claude-skills, which has 5 GitHub stars and 2 forks.
Related skills
Domain Modeling
5GAGAA-HUE/ASHUO-claude-skills
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
Git Guardrails Claude Code
5GAGAA-HUE/ASHUO-claude-skills
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
Setup Pre Commit
5GAGAA-HUE/ASHUO-claude-skills
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
Lira Image Prompts
5GAGAA-HUE/ASHUO-claude-skills
Lira — a master-level prompt-optimization persona for AI IMAGE generation. Use this skill WHENEVER the user wants to write, fix, optimize, or iterate an image-generation prompt — Higgsfield Soul 2.0 / Cinema Studio AI Cast (characters), Higgsfield Soul Cinema (locations/cinematic stills), frame edits via Nano Banana Pro (NBP, always first: post-processing of an original), Seedream 4.5 (texture-slop cleanup only), GPT Image 2 (last resort: finest local micro-edits, location view changes), or any text-to-image / image-edit task. Trigger it for requests like "a prompt for Soul Cinema", "make an N
Handdrawn Live Video Generator
5GAGAA-HUE/ASHUO-claude-skills
For creators making surreal short videos that blend rough glowing hand-drawn animation with live-action spaces. Users provide a scene idea, contact object or hand, desired mood, and optional language or style constraints. The Skill clarifies the physical contact, designs continuous morphing, escape route, and delayed handheld chase movement, then writes a reusable 15-second 16:9 video prompt in the user's language. After user confirmation it recommends MiniMax H3 generation and checks contact realism, camera delay, rough glowing stroke texture, and non-horror tone. Best for single-scene creati
Music Video Subtitle Generator
5GAGAA-HUE/ASHUO-claude-skills
For musicians, video creators, and social-media editors producing AI music videos or emotional short films with lyric typography. Users provide music, lyrics, references, characters, typography direction, mood, or target platform. The Skill analyzes beat and vocal timing, separates character, scene, and text references, designs beat-reactive spatial typography, decomposes long works into connected shots, audits prompts, and routes generation for H3 or other video tools. It outputs MV concepts, shot prompts, lyric text plans, and stitching guidance. Best for stylized MVs and subtitle-driven mus
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.