Skip to content

marktantongco/promptc-os-ai-prompt-wiki / skills/blog-writer

blog-writer

Verified

This skill should be used when writing blog posts, articles, or long-form content in the writer's distinctive writing style. It produces authentic, opinionated content that matches the writer's voice—direct, conversational, and grounded in personal experience. The skill handles the complete workflow from research review through Notion publication. Use this skill for drafting blog posts, thought leadership pieces, or any writing meant to reflect the writer's perspective on AI, productivity, sales, marketing, or technology topics.

FileKindSize
2024-02-17-radical-transparency-sales.mdexecutablescript3.5 KB
2024-02-17-raycast-spotlight-superpowers.mdexecutablescript2.9 KB
2024-02-17-short-form-content-marketing.mdexecutablescript5.0 KB
2024-02-17-typing-speed-benefits.mdexecutablescript3.4 KB
2024-03-14-effective-ai-prompts.mdexecutablescript3.4 KB
2024-11-08-ai-revolutionizing-entry-level-sales.mdexecutablescript5.2 KB
2025-11-12-why-ai-art-is-useless.mdexecutablescript5.6 KB
README.mdexecutablescript189 B
SKILL.mdexecutableskill md6.8 KB
_meta.jsonexecutablescript130 B
manage_examples.pyexecutablescript2.6 KB
style-guide.mdexecutablescript6.2 KB

2024-03-14-effective-ai-prompts.md

View on GitHub
# How to Write More Effective AI Prompts

## The Art of Prompt Engineering for ChatGPT

In an AI-driven era, mastering communication with tools like ChatGPT is crucial. This guide explores writing effective prompts for ChatGPT, unlocking its full potential. Whether you're a tech enthusiast, content creator, or business professional, these tips enhance your AI interaction.

### The GIGO Principle: Quality In, Quality Out

The axiom "Garbage In, Garbage Out" (GIGO) holds true in the world of AI. The quality of the output you receive from ChatGPT directly correlates with the quality of the prompts you provide. Inadequate prompts can lead to misleading or irrelevant answers, while well-crafted ones can produce insightful and accurate responses.

### Crafting Prompts that Spark Excellence

The skill of writing effective prompts is now so crucial that it has spawned a new discipline: prompt engineering. This involves meticulously designing prompts that guide ChatGPT's large language model (LLM) to generate the best possible answers.

### Conversational AI: Talk to ChatGPT Like a Person

Interacting with ChatGPT should mimic a conversation with a colleague. This approach helps in setting the stage, providing context, and maintaining the AI's focus on the topic.

### Context Is Key

Providing ChatGPT with clear context is vital. It narrows down the AI's focus to your specific subject, leading to more accurate and useful responses. Contextualized prompts require more details but offer more refined outputs.

### Assuming Identities and Professions

One of ChatGPT's fascinating features is its ability to adopt different personas or professional perspectives. This ability can be harnessed to gain diverse viewpoints on a topic.

### Maintaining Relevance and Accuracy

While ChatGPT is an advanced AI, it can sometimes veer off-topic or produce fabricated answers. To mitigate this, ask the AI to justify its responses and guide it gently back on track. Remember to prompt it for source citations where necessary.

## Advanced Prompt-Writing Techniques

### Fine-Tuning Your Prompts

Minor adjustments to your prompts can lead to significantly different responses from ChatGPT. Remember, the AI retains its awareness of previous conversations as long as the session is ongoing.

### Breaking Down Responses

Be mindful that responses over 500 words can sometimes lose coherence. Keep your prompts concise and to the point for the best results.

### Evolving Your Questions

If ChatGPT seems hesitant to answer a question, rephrasing it might yield better results. Utilize personas to elicit responses that might not be forthcoming otherwise.

### Seeking Justification and Sources

When looking for well-supported answers, instruct ChatGPT to justify its responses or provide sources. This practice ensures a higher degree of accuracy and reliability in the information provided.

### Embrace Experimentation

Experimentation is key in mastering prompt writing. The more you test different approaches, the better you'll understand how to steer ChatGPT towards desired outcomes.

### Conclusion: The Journey to AI Mastery

Mastering ChatGPT prompts is a journey of continuous learning and adaptation. By understanding the intricacies of prompt engineering and staying updated with the latest advancements, you can transform your interaction with AI from a mere task to an enriching experience. Embrace these tips, keep experimenting, and watch as ChatGPT becomes an invaluable asset in your digital toolkit.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall