← 返回 Skills 市场
ckchzh

Image Prompt

作者 BytesAgain2 · GitHub ↗ · v2.1.0 · MIT-0
cross-platform ✓ 安全检测通过
654
总下载
0
收藏
8
当前安装
14
版本数
在 OpenClaw 中安装
/install image-prompt
功能描述
AI image prompt optimizer. Generate and enhance prompts for Midjourney, DALL-E, and Stable Diffusion. Includes prompt enhancement.
使用说明 (SKILL.md)

🎨 Image Prompt — AI Art Prompt Generator & Optimizer

Turn a vague idea into a detailed, production-ready image prompt. Built-in word banks for styles, lighting, composition, and quality modifiers — just provide a subject and go.

Commands

generate \x3Csubject>

Build a full image prompt from a subject. Randomly picks style, lighting, composition, and quality tags from the internal word bank to create a ready-to-use prompt.

image-prompt generate "a fox in a forest"

style \x3Csubject> \x3Cstyle>

Generate a prompt locked to a specific art style. Supported styles:

  • photorealistic — hyperrealistic photography look
  • anime — Japanese animation aesthetic
  • oil-painting — classical oil on canvas
  • watercolor — soft watercolor washes
  • pixel-art — retro pixel graphics
  • 3d-render — Blender/Octane 3D style
  • sketch — pencil/charcoal drawing
image-prompt style "mountain village" watercolor

enhance \x3Cprompt>

Take an existing prompt and upgrade it with quality boosters, detail tags, and a matching negative prompt suggestion.

image-prompt enhance "a cat sitting on a windowsill"

negative

Print a curated list of commonly used negative prompt terms, grouped by category (anatomy, quality, style, artifacts).

image-prompt negative

template \x3Ctype>

Get a fill-in-the-blank prompt template for a specific genre. Available types:

  • portrait — character/person focus
  • landscape — scenery and environments
  • product — commercial product shots
  • food — food photography
  • architecture — buildings and interiors
  • fantasy — fantasy/sci-fi illustration
image-prompt template portrait

random

Roll the dice — generates a completely random creative prompt by combining random subjects, styles, lighting, and composition from the word bank.

image-prompt random

translate \x3Cchinese_description>

Convert a Chinese-language description into an English image prompt with appropriate tags.

image-prompt translate "一只猫坐在樱花树下"

save \x3Cname> \x3Cprompt>

Save a prompt to your local library for later reuse.

image-prompt save hero-shot "a knight standing on a cliff, dramatic lighting, cinematic, 8k"

list

Show all prompts saved in your local library.

image-prompt list

search \x3Ckeyword>

Search your saved prompts by keyword.

image-prompt search knight

help

Show the help message with all available commands.

version

Print the current version number.

Examples

Basic generation:

$ image-prompt generate "an astronaut"
🎨 Prompt:
an astronaut, digital painting style, volumetric lighting, rule of thirds composition,
intricate details, sharp focus, 8k resolution, trending on artstation

📛 Negative:
blurry, low quality, deformed, watermark, text, signature

Styled output:

$ image-prompt style "cherry blossom garden" anime
🎨 Prompt:
cherry blossom garden, anime style, cel shading, vibrant colors, soft ambient lighting,
wide angle composition, detailed background, studio ghibli inspired, high quality anime art

📛 Negative:
photorealistic, 3d render, blurry, low quality, deformed

Enhancing an existing prompt:

$ image-prompt enhance "a dragon flying over a castle"
🎨 Enhanced Prompt:
a dragon flying over a castle, epic scale, dramatic rim lighting, aerial perspective,
intricate scales and details, sharp focus, 8k resolution, cinematic color grading,
volumetric clouds, masterpiece quality, trending on artstation

📛 Suggested Negative:
blurry, low quality, deformed, watermark, text, bad anatomy, disfigured

Random prompt:

$ image-prompt random
🎨 Random Prompt:
a mechanical owl perched on ancient ruins, steampunk style, golden hour lighting,
centered composition, intricate gears and clockwork, highly detailed, 4k wallpaper,
concept art

📛 Negative:
blurry, low quality, deformed, watermark, text, signature

Configuration

Variable Default Description
IMAGE_PROMPT_DIR $HOME/.image-prompt Base directory for saved prompts and history

The data directory is created automatically on first run.

Data Storage

All data is kept under $HOME/.image-prompt/ (or the path set via IMAGE_PROMPT_DIR):

~/.image-prompt/
├── prompts.txt      # saved prompts (one per line: name|prompt)
└── history.log      # command usage log

Prompts are stored as plain text — easy to back up, grep, or move between machines.

Powered by BytesAgain | bytesagain.com | [email protected]

安全使用建议
This skill appears to be a straightforward, local prompt generator and manager. It stores prompts and a usage log under ~/.image-prompt (or the path you set in IMAGE_PROMPT_DIR) — review those files if you are concerned about sensitive content being saved. No credentials or network endpoints were found in the provided files, but if you rely on the translate command or any later edits to the script, double-check the full script for any network calls (curl/wget/ssh) before installing. As always, inspect the included script yourself if you want to be certain there are no unexpected remote calls or modifications.
功能分析
Type: OpenClaw Skill Name: image-prompt Version: 2.1.0 The image-prompt skill is a straightforward utility for generating and managing AI image prompts. The bash script (scripts/script.sh) implements local storage for prompts and history within the user's home directory (~/.image-prompt/) and contains no network activity, obfuscation, or attempts to access sensitive system files. All functionality, including the Chinese-to-English keyword translation and prompt enhancement, is handled through local logic and predefined word banks as described in SKILL.md.
能力评估
Purpose & Capability
Name/description (image prompt generation and enhancement) align with the included script and SKILL.md. The script implements word banks, style presets, prompt generation/enhancement, saving, listing, and logging — all expected for this utility. No unrelated credentials, binaries, or cloud access are requested.
Instruction Scope
SKILL.md and the script operate on local data and print prompts; they reference only the declared local data directory (IMAGE_PROMPT_DIR / $HOME/.image-prompt). Commands and file accesses in the script are limited to creating/reading/writing the prompts file and history log. I saw no instructions that read unrelated system files or access external endpoints in the provided content.
Install Mechanism
No install spec is present (instruction-only style plus a bundled script). Nothing is downloaded or written outside the user's data directory by the script. This is the lower-risk pattern for skills.
Credentials
The skill requires no environment variables or credentials; it optionally honors IMAGE_PROMPT_DIR to change the local data path. That is proportionate to a local prompt-management tool.
Persistence & Privilege
The skill does not set always: true and does not request elevated privileges. It writes only to its own data directory (~/.image-prompt by default) and does not modify other skills or system-wide agent settings in the visible code.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install image-prompt
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /image-prompt 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v2.1.0
v2.1.0: Real AI image prompt generator with style presets, word banks, templates, and prompt library.
v2.0.1
update
v2.0.0
v2.5 standard: Use-when desc, homepage, source, security fix
v2.4.5
yaml-fix+quality
v2.4.4
yaml-fix+quality
v2.4.3
Quality upgrade
v2.4.2
Quality upgrade: custom functionality
v2.4.1
Quality update: docs, examples, standards compliance
v2.4.0
Fixed: aligned documentation with implementation, added missing commands
v2.3.0
Quality fixes: removed third-party references, aligned docs with implementation
v2.2.0
Enhanced descriptions for better AI triggering
v1.0.2
Runtime fix
v1.0.1
- Removed the tips.md file containing additional tips and guidance. - Core skill functionality remains unchanged; documentation is now more focused.
v1.0.0
- Initial release of image-prompt, an AI image prompt optimizer for popular platforms. - Supports prompt generation and enhancement for Midjourney, DALL-E, and Stable Diffusion. - Provides commands for style reference, negative prompt creation, and batch variant generation. - Includes a prompt formula and platform-specific guidance for crafting effective prompts.
元数据
Slug image-prompt
版本 2.1.0
许可证 MIT-0
累计安装 9
当前安装数 8
历史版本数 14
常见问题

Image Prompt 是什么?

AI image prompt optimizer. Generate and enhance prompts for Midjourney, DALL-E, and Stable Diffusion. Includes prompt enhancement. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 654 次。

如何安装 Image Prompt?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install image-prompt」即可一键安装,无需额外配置。

Image Prompt 是免费的吗?

是的,Image Prompt 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Image Prompt 支持哪些平台?

Image Prompt 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Image Prompt?

由 BytesAgain2(@ckchzh)开发并维护,当前版本 v2.1.0。

💬 留言讨论