prompt-architectTransform rough ideas into professional-grade LLM prompts. Analyzes text, images, links, and documents to craft optimized prompts using proven frameworks (Co...
Install via ClawdBot CLI:
clawdbot install Abdullah4AI/prompt-architectTransform rough concepts into professional-grade LLM prompts.
Follow these 4 steps for every interaction. Do not skip steps.
When the user submits input, do NOT generate the final prompt immediately. Perform deep analysis:
Ask 5-10 clarifying questions based on analysis. Cover these categories:
| Category | What to Ask |
|---|---|
| Purpose | What specific outcome do you need? |
| Audience | Who consumes this output? |
| Tone & Style | Professional, witty, academic, cinematic? |
| Format | Code block, blog post, JSON, narrative? |
| Context | Background info the model needs? |
| Constraints | What to avoid? Length limits? |
| Examples | Specific styles or references to mimic? |
Adapt question count to complexity: simple requests get 5, complex/multimodal get up to 10-15.
Opening format:
I've analyzed your input. To craft the right prompt, I need a few details:
>
1. [Question]
2. [Question]
...
After the user answers, ask exactly:
Would you like the final prompt in English or Arabic?
Construct the optimized prompt using:
references/frameworks.mdreferences/quality-criteria.mdOutput rules:
Delivery format:
Here's your optimized prompt:
>
> [Final Polished Prompt] >
>
Framework used: [Name] - [One-line reason]
Choose the right framework based on the task. See references/frameworks.md for full details.
| Task Type | Recommended Framework |
|---|---|
| Reasoning/analysis | Chain-of-Thought (CoT) |
| Creative/open-ended | Persona + constraints |
| Structured data output | JSON schema + few-shot |
| Multi-step workflows | Prompt chaining |
| Classification/decisions | Few-shot with edge cases |
| Complex problem-solving | Tree-of-Thought |
| Task + tool use | ReAct pattern |
See references/templates.md for ready-to-use prompt templates organized by use case:
Before delivering, verify against references/quality-criteria.md:
Generated Mar 1, 2026
A marketing team needs to generate social media ad copy for a new product launch. They provide a rough idea, target audience details, and brand guidelines. The skill analyzes these inputs, clarifies tone and platform specifics, and outputs a structured prompt for generating multiple ad variations.
An educator has an existing prompt for creating quiz questions but finds the outputs inconsistent. They submit the prompt and examples of desired outputs. The skill diagnoses issues, asks about difficulty levels and subject matter, and produces an optimized prompt using few-shot examples for reliable quiz generation.
A customer support manager wants to automate responses to common inquiries. They provide sample tickets and company policies. The skill analyzes the documents, clarifies response tone and escalation rules, and crafts a prompt using a persona framework to generate empathetic and accurate support replies.
A data analyst needs to generate summaries from complex datasets. They share a vague request and sample data formats. The skill extracts key metrics, asks about report structure and audience, and outputs a prompt with JSON schema constraints for structured data extraction and analysis.
Offer a free tier with basic prompt optimization and a paid tier for advanced features like multimodal analysis, team collaboration, and integration with popular LLM APIs. Revenue comes from subscription fees and enterprise licenses.
Provide expert prompt engineering services for businesses, along with workshops and certification programs. Revenue is generated through project-based contracts, hourly consulting rates, and training course fees.
Develop an API that allows other applications to integrate prompt optimization capabilities. Additionally, create a marketplace for selling pre-built prompt templates. Revenue streams include API usage fees and commissions from template sales.
💬 Integration Tip
Integrate this skill into existing workflows by using its API to automatically optimize prompts before sending them to LLMs, ensuring consistent output quality across applications.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Provides a 7-step debugging protocol plus language-specific commands to systematically identify, verify, and fix software bugs across multiple environments.
A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
Write, run, and manage unit, integration, and E2E tests across TypeScript, Python, and Swift using recommended frameworks.
Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.