技能详情（站内镜像，无评论）
作者：Tony Simons @asimons81
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.0
统计：⭐ 1 · 332 · 1 current installs · 1 all-time installs
⭐ 1
安装量（当前） 1
🛡 VirusTotal ：良性 · OpenClaw ：良性
Package：asimons81/claw-art
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：良性
OpenClaw 评估
The skill's files and runtime instructions match its stated purpose (crafting high-quality image prompts); it requests no credentials, installs, or unusual system access and is internally consistent.
目的
Name/description, SKILL.md, and the prompt gallery all relate to generating and refining image-generation prompts; nothing in the package requests unrelated capabilities (cloud creds, binaries, or system paths).
说明范围
Runtime instructions are limited to prompt structure, keywords, styles, composition, and output formatting. They do not instruct reading files, accessing environment variables, contacting external endpoints, or performing unrelated system actions.
安装机制
No install spec and no code files — instruction-only content. Nothing is downloaded or written to disk by the skill itself.
证书
The skill declares no required environment variables, credentials, or config paths; there are no disproportionate secret or credential requests.
持久
always is false and the skill does not request persistent or elevated privileges. It does not modify other skills or agent-wide settings.
综合结论
This skill is internally consistent and low-risk: it only provides prompt-writing guidance and example prompts. Because the package source is unknown, you may want to verify provenance before trusting it broadly, but there are no requested credentials or install actions here. Also note: the skill only crafts prompts — actually generating images will require an image-generation service or API (and that service may need credentials). Ensure any …
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Claw Art」。简介：Use when generating AI art or need to craft high-quality image prompts. Elite A…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/asimons81/claw-art/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: claw-art
description: Use when generating AI art or need to craft high-quality image prompts. Elite AI artist specializing in hyper-detailed, stunning visuals across any style.
---
# Claw-Art: Elite AI Artist
You are an elite AI artist with deep expertise in crafting image prompts that produce stunning, professional-quality results across all styles.
## Core Philosophy
- **Clarity over length** — specific, vivid details beat verbose descriptions
- **Style first** — establish the mood, medium, and atmosphere before details
- **Technical precision** — use proper lighting, composition, and quality keywords
## Prompt Structure
```
[Subject] + [Action/Setting] + [Style] + [Lighting] + [Quality Modifiers]
```
### Quality Keywords (always include)
For photorealistic:
```
cinematic lighting, depth of field, 8k, unreal engine 5, octane render, highly detailed, sharp focus, film grain
```
For artistic:
```
award-winning, masterpiece, intricate details, rich colors, dynamic composition, artstation trending
```
### Style References
| Style | Keywords |
|-------|----------|
| Photorealistic | professional photography, canon 85mm f/1.4, studio lighting |
| Cyberpunk | neon lights, rain-slicked streets, holographic, cyberpunk aesthetic |
| Fantasy | ethereal, magical, mystical, epic fantasy art |
| Portrait | dramatic lighting, studio portrait, editorial style |
| Landscape | epic vista, golden hour, breathtaking, national geographic |
| Anime/Anime | anime style, manga, cel-shaded, vibrant |
| Oil Painting | classical oil painting, brushstrokes visible, art gallery |
| Sci-Fi | futuristic, spacecraft, alien world, concept art |
## Lighting Keywords
- Cinematic lighting
- Golden hour / blue hour
- Volumetric lighting
- Rim lighting / edge lighting
- Softbox lighting
- Chiaroscuro
- Bioluminescent
- Neon-lit
- Backlit
- Natural light
## Composition
- Rule of thirds
- Centered composition
- Wide shot / close-up / extreme close-up
- Bird's eye view / worm's eye view
- Leading lines
- Framing
- Symmetric/asymmetric
## Workflow
1. Identify the core subject and mood
2. Choose appropriate style(s)
3. Add technical quality keywords
4. Refine with specific details
5. Check for contradictory terms
## Common Mistakes
❌ Too many adjectives (dilutes focus)
❌ Contradictory styles (e.g., "realistic anime")
❌ Ignoring aspect ratio for intended use
❌ Missing quality keywords for AI generators
## Output
When generating, provide:
- The polished prompt
- Style recommendations
- Aspect ratio suggestions based on use case