Prompt Engine
AgriciDaniel/claude-prompts
Ultimate AI prompt database and builder with 2,500+ curated prompts across 19 categories and 17 AI models (Midjourney, Flux, Leonardo AI, DALL-E, Sora, Imagen, Mystic, Stable Diffusion, Ideogram…
Advanced image prompt engineering assistant for Chinese-first users.
$ npx skills add TanShilongMario/PromptSkill4image --skill prompt-engineering -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install TanShilongMario/PromptSkill4image prompt-engineering --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "prompt-engineering" agent skill from https://github.com/TanShilongMario/PromptSkill4image/tree/main into .claude/skills/prompt-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add TanShilongMario/PromptSkill4image --skill prompt-engineering -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install TanShilongMario/PromptSkill4image prompt-engineering --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "prompt-engineering" agent skill from https://github.com/TanShilongMario/PromptSkill4image/tree/main into .agents/skills/prompt-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add TanShilongMario/PromptSkill4image --skill prompt-engineering -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install TanShilongMario/PromptSkill4image prompt-engineering --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "prompt-engineering" agent skill from https://github.com/TanShilongMario/PromptSkill4image/tree/main into .cursor/skills/prompt-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add TanShilongMario/PromptSkill4image --skill prompt-engineering -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install TanShilongMario/PromptSkill4image prompt-engineering --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "prompt-engineering" agent skill from https://github.com/TanShilongMario/PromptSkill4image/tree/main into .gemini/skills/prompt-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install TanShilongMario/PromptSkill4image prompt-engineeringInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add TanShilongMario/PromptSkill4image --skill prompt-engineering -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "prompt-engineering" agent skill from https://github.com/TanShilongMario/PromptSkill4image/tree/main into .github/skills/prompt-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add TanShilongMario/PromptSkill4image --skill prompt-engineering -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install TanShilongMario/PromptSkill4image prompt-engineering --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "prompt-engineering" agent skill from https://github.com/TanShilongMario/PromptSkill4image/tree/main into .opencode/skills/prompt-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
prompt-engineeringAdvanced image prompt engineering assistant for Chinese-first users.
Prompt Engineering is an agent skill from TanShilongMario/PromptSkill4image. Advanced image prompt engineering assistant for Chinese-first users. Turns any input into high-quality image-generation prompts: reverse-engineers prompts from images, expands rough prompts into structured prompts, translates/transwrites prompts, extracts reusable variables, suggests phrase banks, supports minimal prompts, and optionally exports PromptFill-compatible JSON.
Its SKILL.md is about 4.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `README.md`, `examples.md` and `vocabulary-banks.md`).
It sits in AI & LLM Engineering, covering Prompt engineering and Image generation. The repository describes itself as: 一个用于图像创作提示词分析、拆分、翻译、变量扩展的Skills. The licence is MIT.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 118e294. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and json).
From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
placehold.coFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Prompt Engineering loads about 4.2k tokens when it runs. Until then it costs about 99 tokens; SKILL.md has 1,458 words of instructions outside code blocks.
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.
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.
The full file from TanShilongMario/PromptSkill4image at commit 118e294, republished under its MIT licence (© TanShilongMario). 1,458 words, ~4,202 tokens.
.claude/skills/prompt-engineering/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.这是一个中文优先的 AI 图像提示词工程 Skill。它可以把图片、粗糙想法、短关键词、中文提示词、英文提示词或中英混合输入,转成可直接用于 AI 生图工具的高质量提示词。
This is a Chinese-first image prompt engineering skill. It turns images, rough ideas, keywords, Chinese/English prompts, and mixed drafts into high-quality image-generation prompts.
核心目标不是把所有内容都强行变成复杂模板,而是先理解用户真正想要什么,再输出最适合当前场景的提示词版本。
在写最终提示词前,先判断用户需求。
如果用户意图明确,直接执行;如果缺少的信息会显著影响结果,只问一个简短澄清问题。
默认判断:
{{variable_name}} 变量并提供词组建议。把用户请求归入以下一个或多个任务类型。
适用场景:
处理流程:
注意:不要声称可以还原图片的原始隐藏参数。应说明这是对画面的实用重构。
适用场景:
处理流程:
适用场景:
处理流程:
{{variable_name}}。优先输出结果,再解释原因。推荐顺序:
大多数情况下输出两个版本:
如果用户明确说“只要一句”“简单点”“不要结构化”,只输出极简增强版,加一条简短建议即可。
如果用户要求 PromptFill、模板、变量、JSON 或可导入格式,才输出结构化变量和 PromptFill JSON。
适合短提示词、快速试图、不喜欢复杂结构的用户。
格式:
[主体],[核心风格],[主要场景/构图],[光影或氛围],[质量/风格收尾]示例:
A cyberpunk girl in a rainy neon alley, cinematic lighting, high-detail portrait, shallow depth of field.默认推荐给大多数用户。
格式:
[主体和关键特征], [环境], [动作或姿态], [构图/镜头], [光影], [色彩], [风格], [质量细节], [必要时加入画幅比例]适合用户要求高级、模板化、商业级、可复用、PromptFill-ready 的场景。
格式:
主体:...
场景:...
构图:...
光影:...
色彩:...
风格:...
细节:...
质量:...
负面约束:...扩写或反推时,从以下维度中选择必要项,不要机械塞满所有维度。
核心维度:
subject:主体,人物、产品、物体、生物、地点或概念。action:动作、姿势、行为、互动。scene:场景、背景、环境。style:视觉风格、艺术流派、渲染风格、设计语言。视觉控制:
composition:版式、构图、画面布局。camera_angle:平视、低角度、俯视、特写、广角等。lighting:影棚柔光、电影感打光、霓虹灯光、黄金时刻、体积光。color_scheme:莫兰迪色、马卡龙、金红暖色、黑白高对比等。mood:宁静、戏剧化、奢华、未来感、可爱、神秘等。material:玻璃、金属、布料、木材、陶瓷、皮肤纹理、纸张颗粒等。render_quality:照片写实、超高细节、编辑大片、3D 渲染、概念艺术。aspect_ratio:1:1、16:9、9:16、4:3、3:2、21:9。常见图像类型:
只有当用户需要复用、替换、选择或做模板时,才使用变量。
语法:
{{variable_name}}{{variable_name: 默认值}}命名规则:
art_style、character_type、lighting、camera_angle、product_typecyberpunk、beautifulGirl、camera-angle分类:
character:人物、角色、生物、身体特征、表情。item:服装、道具、配饰、产品、材质。action:动作、姿势、手势、互动。location:地点、场景、背景环境。visual:风格、色彩、光影、构图、氛围。technical:镜头、相机、画幅比例、质量、渲染参数。other:其他无法归类的内容。提炼变量时,为重要变量提供 5-12 个候选词组。中文用户场景下,候选词组应尽量中英双语。
## 图像提示词
### 极简增强版
...
### 高级结构化版
...
### 画面要素
- 主体:...
- 场景:...
- 构图:...
- 光影:...
- 色彩:...
- 风格:...
### 进一步建议
- ...## 优化后的提示词
### 极简增强版
...
### 高级结构化版
...
### 为什么这样优化
- ...
### 进一步建议
- ...## 翻译转写结果
### 中文润色版
...
### 英文生图版
...
## 变量提炼
| 变量 | 当前值 | 类别 | 候选词组 |
|---|---|---|---|
| `art_style` | ... | visual | ... |
## 词组建议
### `{{art_style}}`
- 中文 / English
## 进一步建议
- ...仅当用户明确要求 PromptFill、JSON、模板导出或可导入格式时输出。
结构如下:
{
"id": "tpl_descriptive_name",
"name": { "cn": "中文模板名", "en": "English Template Name" },
"content": {
"cn": "{{art_style: 赛博朋克}}风格的{{character_type}}...",
"en": "{{art_style: Cyberpunk}} style {{character_type}}..."
},
"imageUrl": "https://placehold.co/600x400/png?text=Template",
"selections": {
"art_style": { "cn": "赛博朋克", "en": "Cyberpunk" }
},
"tags": ["人物", "摄影"],
"language": ["cn", "en"],
"banks": {
"art_style": {
"label": { "cn": "艺术风格", "en": "Art Style" },
"category": "visual",
"options": [
{ "cn": "赛博朋克", "en": "Cyberpunk" },
{ "cn": "蒸汽朋克", "en": "Steampunk" }
]
}
}
}规则:
id 使用 tpl_ 前缀。content 支持 {{variable}} 和 {{variable: 默认值}}。selections 为每个变量提供一个默认值。banks 为变量提供可选词库,包含 label、category、options。tags 描述内容主题,不要把“图片”“视频”当作主题标签。最终输出前检查:
在有帮助时,用简短建议结尾:
This skill turns almost any user input into a usable image-generation prompt. It supports image-to-prompt, rough-prompt expansion, prompt translation/transwriting, variable extraction, phrase suggestions, minimal prompts, structured prompts, and optional PromptFill JSON.
The primary goal is not to force every prompt into a complex template. The goal is to understand what the user wants, then output the strongest useful image prompt at the right level of complexity.
Always identify the user's actual need before writing the final prompt.
If the user's intent is clear, proceed directly. If the intent is ambiguous and the missing choice changes the output significantly, ask one short clarification question.
Default assumptions:
Classify the request into one or more of these tracks.
Use when:
Process:
Do not claim to recover the original hidden generation parameters. Say the result is a practical reconstruction.
Use when:
Process:
Use when:
Process:
{{variable_name}}.Always output the result before long analysis. Prefer this order:
For most users, produce two prompt versions:
If the user explicitly asks for only a short prompt, output only the minimal enhanced version plus one short improvement note.
If the user asks for PromptFill, template, variables, or JSON, include structured variables and optional PromptFill-compatible JSON.
Use for extremely short prompts, fast ideation, or users who prefer simple prompts.
Format:
[subject], [core style], [main scene/composition], [lighting or mood], [quality/style finish]Example:
A cyberpunk girl in a rainy neon alley, cinematic lighting, high-detail portrait, shallow depth of field.Use as the default for most users.
Format:
[subject with key traits], [environment], [action or pose], [composition/camera], [lighting], [color palette], [style], [quality details], [aspect ratio if relevant]Use when the user asks for advanced, template, repeatable, professional, commercial, or PromptFill-ready output.
Format:
Subject: ...
Scene: ...
Composition: ...
Lighting: ...
Color: ...
Style: ...
Details: ...
Quality: ...
Negative constraints: ...When expanding or reverse-engineering prompts, choose relevant dimensions from this list. Do not force all dimensions into every prompt.
Core:
subject: main person, product, object, creature, place, or conceptaction: pose, motion, behavior, interactionscene: location, background, environmentstyle: visual style, art movement, rendering style, design languageVisual control:
composition: layout, framing, spatial arrangementcamera_angle: eye-level, low angle, bird's-eye view, close-up, wide shotlighting: studio soft light, cinematic lighting, neon lighting, golden hour, volumetric lightcolor_scheme: muted tones, pastel palette, gold-red warm tones, black-and-white contrastmood: serene, dramatic, luxurious, futuristic, playful, mysteriousmaterial: glass, metal, fabric, wood, ceramic, skin texture, paper grainrender_quality: photorealistic, ultra-detailed, editorial, 3D render, concept artaspect_ratio: 1:1, 16:9, 9:16, 4:3, 3:2, 21:9Common image types, inspired by PromptFill templates:
Use variables only when the user benefits from reuse, selection, or customization.
Syntax:
{{variable_name}}{{variable_name: default value}}Naming:
art_style, character_type, lighting, camera_angle, product_typecyberpunk, beautifulGirl, camera-angleCategories:
character: people, roles, creatures, body traits, expressionsitem: clothing, props, accessories, products, materialsaction: actions, poses, gestures, interactionslocation: places, environments, background settingsvisual: style, color, lighting, composition, moodtechnical: camera, lens, aspect ratio, quality, render settingsother: anything that does not fit aboveWhen extracting variables, include 5-12 phrase suggestions for important variables when useful. Suggestions should be meaningfully different, bilingual when the user works in Chinese and English.
## Image Prompt
### Minimal Version
...
### Advanced Version
...
### Observed Elements
- Subject: ...
- Scene: ...
- Composition: ...
- Lighting: ...
- Color: ...
- Style: ...
### Further Suggestions
- ...## Enhanced Prompt
### Minimal Version
...
### Advanced Version
...
### Why This Works
- ...
### Further Suggestions
- ...## Transwritten Prompt
### Chinese
...
### English
...
## Variables
| Variable | Current Value | Category | Suggestions |
|---|---|---|---|
| `art_style` | ... | visual | ... |
## Phrase Suggestions
### `{{art_style}}`
- 中文 / English
## Further Suggestions
- ...Only include this when the user asks for PromptFill, JSON, template export, or importable format.
Use this shape:
{
"id": "tpl_descriptive_name",
"name": { "cn": "中文模板名", "en": "English Template Name" },
"content": {
"cn": "{{art_style: 赛博朋克}}风格的{{character_type}}...",
"en": "{{art_style: Cyberpunk}} style {{character_type}}..."
},
"imageUrl": "https://placehold.co/600x400/png?text=Template",
"selections": {
"art_style": { "cn": "赛博朋克", "en": "Cyberpunk" }
},
"tags": ["人物", "摄影"],
"language": ["cn", "en"],
"banks": {
"art_style": {
"label": { "cn": "艺术风格", "en": "Art Style" },
"category": "visual",
"options": [
{ "cn": "赛博朋克", "en": "Cyberpunk" },
{ "cn": "蒸汽朋克", "en": "Steampunk" }
]
}
}
}Rules:
id starts with tpl_.content may use {{variable}} or {{variable: inline default}}.selections contains one default value per variable.banks contains reusable options with label, category, and options.Before finalizing, check:
End with practical next steps when helpful:
© TanShilongMario, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 5 other files in the repository root of TanShilongMario/PromptSkill4image.
Open the folder on GitHubat commit 118e294
Prompt Engineering 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Prompt Engineering this skillTanShilongMario/PromptSkill4image | 135 | — | ~4.2k | Automated safety check: Pass | MIT | |
| Prompt EngineAgriciDaniel/claude-prompts | 111 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Image Ad Clonekrusemediallc/arcads-claude-code | 1.6k | — | ~2.4k | Automated safety check: Notes | MIT | |
| AI Image Prompts SkillLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.3k | Automated safety check: Pass | MIT | |
| Flux2 Klein PromptingAnastasiyaW/codex-claude-code-config | 154 | — | ~2.8k | Automated safety check: Pass | MIT | |
| Image to Prompt Reverse Engineeringwuyoscar/GPT-Image2-Skill | 5.7k | — | ~1.8k | Automated safety check: Pass | MIT |
AgriciDaniel/claude-prompts
Ultimate AI prompt database and builder with 2,500+ curated prompts across 19 categories and 17 AI models (Midjourney, Flux, Leonardo AI, DALL-E, Sora, Imagen, Mystic, Stable Diffusion, Ideogram…
krusemediallc/arcads-claude-code
A skill your agent uses when the user wants to reverse-engineer an existing image ad into a reusable prompt template.
LeoYeAI/openclaw-master-skills
Recommend curated prompts from a 10,000+ real-world image generation prompt library.
AnastasiyaW/codex-claude-code-config
Expert prompt engineering for FLUX.2 [klein] image generation and editing model.
wuyoscar/GPT-Image2-Skill
Analyzes a reference image and writes a prompt that could recreate it in an AI image generator, focusing on the visual traits that most affect similarity.
renmu2017/Hell-Grind-AIGC-Skill
Model-agnostic workflow for AI image and video projects: prompt writing, tracking of assets and shots, continuity checks and diagnosis of failed generations.
Categories
Advanced image prompt engineering assistant for Chinese-first users. Prompt Engineering is an agent skill from TanShilongMario/PromptSkill4image. Advanced image prompt engineering assistant for Chinese-first users.
Prompt Engineering fits situations like: tasks that involve Prompt engineering; tasks that involve Image generation.
Run `npx skills add TanShilongMario/PromptSkill4image --skill prompt-engineering -a claude-code`. Or copy the skill folder (the TanShilongMario/PromptSkill4image repository) into .claude/skills/prompt-engineering in your project. Claude Code loads it when a task matches its description.
Run `npx skills add TanShilongMario/PromptSkill4image --skill prompt-engineering -a codex`. Or copy the skill folder (the TanShilongMario/PromptSkill4image repository) into .agents/skills/prompt-engineering in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TanShilongMario/PromptSkill4image --skill prompt-engineering -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prompt-engineering, .gemini/skills/prompt-engineering, .github/skills/prompt-engineering and .opencode/skills/prompt-engineering in your project.
SKILL.md names no scripts, command-line tools or credentials: Prompt Engineering is instructions for the agent only.
SKILL.md names 1 domain. In commands or code: placehold.co; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
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.
Prompt Engineering is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.2k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Prompt Engineering: Prompt Engine (AgriciDaniel/claude-prompts, 111 stars), Image Ad Clone (krusemediallc/arcads-claude-code, 1.6k stars), AI Image Prompts Skill (LeoYeAI/openclaw-master-skills, 2.2k stars) and Flux2 Klein Prompting (AnastasiyaW/codex-claude-code-config, 154 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
TanShilongMario (a GitHub user) maintains it in TanShilongMario/PromptSkill4image, which has 135 GitHub stars. The repository was last updated on May 17, 2026.
Source: TanShilongMario/PromptSkill4image on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.