# Review and debug Prompt Pack Prompts for tightening requests, reviewing diffs, and debugging without letting the agent thrash. Pack URL: https://aicodingguild.com/prompts/packs/review-and-debug Filtered library URL: https://aicodingguild.com/prompts?path=ai-tools Plain-text export: https://aicodingguild.com/prompts/packs/review-and-debug/txt Featured prompt: Review The Diff Prompt count: 23 ## 1. The AI Coding Tool Landscape Category: Working With AI Tools Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/ai-coding-tool-landscape Prompt page: https://aicodingguild.com/prompts/ai-coding-tool-landscape Tags: ai-tools, cursor, bolt, replit, v0, lovable, comparison Summary: Cursor, Bolt, Replit, v0, Lovable compared — which tool fits your workflow? Prompt: "Help me choose the right AI coding tool for this project. Project type: [describe it] Current stage: [prototype, feature build, maintenance, refactor] My skill level: [describe honestly] Constraints: [privacy, deployment target, code ownership, budget] Recommend: 1. the best primary tool 2. one secondary tool if the project grows 3. the tradeoffs of each 4. the handoff point where I should switch tools instead of forcing one tool to do everything" ## 2. Cursor — The Power User's Choice (Setup and First Steps) Category: Working With AI Tools Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/cursor-setup Prompt page: https://aicodingguild.com/prompts/cursor-setup Tags: ai-tools, cursor, setup, editor Summary: Install Cursor, configure it for vibe coding, and build your first project with AI assistance. Prompt: Help me set up Cursor for this project in a safe way. First, explain whether this task should use chat, inline edit, or Composer. Then propose a short `.cursorrules` file based on this stack and these constraints: - [stack] - [current files or feature area] - no new dependencies without asking - stop before auth, schema, billing, or infra changes After that, help me make one small reviewable change and tell me exactly what I must inspect before I accept it. ## 3. Bolt.new and Lovable — Instant Full-Stack Apps Category: Working With AI Tools Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/bolt-and-lovable Prompt page: https://aicodingguild.com/prompts/bolt-and-lovable Tags: ai-tools, bolt, lovable, prototyping, full-stack Summary: Build complete web applications from a text prompt with Bolt.new and Lovable. Prompt: "I want to prototype this app in Bolt or Lovable. App idea: [describe it] Must-have flow: [describe it] Data fields: [list them] Visual direction: [describe it] Constraints: [auth, payments, storage, deployment, handoff plan] Recommend whether Bolt or Lovable is the better starting point and give me a prompt that is specific enough to produce a usable first prototype." ## 4. Replit — Code, Deploy, and Collaborate in Your Browser Category: Working With AI Tools Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/replit Prompt page: https://aicodingguild.com/prompts/replit Tags: ai-tools, replit, browser-ide, deployment, collaboration Summary: Use Replit for browser-based development, instant deployment, and real-time collaboration. Prompt: "I want to use Replit for this project. Goal: [learning, prototype, collaboration] App idea: [describe it] Constraints: [no local setup, shareable URL, collaboration, budget] Tell me: 1. whether Replit is the right tool 2. which template I should start from 3. what I should keep simple to stay inside Replit's strengths 4. when I should export the code and move to a different environment" ## 5. v0 by Vercel — UI Components From a Text Prompt Category: Working With AI Tools Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/v0-by-vercel Prompt page: https://aicodingguild.com/prompts/v0-by-vercel Tags: ai-tools, v0, vercel, ui-components, design Summary: Generate production-ready UI components with v0 and integrate them into your projects. Prompt: "I want v0 to generate a React component for this screen: [describe the UI, data fields, visual style, empty state, loading state, and mobile behavior] The component must: 1. work in a Next.js + Tailwind project 2. be easy to wire to real data later 3. avoid making up backend logic 4. call out any shadcn/ui dependencies it expects" ## 6. Claude Code — When You Want AI in Your Terminal Category: Working With AI Tools Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/claude-code Prompt page: https://aicodingguild.com/prompts/claude-code Tags: ai-tools, claude-code, terminal, anthropic, advanced Summary: Use Claude Code for terminal-based AI development with deep codebase understanding. Prompt: "I'm using Claude Code on this project. First, read the codebase and summarize: 1. what the app does 2. how the architecture is organized 3. the risky areas to avoid touching casually Then propose a `CLAUDE.md` file and a safe plan for this change: [describe change]. Do not modify [list protected areas] without asking first." ## 7. GitHub Copilot — The AI That Lives in Your Editor Category: Working With AI Tools Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/github-copilot Prompt page: https://aicodingguild.com/prompts/github-copilot Tags: ai-tools, github-copilot, vs-code, code-completion Summary: Set up GitHub Copilot for inline code completions and AI-assisted development in VS Code. Prompt: "I'm using GitHub Copilot in VS Code. Help me get better suggestions for this task: [describe task]. Tell me: 1. what comments or function names I should write first 2. which related files I should open for context 3. when Copilot is likely enough and when I should switch to a stronger multi-file tool 4. what I must review manually before I accept a suggestion" ## 8. 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." ## 9. System Prompts — .cursorrules and CLAUDE.md Explained Category: Working With AI Tools Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/system-prompts Prompt page: https://aicodingguild.com/prompts/system-prompts Tags: ai-tools, system-prompts, cursorrules, claude-md, configuration Summary: Write system prompts that give AI persistent context about your project and preferences. Prompt: **Use this when you want the agent to draft your persistent project instructions:** "Help me write a system prompt file for this project. Tool target: [Cursor / Claude Code / both] Project summary: [what the app does] Stack: [frameworks, languages, key services] Repo conventions: [folders, naming, testing, styling, data access] Constraints: [things the agent must never do] Current phase: [what is already built and what is in progress] Return: 1. A concise `.cursorrules` or `CLAUDE.md` 2. A short list of rules I should not include because they are too vague, too stale, or too noisy 3. A maintenance checklist for keeping this file current as the project changes." ## 10. 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." ## 11. 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." ## 12. 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." ## 13. 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." ## 14. The Build-Review-Iterate Loop Category: Working With AI Tools Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/build-review-iterate Prompt page: https://aicodingguild.com/prompts/build-review-iterate Tags: ai-tools, workflows, vibe-coding, iteration Summary: Master the core vibe coding workflow — generate code, review it critically, and iterate toward your goal. Prompt: "I want to work in a build-review-iterate loop for this feature. Start with the smallest reviewable slice that proves the approach. After you propose or implement that slice, stop and show me: 1. what you changed 2. what assumptions you made 3. what could still go wrong 4. what the next iteration should focus on Keep each iteration scoped to one to three concrete changes. If we pass five iterations on one feature, tell me to step back and reassess instead of patching blindly." ## 15. Review The Diff Category: Review Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/code-review-with-ai Prompt page: https://aicodingguild.com/prompts/code-review-with-ai Tags: ai-tools, workflows, code-review, quality Summary: Use this after an AI-generated change lands so the reviewer focuses on correctness, security, edge cases, and misleading tests. Prompt: "Review the diff between my branch and `main`. For every finding: 1. label it as must-fix, should-fix, consider, or optional 2. explain why it matters 3. point to the relevant file or code section 4. suggest a concrete fix Prioritize bugs, security issues, missing edge cases, and misleading tests. Do not waste time on style commentary unless it affects correctness or maintainability." ## 16. Debug This Without Thrashing Category: Debugging Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/debugging-with-ai Prompt page: https://aicodingguild.com/prompts/debugging-with-ai Tags: ai-tools, workflows, debugging, troubleshooting Summary: Use this when the app is already broken and you need the agent to isolate one likely cause, propose a narrow fix, and define how to verify it. Prompt: "Help me debug this issue systematically. Feature: [what is broken] Error or symptom: [full message or precise symptom] Expected behavior: [what should happen] Actual behavior: [what happens instead] Steps to reproduce: [exact steps] Relevant code: [paste code] What I've already tried: [list] First tell me the likely root causes in order. Then give me the smallest fix to test first. After that, tell me how I should verify the fix and what related areas I should retest." ## 17. Refactoring With AI — Making Code Better Without Breaking It Category: Working With AI Tools Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/refactoring-with-ai Prompt page: https://aicodingguild.com/prompts/refactoring-with-ai Tags: ai-tools, workflows, refactoring, code-quality Summary: Use AI to safely improve, reorganize, and simplify existing code without changing what it does. Prompt: "Help me refactor this code without changing behavior. First explain what the current code does and what parts are risky to change. Then propose the smallest valuable refactoring step. For that step, show me: 1. the files involved 2. what behavior must stay the same 3. what tests or manual checks should prove we did not break anything Do not mix new features into this refactor. If the refactor is too large, split it into reviewable phases." ## 18. When to Stop Prompting and Start Reading Category: Working With AI Tools Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/when-to-stop-prompting Prompt page: https://aicodingguild.com/prompts/when-to-stop-prompting Tags: ai-tools, workflows, learning, understanding Summary: Recognize when AI stops helping and learn when reading code yourself is the faster path forward. Prompt: "Do not suggest code changes yet. Help me understand this flow first. Walk me through what happens from [user action] to [visible result]. Reference the key files, functions, and state changes in order. Then tell me: 1. which part I seem not to understand yet 2. what questions I should answer before prompting for a fix 3. whether the better next move is explanation, debugging, refactoring, or a new implementation prompt" ## 19. How LLMs Actually Work — For Non-ML People Category: Working With AI Tools Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/how-llms-work Prompt page: https://aicodingguild.com/prompts/how-llms-work Tags: llm, tokens, context-window, attention, temperature, ai-fundamentals Summary: Understand tokens, context windows, attention, and temperature without a single equation. Prompt: "Explain this model behavior in practical coding terms: - why the output changed between runs - why context seems to fade in a long conversation - how I should structure prompts for better focus Use tokens, context windows, attention, and temperature in the explanation, but keep it tied to real development workflows." ## 20. OpenAI vs Anthropic vs Open Source — An Honest Comparison Category: Working With AI Tools Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/openai-vs-anthropic-vs-open-source Prompt page: https://aicodingguild.com/prompts/openai-vs-anthropic-vs-open-source Tags: openai, anthropic, open-source, llama, comparison, ai-models Summary: Compare the major AI model providers — strengths, weaknesses, pricing, and when to use which. Prompt: "Help me choose an AI provider strategy for my work. Stack: [describe stack] Task mix: [quick edits, debugging, architecture, code review, private code] Constraints: [budget, privacy, offline needs, existing subscriptions] Recommend: 1. the best default provider 2. when to switch to another provider or model family 3. where open source is worth considering 4. the biggest tradeoffs I should test myself instead of trusting benchmarks" ## 21. API Keys, Rate Limits, and Cost Management Category: Working With AI Tools Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/api-keys-rate-limits-costs Prompt page: https://aicodingguild.com/prompts/api-keys-rate-limits-costs Tags: api-keys, rate-limits, costs, pricing, budget, ai-operations Summary: Understand AI API pricing, rate limits, budgets, and how to monitor and control your AI spending. Prompt: "Help me operationalize AI API usage for this app. I need: 1. a secure API key handling plan for local, CI, and production 2. a rate-limit and retry strategy for 429s 3. a budget recommendation 4. guidance on which model tier to use for which task 5. a monitoring checklist so costs do not surprise me" ## 22. 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." ## 23. Running Local Models — Ollama and LM Studio Category: Working With AI Tools Path: Working With AI Tools Lesson: https://aicodingguild.com/learn/ai-tools/running-local-models Prompt page: https://aicodingguild.com/prompts/running-local-models Tags: ollama, lm-studio, local-models, privacy, self-hosted, llama Summary: Run AI models on your own machine — privacy benefits, performance tradeoffs, setup guides, and when local makes sense. Prompt: "Design a local AI coding setup for me. Hardware: [CPU/GPU/RAM] Operating system: [OS] Constraints: [privacy, offline use, budget] Typical tasks: [simple coding help, reviews, refactors, chat] Recommend: 1. the best local model size I can realistically run 2. whether Ollama or LM Studio is the better starting point 3. what tool integration I should use 4. which tasks should still go to cloud models if policy allows"