agentleFS
Sign inStart free
AgriciDanielAgriciDaniel/claude-prompts/prompt-engine/SKILL.md

prompt-engine

Skill105 starsChanged 8 months agoMITView on GitHub

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, Adobe Firefly, and more). Search, build, enhance, and adapt prompts for image generation, video creation, text, and meta-prompt generators. Use when user says "prompt", "find a prompt", "build a prompt", "enhance my prompt", "adapt this prompt", "prompt library", "image prompt", "video prompt", "midjourney prompt", "flux prompt", or any AI prompt engineering task. Do NOT use for terminal/CLI prompts, JavaScript prompt() dialogs, user input prompts, or bash prompt customization.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 4 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If user provides a search query or asks to find/search -> run search workflow below

    line 33
  2. Very specific:

    If user wants to create/build a new prompt -> route to /prompt-build

    line 34
  3. Very specific:

    If user has an existing prompt to improve -> route to /prompt-enhance

    line 35
  4. Very specific:

    If user wants to convert between models -> route to /prompt-adapt

    line 36
  5. Very specific:

    If user wants to browse/explore -> route to /prompt-library

    line 37
  6. Distinctive:

    If ambiguous, show the Quick Reference table and ask

    line 38
  7. Distinctive:

    When user provides a search query:

    line 42
  8. Distinctive:

    Run the search script:

    line 44
  9. Very specific:

    Script fails: Verify Python 3.10+ is available (python3 --version).

    line 59

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Prompt Engine -- Ultimate AI Prompt Database and Builder

2,500+ curated prompts across 19 categories, 17 AI models, and 4 output types.

Quick Reference

CommandWhat it does
/prompt [query]Search prompts by keyword, category, model, or style
/prompt-buildBuild a custom prompt from scratch with guided workflow
/prompt-enhanceEnhance an existing prompt with pro techniques
/prompt-adaptAdapt a prompt for a different AI model
/prompt-libraryBrowse, filter, and explore the full prompt library

Orchestration Logic

  1. If user provides a search query or asks to find/search -> run search workflow below
  2. If user wants to create/build a new prompt -> route to /prompt-build
  3. If user has an existing prompt to improve -> route to /prompt-enhance
  4. If user wants to convert between models -> route to /prompt-adapt
  5. If user wants to browse/explore -> route to /prompt-library
  6. If ambiguous, show the Quick Reference table and ask

Search Workflow (Default /prompt)

When user provides a search query:

  1. Run the search script:
    python3 {PROMPT_ENGINE_DIR}/scripts/search_prompts.py "QUERY" [--category CAT] [--model MODEL] [--type TYPE] [--limit N]
  2. Present results as a numbered list with:
    • Prompt text (truncated to 200 chars for preview)
    • Category, model, output type
    • Tags/styles if available
  3. Let user select a prompt to see full details, or refine their search

Error Handling

  • 0 search results: Suggest broadening the query, trying different keywords, or removing filters. Offer to show available categories with --categories.
  • Script fails: Verify Python 3.10+ is available (python3 --version). Check that the database exists at {PROMPT_ENGINE_DIR}/prompts/all_prompts.json.
  • Empty or short prompt input: For /prompt-enhance and /prompt-adapt, ask the user to provide a longer prompt (minimum 30 characters).

Database Stats

MetricValue
Total prompts2,503
Categories19
AI Models17
Output typesVideo (1,225), Image (1,049), Generator (115), Text (114)
Model coverage78% of prompts have model attribution
Sources11 Airtable databases

Categories

CategoryCountDescription
fashion-editorial473Fashion, editorial, magazine shoots
video-general287Video-specific prompts
general221Multi-purpose prompts
portraits-people198Faces, characters, headshots
landscapes-nature180Mountains, oceans, forests, sunsets
abstract-backgrounds171Gradients, patterns, wallpapers
sci-fi-futuristic135Cyberpunk, robots, space, neon
architecture129Buildings, interiors, cityscapes
logos-icons116Logo design, icon sets, branding
generators115Meta-prompts that create prompts
text114Copywriting, content, storytelling
animated-3d92Pixar, 3D renders, anime
vehicles82Cars, motorcycles, racing
superheroes58Marvel, DC, superhero art
fantasy56Dragons, magic, medieval, mythical
products42Product photography, packshots
animals18Wildlife, pets, creatures
food-drink11Food photography, recipes
print-merchandise5T-shirts, stickers, merch

Models

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).

Data Paths

  • Prompt database: {PROMPT_ENGINE_DIR}/prompts/
  • Master file: {PROMPT_ENGINE_DIR}/prompts/all_prompts.json
  • Per-category: {PROMPT_ENGINE_DIR}/prompts/{category}/prompts.json
  • Stats: {PROMPT_ENGINE_DIR}/prompts/stats.json
  • Search script: {PROMPT_ENGINE_DIR}/scripts/search_prompts.py

Reference Files

  • references/prompt-patterns.md -- Common prompt engineering patterns and structures
  • references/model-guide.md -- Model-specific syntax, features, and best practices

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free