# Write better prompts Prompt Pack

Prompts for tightening vague requests, decomposing big ideas, teaching patterns with examples, and avoiding prompting anti-patterns.

Pack URL: https://aicodingguild.com/prompts/packs/write-better-prompts
Filtered library URL: https://aicodingguild.com/prompts?q=prompt-engineering&path=ai-tools
Plain-text export: https://aicodingguild.com/prompts/packs/write-better-prompts/txt
Featured prompt: The Anti-Patterns — Prompts That Produce Bad Code
Prompt count: 6

## 1. Tighten My Coding Prompt
Category: Prompt Design
Path: Working With AI Tools
Lesson: https://aicodingguild.com/learn/ai-tools/anatomy-of-good-coding-prompt
Prompt page: https://aicodingguild.com/prompts/anatomy-of-good-coding-prompt
Tags: ai-tools, prompt-engineering, best-practices
Summary: Use this when your current request feels vague and you want the agent to help shape a safer, sharper implementation prompt before files change.

Prompt:
**Use this with Cursor or Claude Code before you ask for implementation work:**
"Help me tighten this coding prompt before any files are changed.
Project context: [stack, app purpose, relevant data model]
Goal: [the feature or fix I want]
Rough prompt: [paste your current prompt]

Rewrite it using these sections:
1. Context
2. Task
3. Specifics
4. Constraints
5. Output

Keep the scope limited to one reviewable change.
Tell me which assumptions are still missing.
Tell me what I must verify manually before I let an agent write code."

## 2. Breaking Big Ideas into Small Tasks — The Decomposition Pattern
Category: Working With AI Tools
Path: Working With AI Tools
Lesson: https://aicodingguild.com/learn/ai-tools/decomposition-pattern
Prompt page: https://aicodingguild.com/prompts/decomposition-pattern
Tags: ai-tools, prompt-engineering, decomposition, workflow
Summary: Learn why small, focused prompts produce better code than trying to build everything at once.

Prompt:
**Use this before you start building a multi-part feature:**
"I want to build [feature or app idea]. Break it into 8-12 implementation steps.

Requirements for each step:
- It must build on the previous step
- It must produce something testable
- It must avoid mixing auth, billing, schema, and UI redesign into one step
- It must name the files or systems likely to change
- It must include a short verification check before the next step

Start with foundations first.
Tell me which steps need my approval before an agent should continue."

## 3. Few-Shot Prompting — Teaching AI by Showing Examples
Category: Working With AI Tools
Path: Working With AI Tools
Lesson: https://aicodingguild.com/learn/ai-tools/few-shot-prompting
Prompt page: https://aicodingguild.com/prompts/few-shot-prompting
Tags: ai-tools, prompt-engineering, few-shot, examples
Summary: Use examples to teach AI your patterns, styles, and conventions before it writes new code.

Prompt:
**Use this when you want the agent to follow an existing pattern instead of inventing one:**
"I need a new [component / route / hook / migration].
Use these files as examples:
- [file 1]
- [file 2]

Replicate these aspects:
- [imports and file structure]
- [error handling pattern]
- [response shape or UI composition]

Adapt these aspects for the new task:
- [field names]
- [queries]
- [business logic]

Before coding, summarize the pattern you see.
Call out any inconsistencies between the examples.
Stop if the examples appear outdated or conflict with the rest of the repo."

## 4. Chain-of-Thought — Making AI Think Step by Step
Category: Working With AI Tools
Path: Working With AI Tools
Lesson: https://aicodingguild.com/learn/ai-tools/chain-of-thought
Prompt page: https://aicodingguild.com/prompts/chain-of-thought
Tags: ai-tools, prompt-engineering, chain-of-thought, reasoning
Summary: Use chain-of-thought prompting to get AI to reason through complex coding problems.

Prompt:
**Use this for tasks with real logic, architecture, or debugging complexity:**
"I need help with [problem].
Before writing code, work in three phases.

Phase 1: Think
- Explain the problem in plain English
- Identify the main rules, dependencies, and edge cases
- Point out anything ambiguous or risky

Phase 2: Plan
- Propose the implementation approach
- List files or systems likely to change
- Explain how you will verify correctness

Phase 3: Code
- Do not start this phase until I approve phases 1 and 2

Keep these constraints in mind: [constraints].
Tell me what I must test manually after implementation."

## 5. The Anti-Patterns — Prompts That Produce Bad Code
Category: Working With AI Tools
Path: Working With AI Tools
Lesson: https://aicodingguild.com/learn/ai-tools/anti-patterns
Prompt page: https://aicodingguild.com/prompts/anti-patterns
Tags: ai-tools, prompt-engineering, anti-patterns, mistakes
Summary: Recognize and avoid the most common prompting mistakes that lead to buggy, bloated, or wrong code.

Prompt:
**Use this when a conversation with the agent keeps going sideways:**
"I am going to paste three prompts that produced bad results.
For each prompt:
1. Classify the anti-pattern causing the failure
2. Explain why the prompt created bad code or bad direction
3. Rewrite it into a safer, more specific prompt
4. Add the right constraints, review gates, and stop conditions

Use these anti-pattern labels when relevant:
mega prompt, vague request, implicit standards, error dump,
moving target, trust fall, kitchen sink, outdated assumption.

After the rewrites, give me one reusable rule I should add to my workflow so I stop making the same mistake."

## 6. Fine-Tuning vs RAG vs Prompt Engineering
Category: Working With AI Tools
Path: Working With AI Tools
Lesson: https://aicodingguild.com/learn/ai-tools/fine-tuning-vs-rag-vs-prompting
Prompt page: https://aicodingguild.com/prompts/fine-tuning-vs-rag-vs-prompting
Tags: fine-tuning, rag, prompt-engineering, customization, ai-strategy
Summary: Three approaches to customizing AI — when each works, the cost and complexity tradeoffs, and which to try first.

Prompt:
"Help me choose between prompt engineering, RAG, and fine-tuning for this use case.
Problem: [describe it]
Knowledge base size: [small, medium, large]
How often it changes: [frequency]
Query volume: [approximate]
Budget and complexity tolerance: [describe]

Recommend the simplest approach that is likely to work, explain why, and tell me what evidence would justify moving to the next level."