prompt-factory
World-class prompt powerhouse that generates production-ready mega-prompts for any role, industry, and task through intelligent 7-question flow, 69 comprehensive presets across 15 professional domains (technical, business, creative, legal, finance, HR, design, customer, executive, manufacturing, R&D, regulatory, specialized-technical, research, creative-media), multiple output formats (XML/Claude/ChatGPT/Gemini), quality validation gates, and contextual best practices from OpenAI/Anthropic/Google. Supports both core and advanced modes with testing scenarios and prompt variations.
Profile →npx skills add alirezarezvani/claude-code-skill-factory --skill prompt-factory --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill generates a single, production-ready mega-prompt document in a chosen output format after asking 5-7 mandatory questions to understand requirements. It validates prompt quality before delivery, and delivers the prompt ready to copy/use. It operates in core or advanced modes, with optional testing scenarios and variations, and supports multiple formats (XML/Claude/ChatGPT/Gemini).
How it works
- It begins by requiring the user to answer 5-7 questions covering: role and domain, primary task, desired output format, tech constraints, and style/format preferences. It insists on confirmation for inferred details.
- After questions, the user selects an output format (xml, claude, chatgpt, gemini, or all) and a mode (core or advanced).
- It then matches against presets/templates, choosing a high-match preset when possible or synthesizing a custom template using best-practices references. It performs a 7-point quality validation before delivery, ensuring XML structure, completeness, token count, no placeholders, actionable workflow, best practices, and presence of examples.
- Finally, it generates the mega-prompt in the chosen format with sections like role, mission, context, workflow, output_specifications, and communication_guidelines, including content tailored to the user-provided details.
When to use it
- Use when you need a single, ready-to-use mega-prompt for a specific role and domain, rather than implementing work tasks.
- Use when you want a prompt document that includes validation gates and multiple output formats, ensuring consistency across LLMs.
What it can touch
- The skill touches prompts only; it does not implement the work described by the prompt.
- Output formats supported: XML, Claude, ChatGPT, Gemini (and all formats if chosen).
- It references external best-practices sources for synthesis when no close preset exists (OpenAI/Anthropic/Google guidance).
Caveats
- It generates a single prompt document and does not execute or implement the prompt content.
- It requires user input for 5-7 questions and explicit confirmation of inferred details.
- Token counts are announced in the delivery message and must stay within stated ranges per mode.
# Prompt Factory - World-Class Prompt Powerhouse A comprehensive system for generating world-class, production-ready prompts in one shot, eliminating the need for iteration. --- ## ⚠️ CRITICAL CONSTRAINTS - READ FIRST **This skill generates PROMPTS only. It does NOT implement the work described in the prompt.** ### What This Skill DOES: ✅ Generate a comprehensive PROMPT (text document in chosen format) ✅ **Ask 5-7 questions to understand requirements** (MANDATORY - no skipping) ✅ Validate prompt quality before delivery ✅ Output a SINGLE prompt document with token count ✅ Provide the prompt ready to copy and use elsewhere ### What This Skill DOES NOT DO: ❌ Implement the actual work (no code files, no diagrams, no APIs) ❌ Create architectural diagrams or technical implementations ❌ Write actual marketing campaigns or business strategies ❌ Build infrastructure or deploy anything ❌ Create multiple files or deliverables ❌ Execute the prompt after generating it ### Expected Workflow: 1. User asks for help creating a prompt 2. **Skill MUST ask 5-7 questions** (even if context seems obvious) 3. User answers questions with specific details 4. Skill generates ONE comprehensive prompt documen
- ⚠️ CRITICAL CONSTRAINTS - READ FIRST
- What This Skill DOES:
- What This Skill DOES NOT DO:
- Expected Workflow:
- Why This Matters:
- Overview
- Relationship to PROMPTSFACTORYPROMPT.md
- Quick Start: Choose Your Path
- Path 1: Quick-Start Preset (Fastest)
- Path 2: Custom Prompt (5-7 Questions - MANDATORY)
- Workflow: Custom Prompt Generation
- Step 1: Intent Detection & Context Inference
- Step 2: Smart 7-Question Flow
- Step 3: Output Format Selection
Generate with JSON config python scripts/generate_prompt.py \ Batch generation python scripts/batch_generator.py \ Validate existing prompt python scripts/validator.py \ Optimize prompt python scripts/optimizer.py \
What does the prompt-factory skill do?
World-class prompt powerhouse that generates production-ready mega-prompts for any role, industry, and task through intelligent 7-question flow, 69 comprehensive presets across 15 professional domains (technical, business, creative, legal, finance, HR, design, customer, executive, manufacturing, R&D, regulatory, specialized-technical, research, creative-media), multiple output formats (XML/Claude/ChatGPT/Gemini), quality validation gates, and contextual best practices from OpenAI/Anthropic/Google. Supports both core and advanced modes with testing scenarios and prompt variations.
How do I install it?
Run `npx skills add alirezarezvani/claude-code-skill-factory --skill prompt-factory --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From alirezarezvani/claude-code-skill-factory, a repository with 839 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.