用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/tomevault-io/skills-registry --skill prompt-engine命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
| Use when this capability is needed.
> Use when this capability is needed.
Review architecture and API design for the vfs-s3 project. Use when the user mentions @architect, asks to review an issue's design, discuss module boundaries, API shape, or architectural decisions for vfs-s3. Also trigger when the user wants to create an ADR (Architecture Decision Record) or evaluate a technical approach for the project. Intended for dispatch from Codex automation or Claude routines; GitHub trigger phrase: @vfs-s3-bot please prepare design doc Use when this capability is needed.
基于 SOC 职业分类
正在显示 SKILL.md
| name | prompt-engine |
| description | > Use when this capability is needed. |
2,500+ curated prompts across 19 categories, 17 AI models, and 4 output types.
| Command | What it does |
|---|---|
/prompt [query] | Search prompts by keyword, category, model, or style |
/prompt-build | Build a custom prompt from scratch with guided workflow |
/prompt-enhance | Enhance an existing prompt with pro techniques |
/prompt-adapt | Adapt a prompt for a different AI model |
/prompt-library | Browse, filter, and explore the full prompt library |
/prompt-build/prompt-enhance/prompt-adapt/prompt-libraryWhen user provides a search query:
Run the search script:
python3 {PROMPT_ENGINE_DIR}/scripts/search_prompts.py "QUERY" [--category CAT] [--model MODEL] [--type TYPE] [--limit N]
Present results as a numbered list with:
Let user select a prompt to see full details, or refine their search
--categories.python3 --version). Check that the database exists at {PROMPT_ENGINE_DIR}/prompts/all_prompts.json./prompt-enhance and /prompt-adapt, ask the user to provide a longer prompt (minimum 30 characters).| Metric | Value |
|---|---|
| Total prompts | 2,503 |
| Categories | 19 |
| AI Models | 17 |
| Output types | Video (1,225), Image (1,049), Generator (115), Text (114) |
| Model coverage | 78% of prompts have model attribution |
| Sources | 11 Airtable databases |
| Category | Count | Description |
|---|---|---|
| fashion-editorial | 473 | Fashion, editorial, magazine shoots |
| video-general | 287 | Video-specific prompts |
| general | 221 | Multi-purpose prompts |
| portraits-people | 198 | Faces, characters, headshots |
| landscapes-nature | 180 | Mountains, oceans, forests, sunsets |
| abstract-backgrounds | 171 | Gradients, patterns, wallpapers |
| sci-fi-futuristic | 135 | Cyberpunk, robots, space, neon |
| architecture | 129 | Buildings, interiors, cityscapes |
| logos-icons | 116 | Logo design, icon sets, branding |
| generators | 115 | Meta-prompts that create prompts |
| text | 114 | Copywriting, content, storytelling |
| animated-3d | 92 | Pixar, 3D renders, anime |
| vehicles | 82 | Cars, motorcycles, racing |
| superheroes | 58 | Marvel, DC, superhero art |
| fantasy | 56 | Dragons, magic, medieval, mythical |
| products | 42 | Product photography, packshots |
| animals | 18 | Wildlife, pets, creatures |
| food-drink | 11 | Food photography, recipes |
| print-merchandise | 5 | T-shirts, stickers, merch |
Top models: Midjourney (981), Leonardo AI (237), Freepik (172), Mystic (166), Flux (137), Any Platform (97), DALL-E (42), Imagen (26), Sora (24), ChatGPT (22).
{PROMPT_ENGINE_DIR}/prompts/{PROMPT_ENGINE_DIR}/prompts/all_prompts.json{PROMPT_ENGINE_DIR}/prompts/{category}/prompts.json{PROMPT_ENGINE_DIR}/prompts/stats.json{PROMPT_ENGINE_DIR}/scripts/search_prompts.pyreferences/prompt-patterns.md -- Common prompt engineering patterns and structuresreferences/model-guide.md -- Model-specific syntax, features, and best practicesConverted and distributed by TomeVault — claim your Tome and manage your conversions.