Skip to content
Back to search

claude-prompts

SkillWorks with Claude CodeGitHub

AI prompt database and builder skill for Claude Code. 2,500+ curated prompts across 19 categories and 17 AI models.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/agricidaniel--claude-prompts/badge.svg)](/listings/agricidaniel--claude-prompts)

HTML

<a href="/listings/agricidaniel--claude-prompts"><img src="/api/listings/agricidaniel--claude-prompts/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Requirements

- [Claude Code](https://docs.anthropic.com/en/docs/claude-code) CLI - Python 3.10+

Install (Linux / macOS)

git clone https://github.com/AgriciDaniel/claude-prompts.git
cd claude-prompts
bash install.sh

Install (Windows / PowerShell)

git clone https://github.com/AgriciDaniel/claude-prompts.git
cd claude-prompts
.\install.ps1

> **Note:** The prompt database (`prompts/all_prompts.json`) is ~5.4 MB. Total repository size is approximately 12 MB.

The install script: 1. Copies skill files to `~/.claude/skills/` 2. Substitutes path placeholders with your local repo path 3. Symlinks reference files (no duplication) 4. Verifies the prompt database and search script

Verify

python3 scripts/search_prompts.py --stats

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 197 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <img src="claude-prompt-header.jpeg" alt="Claude Prompts — AI-Powered Prompt Engine" width="100%">
  3. </p>
  4. # Claude Prompts
  5. AI prompt database and builder skill for [Claude Code](https://docs.anthropic.com/en/docs/claude-code) with 2,500+ curated prompts across 19 categories and 17 AI models.
  6. Search, build, enhance, and adapt prompts for Midjourney, Flux, Leonardo AI, DALL-E, Sora, Imagen, Mystic, Stable Diffusion, Ideogram, Adobe Firefly, Freepik, and more.
  7. ## Features
  8. - **2,503 curated prompts** extracted from 11 Airtable sources
  9. - **19 categories**: fashion-editorial, video, portraits, landscapes, sci-fi, architecture, logos, fantasy, and more
  10. - **17 AI models**: Midjourney (981), Leonardo AI (237), Freepik (172), Mystic (166), Flux (137), and others
  11. - **4 output types**: Video (1,225), Image (1,049), Generator (115), Text (114)
  12. - **5 skill commands** for searching, building, enhancing, adapting, and browsing prompts
  13. ## Commands
  14. | Command | What it does |
  15. |---------|-------------|
  16. | `/prompt [query]` | Search prompts by keyword, category, model, or style |
  17. | `/prompt-build` | Build a custom prompt from scratch with guided workflow |
  18. | `/prompt-enhance` | Enhance an existing prompt with pro techniques |
  19. | `/prompt-adapt` | Adapt a prompt for a different AI model |
  20. | `/prompt-library` | Browse, filter, and explore the full prompt library |
  21. ## Installation
  22. ### Requirements
  23. - [Claude Code](https://docs.anthropic.com/en/docs/claude-code) CLI
  24. - Python 3.10+
  25. ### Install (Linux / macOS)
  26. ```bash
  27. git clone https://github.com/AgriciDaniel/claude-prompts.git
  28. cd claude-prompts
  29. bash install.sh
  30. ```
  31. ### Install (Windows / PowerShell)
  32. ```powershell
  33. git clone https://github.com/AgriciDaniel/claude-prompts.git
  34. cd claude-prompts
  35. .\install.ps1
  36. ```
  37. > **Note:** The prompt database (`prompts/all_prompts.json`) is ~5.4 MB. Total repository size is approximately 12 MB.
  38. The install script:
  39. 1. Copies skill files to `~/.claude/skills/`
  40. 2. Substitutes path placeholders with your local repo path
  41. 3. Symlinks reference files (no duplication)
  42. 4. Verifies the prompt database and search script
  43. ### Verify
  44. ```bash
  45. python3 scripts/search_prompts.py --stats
  46. ```
  47. ## Usage Examples
  48. ### Search for prompts
  49. ```bash
  50. # In Claude Code, just type:
  51. /prompt cyberpunk city
  52. # Or use the search script directly:
  53. python3 scripts/search_prompts.py "cyberpunk city" --limit 5
  54. ```
  55. ### Filter by model
  56. ```bash
  57. /prompt --model Midjourney
  58. python3 scripts/search_prompts.py --model "Midjourney" --limit 10
  59. ```
  60. ### Filter by category
  61. ```bash
  62. /prompt --category fashion-editorial
  63. python3 scripts/search_prompts.py --category fantasy --limit 10
  64. ```
  65. ### Get a random prompt
  66. ```bash
  67. python3 scripts/search_prompts.py --random --model Flux
  68. ```
  69. ### Build a custom prompt
  70. ```
  71. /prompt-build
  72. # Follow the guided workflow: output type -> target model -> subject -> style
  73. ```
  74. ### Enhance an existing prompt
  75. ```
  76. /prompt-enhance "A cat sitting on a windowsill"
  77. # Scores your prompt, finds similar top prompts, applies enhancement techniques
  78. ```
  79. ### Adapt between models
  80. ```
  81. /prompt-adapt
  82. # Translates prompts between Midjourney, Flux, DALL-E, Sora, and other models
  83. ```
  84. ## Project Structure
  85. ```
  86. claude-prompts/
  87. prompt-engine/ # Main orchestrator skill
  88. SKILL.md # Entry point with routing table
  89. skills/ # Sub-skills
  90. prompt-build/SKILL.md # Build custom prompts
  91. prompt-enhance/SKILL.md # Enhance existing prompts
  92. prompt-adapt/SKILL.md # Adapt between models
  93. prompt-library/SKILL.md # Browse the library
  94. scripts/ # Python scripts
  95. search_prompts.py # Search and filter the database
  96. extract_prompts.py # Extract prompts from raw Airtable data
  97. scrape_airtable.py # Scrape Airtable shared views (template)
  98. references/ # Knowledge files
  99. model-guide.md # Model-specific syntax and best practices
  100. prompt-patterns.md # Common prompt engineering patterns
  101. prompts/ # Prompt database (JSON)
  102. all_prompts.json # Master file (2,503 prompts)
  103. stats.json # Database statistics
  104. {category}/prompts.json # Per-category files (19 categories)
  105. install.sh # Installation script
  106. ```
  107. ## Categories
  108. | Category | Count | Description |
  109. |----------|-------|-------------|
  110. | fashion-editorial | 473 | Fashion, editorial, magazine shoots |
  111. | video-general | 287 | Video-specific prompts |
  112. | general | 221 | Multi-purpose prompts |
  113. | portraits-people | 198 | Faces, characters, headshots |
  114. | landscapes-nature | 180 | Mountains, oceans, forests, sunsets |
  115. | abstract-backgrounds | 171 | Gradients, patterns, wallpapers |
  116. | sci-fi-futuristic | 135 | Cyberpunk, robots, space, neon |
  117. | architecture | 129 | Buildings, interiors, cityscapes |
  118. | logos-icons | 116 | Logo design, icon sets, branding |
  119. | generators | 115 | Meta-prompts that create prompts |
  120. | text | 114 | Copywriting, content, storytelling |
  121. | animated-3d | 92 | Pixar, 3D renders, anime |
  122. | vehicles | 82 | Cars, motorcycles, racing |
  123. | superheroes | 58 | Marvel, DC, superhero art |
  124. | fantasy | 56 | Dragons, magic, medieval, mythical |
  125. | products | 42 | Product photography, packshots |
  126. | animals | 18 | Wildlife, pets, creatures |
  127. | food-drink | 11 | Food photography, recipes |
  128. | print-merchandise | 5 | T-shirts, stickers, merch |
  129. ## Adding Your Own Prompts
  130. The extraction pipeline supports Airtable shared views:
  131. 1. Add your Airtable shared view URLs to `scripts/scrape_airtable.py` (TABLES dict)
  132. 2. Install Playwright: `pip install playwright && playwright install chromium`
  133. 3. Run the scraper: `python3 scripts/scrape_airtable.py --output raw`
  134. 4. Extract and categorize: `python3 scripts/extract_prompts.py --input raw --output prompts`
  135. 5. Reinstall: `bash install.sh`
  136. ## Attribution & Disclaimer
  137. The prompts in this database were collected from publicly shared Airtable views and community sources.
  138. If you are the original creator of any prompt and would like it removed or credited differently,
  139. please open an issue and we will address it promptly. This project is intended for educational
  140. and creative purposes. Always respect the original creators' rights and terms of service.
  141. ## Support
  142. - **Issues**: [GitHub Issues](https://github.com/AgriciDaniel/claude-prompts/issues)
  143. - **Discussions**: [GitHub Discussions](https://github.com/AgriciDaniel/claude-prompts/discussions)
  144. - **Contributing**: See [CONTRIBUTING.md](CONTRIBUTING.md)
  145. ## License
  146. [MIT](LICENSE)
  147. ---
  148. ## Author
  149. Built by [Agrici Daniel](https://agricidaniel.com/about) - AI Workflow Architect.
  150. - [Blog](https://agricidaniel.com/blog) - Deep dives on AI marketing automation
  151. - [AI Marketing Hub](https://www.skool.com/ai-marketing-hub) - Free community, 2,800+ members
  152. - [YouTube](https://www.youtube.com/@AgriciDaniel) - Tutorials and demos
  153. - [All open-source tools](https://github.com/AgriciDaniel)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.