AgriciDanielAgriciDaniel/claude-prompts/CLAUDE.md

claude-prompts

CLAUDE.md105 starsChanged 8 months agoMITView on GitHub

This repository contains Claude Prompts, a Tier 4 Claude Code skill for searching, building, enhancing, and adapting AI image/video prompts. It includes 2,500+ curated prompts across 19 categories and 17 AI models. It follows the Agent Skills open standard and the 3-layer architecture (directive, orchestration, execution).

In this repositoryOne other file it gives its agents.
- prompt-engineSkill

The file

We split this CLAUDE.md into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific
could be automatic: a setting could enforce it

Very specific:
Test search with python3 scripts/search_prompts.py --stats after changes
line 47
Very specific:
Keep SKILL.md files under 500 lines / 5000 tokens
line 48
Distinctive:
Follow kebab-case naming for all skill directories
line 51
Very specific:
Never commit real Airtable URLs or API keys (only in gitignored raw/)
line 52

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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

CLAUDE.md

Claude Prompts — AI Prompt Database and Builder

Project Overview

This repository contains Claude Prompts, a Tier 4 Claude Code skill for searching, building, enhancing, and adapting AI image/video prompts. It includes 2,500+ curated prompts across 19 categories and 17 AI models. It follows the Agent Skills open standard and the 3-layer architecture (directive, orchestration, execution).

Architecture

claude-prompts/
  CLAUDE.md                          # This file (project instructions)
  prompt-engine/                     # Main orchestrator skill (Tier 4)
    SKILL.md                         # Entry point, routing table, database stats
    references/                      # Symlinked at install time
  skills/                            # Sub-skills
    prompt-build/SKILL.md           # Build custom prompts from scratch
    prompt-enhance/SKILL.md         # Enhance existing prompts with pro techniques
    prompt-adapt/SKILL.md           # Adapt prompts between AI models
    prompt-library/SKILL.md         # Browse, filter, and explore the library
  scripts/                           # Python execution scripts
    search_prompts.py               # Search and filter the prompt database
    extract_prompts.py              # Extract prompts from raw Airtable data
    scrape_airtable.py              # Scrape Airtable shared views (template)
  references/                        # Knowledge files
    model-guide.md                  # Model-specific syntax and best practices (17 models)
    prompt-patterns.md              # Common prompt engineering patterns
  prompts/                           # Prompt database (JSON)
    all_prompts.json                # Master file (2,503 prompts, ~5.4 MB)
    stats.json                      # Database statistics
    {category}/prompts.json         # Per-category files (19 categories)
  install.sh                         # Linux/macOS installation script
  install.ps1                        # Windows/PowerShell installation script

Key Principles

Progressive Disclosure: Metadata always loaded, instructions on activation, references on demand
Placeholder Paths: Source files use {PROMPT_ENGINE_DIR} — install.sh substitutes with actual repo path
Symlinked References: references/ is symlinked into the installed skill to avoid duplication
Template Scraper: scrape_airtable.py ships with an empty TABLES dict — users add their own URLs

Development Rules

Test search with python3 scripts/search_prompts.py --stats after changes
Keep SKILL.md files under 500 lines / 5000 tokens
Reference files should be focused and under 200 lines
Scripts must have docstrings, CLI interface, and JSON output
Follow kebab-case naming for all skill directories
Never commit real Airtable URLs or API keys (only in gitignored raw/)

Commands

Command	Purpose
`/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

Data Pipeline

Scrape: scrape_airtable.py extracts raw data from Airtable shared views (Playwright)
Extract: extract_prompts.py deduplicates, filters noise, categorizes, and infers models
Output: prompts/all_prompts.json (master) + per-category JSONs + stats.json
Install: install.sh copies skills to ~/.claude/skills/, substitutes paths, symlinks references

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