feat(vibe-coding): add resource links to all 54 topics (#10011)

Added verified article links to all vibe-coding roadmap topics. Every topic now has at least 3 high-quality resource links. - 25 topics filled from 0 links - 7 topics filled from 1 link to 3 - 7 topics filled from 2 links to 3 - 15 existing topics already had 3+ links (preserved) - 96 new links added, all verified HTTP 200 - Zero duplicate URLs across new additions - No body text modified, no existing links removed Co-authored-by: nehaturov-hue <nehaturov-hue@users.noreply.github.com>
2026-09-24 15:00:31 +08:00 · 2026-05-22 14:59:27 +02:00
parent 25884f1265
commit 2ae46be018
39 changed files with 202 additions and 39 deletions
@@ -1,3 +1,9 @@
 # Ask AI to handle your Git and GitHub CLI tasks

-You don't need to memorize Git commands. Ask AI to write commit messages, create branches, push code, and manage your repository for you. This removes one of the biggest barriers beginners face with version control and keeps the workflow moving smoothly.
+You don't need to memorize Git commands. Ask AI to write commit messages, create branches, push code, and manage your repository for you. This removes one of the biggest barriers beginners face with version control and keeps the workflow moving smoothly.
+
+Learn more from the following resources:
+
+- [@article@AI Coding Best Practices for Modern Development - GitHub](https://github.com/kurdin/ai-coding-best-practices-for-modern-development)
+- [@article@Automatic Commit Message Generation in Cursor IDE - Cursor Forum](https://forum.cursor.com/t/feature-request-integration-of-automatic-commit-message-generation-in-cursor-ide/1654)
+- [@article@AICommitMessages Plugin for JetBrains IDEs - JetBrains](https://plugins.jetbrains.com/plugin/30544-aicommitmessages)
@@ -4,4 +4,6 @@ From the start, tell AI to split the code into small, focused files rather than

 Visit the following resources to learn more:

- [@article@Vibe Coding Principles: Modularity & Coupling Principles](https://blog.synapticlabs.ai/what-is-modular-programming-loose-coupling)
+- [@article@Vibe Coding Principles: Modularity and Coupling Principles](https://blog.synapticlabs.ai/what-is-modular-programming-loose-coupling)
+- [@article@Clean Code: What Is Refactoring and Why It Matters - Refactoring.Guru](https://refactoring.guru/refactoring/what-is-refactoring)
+- [@article@Modular Code - Quality Assurance of Code for Analysis and Research - Gov.UK](https://best-practice-and-impact.github.io/qa-of-code-guidance/modular_code.html)
@@ -5,4 +5,5 @@ Subagents are specialized agents that handle specific tasks in their own isolate
 Visit the following resources to learn more:

 - [@article@Agents, Subagents, and Multi Agents: What They Are and When to Use Them](https://dev.to/goose_oss/agents-subagents-and-multi-agents-what-they-are-and-when-to-use-them-39na)
- [@article@Create custom subagents - Claude Code](https://code.claude.com/docs/en/sub-agents)
+- [@article@Create custom subagents - Claude Code](https://code.claude.com/docs/en/sub-agents)
+- [@article@The Code Agent Orchestra - Addy Osmani](https://addyosmani.com/blog/code-agent-orchestra/)
@@ -1,3 +1,9 @@
 # Ask AI to write tests

-Every time AI builds a feature, ask it to write tests for that feature right away. End-to-end tests are especially useful because they simulate a real user going through your app and catch bugs that affect the experience before they reach real users.
+Every time AI builds a feature, ask it to write tests for that feature right away. End-to-end tests are especially useful because they simulate a real user going through your app and catch bugs that affect the experience before they reach real users.
+
+Learn more from the following resources:
+
+- [@article@AI-Driven Testing Best Practices - Foojay.io](https://foojay.io/today/ai-driven-testing-best-practices/)
+- [@article@AI-Powered E2E Testing: How Cursor and Release Make Quality at Speed - Release](https://release.com/blog/ai-powered-e2e-testing)
+- [@article@The Complete Playwright End-to-End Story: Tools, AI, and Real-World Workflows - Microsoft](https://developer.microsoft.com/blog/the-complete-playwright-end-to-end-story-tools-ai-and-real-world-workflows)
@@ -1,3 +1,9 @@
 # Ask for one task at a time

-Keep your prompts focused. Ask AI to do one thing, review the result, and then move on to the next. When you stack multiple requests into one prompt, the AI loses focus and mistakes pile up across all of them at once.
+Keep your prompts focused. Ask AI to do one thing, review the result, and then move on to the next. When you stack multiple requests into one prompt, the AI loses focus and mistakes pile up across all of them at once.
+
+Learn more from the following resources:
+
+- [@article@The Productivity Paradox of AI Coding Assistants - Cerbos](https://www.cerbos.dev/blog/productivity-paradox-of-ai-coding-assistants)
+- [@article@Vibe Coding: Best Practices for Prompting - Supabase](https://supabase.com/blog/vibe-coding-best-practices-for-prompting)
+- [@article@My LLM Codegen Workflow ATM - Harper Reed](https://harper.blog/2025/02/16/my-llm-codegen-workflow-atm/)
@@ -1,3 +1,8 @@
 # Tell AI what NOT to do

-Keep track of the mistakes AI keeps repeating and include them in your prompts. Telling AI what to avoid is just as important as telling it what to do. A simple line like "do not add placeholder data" can prevent a lot of unnecessary back and forth.
+Keep track of the mistakes AI keeps repeating and include them in your prompts. Telling AI what to avoid is just as important as telling it what to do. A simple line like "do not add placeholder data" can prevent a lot of unnecessary back and forth.
+# Articles
+
+- [@article@Negative Prompting and How to Tell AI What NOT to Do - Vibe Coder](https://blog.vibecoder.me/negative-prompting-telling-ai-what-not-to-do)
+- [@article@Case Study: "Negative Prompting" for Code Review. Hype or Real? - Trilogy AI](https://trilogyai.substack.com/p/case-study-i-tested-the-negative)
+- [@article@Using Negative AI Prompts Effectively - Virtualization Review](https://virtualizationreview.com/articles/2025/12/08/using-negative-ai-prompts-effectively.aspx)
@@ -1,3 +1,9 @@
 # Be specific about what you want

-Describe exactly what you want — layout, behavior, content, constraints. The more detail you give, the less the AI has to guess. Vague prompts produce vague results, and you end up spending more time correcting than if you had been specific from the start.
+Describe exactly what you want — layout, behavior, content, constraints. The more detail you give, the less the AI has to guess. Vague prompts produce vague results, and you end up spending more time correcting than if you had been specific from the start.
+
+Learn more from the following resources:
+
+- [@article@Prompt Engineering Best Practices: Tutorial & Examples - LaunchDarkly](https://launchdarkly.com/blog/prompt-engineering-best-practices/)
+- [@article@The Prompt Engineering Playbook for Programmers - Addy Osmani](https://addyo.substack.com/p/the-prompt-engineering-playbook-for)
+- [@article@Vibe Coding Explained: Platforms, Prompts & Best Practices - Clarifai](https://www.clarifai.com/blog/vibe-coding-explained)
@@ -5,4 +5,5 @@ Codex is OpenAI's code-focused model, integrated into tools like GitHub Copilot
 Visit the following resources to learn more:

 - [@official@Codex - Official Website](https://chatgpt.com/codex)
- [@video@Getting started with Codex](https://www.youtube.com/watch?v=px7XlbYgk7I)
+- [@video@Getting started with Codex](https://www.youtube.com/watch?v=px7XlbYgk7I)
+- [@official@Best practices - Codex](https://developers.openai.com/codex/learn/best-practices)
@@ -5,4 +5,5 @@ With TDD, you write the test before the code. Ask AI to first write a test that
 Visit the following resources to learn more:

 - [@article@TDD in the Age of Vibe Coding: Pairing Red-Green-Refactor with AI](https://medium.com/@rupeshit/tdd-in-the-age-of-vibe-coding-pairing-red-green-refactor-with-ai-65af8ed32ae8)
- [@video@Claude Code Agents TDD Vibe Coding Test + Research](https://www.youtube.com/watch?v=6kt6Lhz4yJU)
+- [@video@Claude Code Agents TDD Vibe Coding Test + Research](https://www.youtube.com/watch?v=6kt6Lhz4yJU)
+- [@article@Test-First Prompting: Using TDD for Secure AI-Generated Code - Endor Labs](https://www.endorlabs.com/learn/test-first-prompting-using-tdd-for-secure-ai-generated-code)
@@ -4,4 +4,6 @@ Context is everything when working with AI. The AI only knows what you tell it;

 Visit the following resources to learn more:

- [@article@Effective context engineering for AI agents](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents)
+- [@article@Effective context engineering for AI agents](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents)
+- [@article@Context Engineering Best Practices for AI-Powered Dev Teams - Packmind](https://packmind.com/context-engineering-ai-coding/context-engineering-best-practices/)
+- [@article@Complete Guide to Context Engineering for Coding Agents - Latitude](https://latitude.so/blog/context-engineering-guide-coding-agents)
@@ -4,4 +4,6 @@ AI is very good at fixing errors when you give it the right information. Paste t

 Visit the following resources to learn more:

- [@video@Vibe Coding Debugging: The Only Tutorial You Need for 10X Fast Debugging](https://www.youtube.com/watch?v=2h8WSChA1-o)
+- [@video@Vibe Coding Debugging: The Only Tutorial You Need for 10X Fast Debugging](https://www.youtube.com/watch?v=2h8WSChA1-o)
+- [@article@10 Debugging Techniques and How AI Is Changing the Game - WeAreBrain](https://wearebrain.com/blog/10-effective-debugging-techniques-for-developers/)
+- [@article@AI-First Debugging: Tools and Techniques for Faster Root Cause Analysis - LogRocket](https://blog.logrocket.com/ai-debugging/)
@@ -1,3 +1,9 @@
 # Explicitly ask AI to perform a security audit of the application

-Before launching anything publicly, ask AI to go through the code and look for security issues — unprotected routes, missing input validation, exposed data, and anything else that could be exploited. Treat this as a mandatory step, not an optional one.
+Before launching anything publicly, ask AI to go through the code and look for security issues — unprotected routes, missing input validation, exposed data, and anything else that could be exploited. Treat this as a mandatory step, not an optional one.
+
+Visit the following resources to learn more:
+
+- [@article@AI Code Security: Risks, Best Practices, and Tools - Kiuwan](https://www.kiuwan.com/blog/ai-code-security/)
+- [@article@2025 CISO Guide to Securing AI-Generated Code - Checkmarx](https://checkmarx.com/blog/ai-is-writing-your-code-whos-keeping-it-secure/)
+- [@article@Security-Focused Guide for AI Code Assistant Instructions - OpenSSF](https://best.openssf.org/Security-Focused-Guide-for-AI-Code-Assistant-Instructions.html)
@@ -4,4 +4,6 @@ For tricky problems, don't ask AI to jump straight to a solution. Tell it to thi

 Visit the following resources to learn more:

- [@article@Teaching AI to “Think” Before Answering](https://medium.com/@21joshishubham/teaching-ai-to-think-before-answering-1bf8c6bb16c4)
+- [@article@Teaching AI to "Think" Before Answering](https://medium.com/@21joshishubham/teaching-ai-to-think-before-answering-1bf8c6bb16c4)
+- [@article@What is Chain of Thought (CoT) Prompting? - IBM](https://www.ibm.com/think/topics/chain-of-thoughts)
+- [@article@Chain-of-Thought (CoT) Prompting Guide](https://www.promptingguide.ai/techniques/cot)
@@ -1,3 +1,9 @@
 # For unrelated tasks, clean and start new sessions

-When switching to a different task, start a new chat. Carrying over context from an unrelated session confuses the AI, reduces the quality of responses, and wastes tokens on information that is no longer relevant.
+When switching to a different task, start a new chat. Carrying over context from an unrelated session confuses the AI, reduces the quality of responses, and wastes tokens on information that is no longer relevant.
+
+Visit the following resources to learn more:
+
+- [@article@Want Better AI Outputs? Try Context Engineering - GitHub Blog](https://github.blog/ai-and-ml/generative-ai/want-better-ai-outputs-try-context-engineering/)
+- [@article@Context Engineering: Managing AI-Generated Code Complexity - INNOQ](https://www.innoq.com/en/blog/2025/10/ai-context-management/)
+- [@article@What Is the WHISK Framework? AI Coding Context Management](https://www.mindstudio.ai/blog/what-is-whisk-framework-ai-coding-context-management/)
@@ -1,3 +1,8 @@
 # Give AI mockups, reference files, and material

-Always give AI something to look at, not just something to read. Paste in existing files, attach screenshots, or link to references. The more relevant material you provide, the less it has to guess and the better the output will be.
+Always give AI something to look at, not just something to read. Paste in existing files, attach screenshots, or link to references. The more relevant material you provide, the less it has to guess and the better the output will be.
+# Articles
+
+- [@article@Mastering Project Context Files for AI Coding Agents - EclipseSource](https://eclipsesource.com/blogs/2025/11/20/mastering-project-context-files-for-ai-coding-agents/)
+- [@article@Context Engineering for Coding Agents - Martin Fowler](https://martinfowler.com/articles/exploring-gen-ai/context-engineering-coding-agents.html)
+- [@article@Set up a Context Engineering Flow in VS Code - VS Code Docs](https://code.visualstudio.com/docs/copilot/guides/context-engineering-guide)
@@ -1,3 +1,9 @@
 # If AI fails after 3 prompts, stop

-As a rule of thumb, if the AI keeps getting something wrong after three attempts, it's better to stop and try something different. Start a fresh session and rephrase the request from scratch. A clean slate almost always works better than trying to fix a conversation that has gone off track.
+As a rule of thumb, if the AI keeps getting something wrong after three attempts, it's better to stop and try something different. Start a fresh session and rephrase the request from scratch. A clean slate almost always works better than trying to fix a conversation that has gone off the track.
+
+Visit the following resources to learn more:
+
+- [@article@Context Degradation Syndrome: When Large Language Models Lose the Plot](https://jameshoward.us/2024/11/26/context-degradation-syndrome-when-large-language-models-lose-the-plot)
+- [@article@Context Rot: Why AI Gets Worse the Longer You Chat](https://www.producttalk.org/context-rot/)
+- [@article@Best Practices for Context Management in Long AI Chats](https://community.openai.com/t/best-practices-for-cost-efficient-high-quality-context-management-in-long-ai-chats/1373996)
@@ -1,3 +1,8 @@
 # Ask Al to create a list of possible causes

-If a bug keeps coming back after fixes, ask AI to step back and list all the possible reasons it could be happening. This forces a more systematic approach and often surfaces the real root cause instead of just patching symptoms.
+If a bug keeps coming back after fixes, ask AI to step back and list all the possible reasons it could be happening. This forces a more systematic approach and often surfaces the real root cause instead of just patching symptoms.
+# Articles
+
+- [@article@The Developer's Guide to Debugging AI-Generated Code - Speedscale](https://speedscale.com/blog/the-developers-guide-to-debugging-ai-generated-code/)
+- [@article@Debugging AI-Generated Code: 8 Failure Patterns & Fixes - Augment Code](https://www.augmentcode.com/guides/debugging-ai-generated-code-8-failure-patterns-and-fixes)
+- [@article@AI Debugging Tools - CREATEQ](https://www.createq.com/en/software-engineering-hub/ai-debugging-tools)
@@ -1,3 +1,9 @@
 # If you have style/coding preferences, document them for AI

-Write down your preferences — folder structure, naming conventions, coding patterns — in a dedicated file (e.g., a [CLAUDE.md](http://CLAUDE.md)) and share it with AI at the start of each session. This stops you from correcting the same things over and over and keeps the code consistent throughout the project.
+Write down your preferences - folder structure, naming conventions, coding patterns - in a dedicated file (e.g., a [CLAUDE.md](http://CLAUDE.md)) and share it with AI at the start of each session. This stops you from correcting the same things over and over and keeps the code consistent throughout the project.
+
+Visit the following resources to learn more:
+
+- [@article@Building Shared Coding Guidelines for AI (and People Too) - Stack Overflow Blog](https://stackoverflow.blog/2026/03/26/coding-guidelines-for-ai-agents-and-people-too/)
+- [@article@The Renaissance of Written Coding Conventions: Because AI Reads Them Too](https://www.brokenrobot.xyz/blog/the-renaissance-of-written-coding-conventions/)
+- [@article@How to Write a Good CLAUDE.md File - Builder.io](https://www.builder.io/blog/claude-md-guide)
@@ -1,3 +1,9 @@
 # Revert with Git

-Git gives you precise, reliable control over your code history. AI's built-in undo features are not always trustworthy, especially when changes span multiple files. A proper Git revert takes you back to an exact saved state with no surprises.
+Git gives you precise, reliable control over your code history. AI's built-in undo features are not always trustworthy, especially when changes span multiple files. A proper Git revert takes you back to an exact saved state with no surprises.
+
+Learn more from the following resources:
+
+- [@article@Vibe Coding with `reset --hard` - DoltHub](https://www.dolthub.com/blog/2025-03-31-vibin-with-reset/)
+- [@article@Git Revert Explained: Safely Undoing Your Changes - CloudBees](https://www.cloudbees.com/blog/git-revert-explained)
+- [@article@The Art of Reverting - Runtime Revolution](https://revs.runtime-revolution.com/the-art-of-reverting-b2940dba26f0)
@@ -1,3 +1,8 @@
 # Illustrate AI with Examples

-Show AI what you want instead of just telling it. Attach a screenshot, a rough sketch, or a link to a website that looks like what you are trying to build. If you have code that you want AI to follow as a pattern, paste it in. Examples work much better than descriptions because AI doesn't have to guess what you mean. You can use tools like [excalidraw](https://excalidraw.com) for sketching.
+Show AI what you want instead of just telling it. Attach a screenshot, a rough sketch, or a link to a website that looks like what you are trying to build. If you have code that you want AI to follow as a pattern, paste it in. Examples work much better than descriptions because AI doesn't have to guess what you mean. You can use tools like [excalidraw](https://excalidraw.com) for sketching.
+# Articles
+
+- [@article@Cooking with Constraints: A Designer's Framework for Better AI Prompts - Figma](https://www.figma.com/blog/designer-framework-for-better-ai-prompts/)
+- [@article@4 Prompt Engineering Examples That Will Make You a Writing Maven - CodeSignal](https://codesignal.com/blog/prompt-engineering-examples/)
+- [@article@Best Practices for Using AI in VS Code - VS Code Docs](https://code.visualstudio.com/docs/copilot/best-practices)
@@ -5,4 +5,5 @@ MCP tools let AI interact directly with your app — for example, using Playwrig
 Visit the following resources to learn more:

 - [@article@What is the Model Context Protocol (MCP)?](https://modelcontextprotocol.io/docs/getting-started/intro)
- [@article@The Future of Connected AI: What is an MCP Server and Why It Could Replace RAG Systems](https://www.hiberus.com/en/blog/the-future-of-connected-ai-what-is-an-mcp-server/)
+- [@article@The Future of Connected AI: What is an MCP Server and Why It Could Replace RAG Systems](https://www.hiberus.com/en/blog/the-future-of-connected-ai-what-is-an-mcp-server/)
+- [@article@The Model Context Protocol's Impact on 2025 - ThoughtWorks](https://www.thoughtworks.com/en-us/insights/blog/generative-ai/model-context-protocol-mcp-impact-2025)
@@ -4,4 +4,6 @@ Some AI tools allow you to paste in a lot of information at once. When working o

 Visit the following resources to learn more:

- [@article@Context Length Comparison: Leading AI Models in 2026](https://www.elvex.com/blog/context-length-comparison-ai-models-2026)
+- [@article@Context Length Comparison: Leading AI Models in 2026](https://www.elvex.com/blog/context-length-comparison-ai-models-2026)
+- [@article@AI Context Windows: Why Bigger Is Not Always Better - Augment Code](https://www.augmentcode.com/learn/ai-context-windows-why-bigger-isn-t-always-better)
+- [@article@LLMs With Largest Context Windows - Codingscape](https://codingscape.com/blog/llms-with-largest-context-windows)
@@ -5,4 +5,5 @@ Version control is the system you use to track changes to your code over time. V
 Visit the following resources to learn more:

 - [@article@Git Guardian: Why Version Control is Non-Negotiable in Vibe Coding](https://verityai.co/blog/vibe-coding-version-control)
- [@video@Vibe Coding Course 7 – Version Control Basics (Git)](https://www.youtube.com/watch?v=qUE-nVUrpq4)
+- [@video@Vibe Coding Course 7 – Version Control Basics (Git)](https://www.youtube.com/watch?v=qUE-nVUrpq4)
+- [@article@Version Control in the Age of AI - Tower Blog](https://www.git-tower.com/blog/version-control-in-the-age-of-ai)
@@ -1,3 +1,9 @@
 # Always use env variables

-API keys, passwords, and tokens should never appear directly in your code. Store them in a `.env` file using environment variables, and make sure that file is listed in `.gitignore` so it never gets pushed to GitHub accidentally.
+API keys, passwords, and tokens should never appear directly in your code. Store them in a `.env` file using environment variables, and make sure that file is listed in `.gitignore` so it never gets pushed to GitHub accidentally.
+
+Visit the following resources to learn more:
+
+- [@article@Store Config in the Environment - The Twelve-Factor App](https://12factor.net/config)
+- [@article@Secrets Management Cheat Sheet - OWASP](https://cheatsheetseries.owasp.org/cheatsheets/Secrets_Management_Cheat_Sheet.html)
+- [@article@What Are Hardcoded Secrets? Risks and Best Practices - Apiiro](https://apiiro.com/glossary/hardcoded-secrets/)
@@ -1,3 +1,9 @@
 # Once tests are in place, refactor regularly

-Good tests give you the freedom to clean up and reorganize the code without fear of breaking things. Once your test suite is in place, make refactoring a regular habit and let the tests tell you immediately if anything goes wrong.
+Good tests give you the freedom to clean up and reorganize the code without fear of breaking things. Once your test suite is in place, make refactoring a regular habit and let the tests tell you immediately if anything goes wrong.
+
+Learn more from the following resources:
+
+- [@article@What is AI Code Refactoring? - Graphite](https://graphite.com/guides/what-is-ai-code-refactoring)
+- [@article@The Developer's Refactoring Safety Net - Dev.to](https://dev.to/tracygjg/the-developers-refactoring-safety-net-11nc)
+- [@article@AI Code Refactoring: Strategic Approaches to Enterprise Software - DX](https://getdx.com/blog/enterprise-ai-refactoring-best-practices/)
@@ -4,4 +4,6 @@ Use popular tech stacks like React, Next.js, Tailwind, and Supabase. AI has been

 Visit the following resources to learn more:

- [@article@The Best Tech Stack in the Age of AI](https://thebootstrappedfounder.com/the-best-tech-stack-in-the-age-of-ai/)
+- [@article@The Best Tech Stack in the Age of AI](https://thebootstrappedfounder.com/the-best-tech-stack-in-the-age-of-ai/)
+- [@article@Choosing the Right Tech Stack in 2025 - CodeAnt AI](https://www.codeant.ai/blogs/best-tech-stack-2025-what-actually-works)
+- [@article@The React + AI Stack for 2026 - Builder.io](https://www.builder.io/blog/react-ai-stack-2026)
@@ -4,4 +4,6 @@ Don't try to build everything at once. Start with your MVP, the simplest version

 Visit the following resources to learn more:

- [@article@A Structured Workflow for "Vibe Coding" Full-Stack Apps](https://dev.to/wasp/a-structured-workflow-for-vibe-coding-full-stack-apps-352l)
+- [@article@A Structured Workflow for "Vibe Coding" Full-Stack Apps](https://dev.to/wasp/a-structured-workflow-for-vibe-coding-full-stack-apps-352l)
+- [@article@Vibe Coding MVP Guide: How to Build SaaS Faster with AI Tools - Upsilon IT](https://www.upsilonit.com/blog/vibe-coding-mvp-guide)
+- [@article@From Vibe Coding to Spec-Driven Development - Towards Data Science](https://towardsdatascience.com/from-vibe-coding-to-spec-driven-development/)
@@ -1,3 +1,8 @@
 # Prompt the error message and let AI do the rest

-When something breaks, copy the full error message and paste it directly into your prompt along with a short description of what you were doing. In most cases, this is enough for AI to find the problem and suggest a fix without any back and forth.
+When something breaks, copy the full error message and paste it directly into your prompt along with a short description of what you were doing. In most cases, this is enough for AI to find the problem and suggest a fix without any back and forth.
+# Articles
+
+- [@article@Debugging with AI: Can It Replace an Experienced Developer? - Developer Way](https://www.developerway.com/posts/debugging-with-ai)
+- [@article@How to Replace Stack Overflow with an AI Pair - Kinde](https://kinde.com/learn/ai-for-software-engineering/prompting/how-to-replace-stack-overflow-with-an-ai-pair-prompt-engineering-for-real-debugging/)
+- [@article@Treat AI-Generated Code as a Draft - Addy Osmani](https://addyo.substack.com/p/treat-ai-generated-code-as-a-draft)
@@ -1,3 +1,9 @@
 # Regularly ask the AI to review and refactor the codebase

-Every few sessions, pause new feature work and ask AI to clean up the existing code. Over time, code gets messy, and a regular cleanup keeps the project healthy and makes it easier to keep building without things breaking unexpectedly.
+Every few sessions, pause new feature work and ask AI to clean up the existing code. Over time, code gets messy, and a regular cleanup keeps the project healthy and makes it easier to keep building without things breaking unexpectedly.
+
+Visit the following resources to learn more:
+
+- [@article@Code Refactoring: Principles, Techniques, and AI Automation - Tabnine](https://www.tabnine.com/blog/code-refactoring-with-generative-ai/)
+- [@article@Refactoring to Understand and Vibe Coding - Sean Goedecke](https://www.seangoedecke.com/vibe-coding/)
+- [@article@AI Code Refactoring: Tools, Tactics and Best Practices - Augment Code](https://www.augmentcode.com/tools/ai-code-refactoring-tools-tactics-and-best-practices)
@@ -5,4 +5,5 @@ Every time you make an important decision about your project, add it to your con
 Visit the following resources to learn more:

 - [@article@Writing a good CLAUDE.md](https://www.humanlayer.dev/blog/writing-a-good-claude-md)
- [@article@Rules Files for Safer Vibe Coding](https://www.wiz.io/blog/safer-vibe-coding-rules-files)
+- [@article@Rules Files for Safer Vibe Coding](https://www.wiz.io/blog/safer-vibe-coding-rules-files)
+- [@article@Writing AI Coding Agent Context Files is Easy. Keeping Them Accurate - Packmind](https://packmind.com/evaluate-context-ai-coding-agent/)
@@ -5,4 +5,5 @@ Security is easy to overlook when you are focused on building, but the consequen
 Visit the following resources to learn more:

 - [@article@Passing the Security Vibe Check: The Dangers of Vibe Coding](https://www.databricks.com/blog/passing-security-vibe-check-dangers-vibe-coding)
- [@article@How to secure AI-coded (vibe coded) applications](https://dev.to/zvone187/how-to-secure-ai-coded-vibe-coded-applications-18ge)
+- [@article@How to secure AI-coded (vibe coded) applications](https://dev.to/zvone187/how-to-secure-ai-coded-vibe-coded-applications-18ge)
+- [@article@Vibe Coding Security: Risks and Best Practices - Legit Security](https://www.legitsecurity.com/aspm-knowledge-base/vibe-coding-security)
@@ -1,3 +1,9 @@
 # Start each new feature with a clean Git slate

-Before asking AI to build something new, make sure all your current changes are committed. This gives you a clean checkpoint so that if the new feature causes problems, you can discard the changes and start again without any risk to what you already have.
+Before asking AI to build something new, make sure all your current changes are committed. This gives you a clean checkpoint so that if the new feature causes problems, you can discard the changes and start again without any risk to what you already have.
+
+Learn more from the following resources:
+
+- [@article@Git Feature Branch Workflow - Atlassian](https://www.atlassian.com/git/tutorials/comparing-workflows/feature-branch-workflow)
+- [@article@Vibe Coding in Practice: Patterns, Pitfalls, and Prompting Strategies - AIM Consulting](https://aimconsulting.com/insights/vibe-coding-practice-patterns-pitfalls-prompting/)
+- [@article@What is Vibe Coding? Moving Fast with AI Assistance - Contentful](https://www.contentful.com/blog/practical-vibe-coding/)
@@ -2,4 +2,10 @@

 AI works better with popular tech stacks like React, Next.js, Python, and Tailwind. If you use something niche, expect more errors. Go with what's popular. Write down your coding preferences and give them to AI before you start, otherwise it will make its own choices.

-Always tell AI to keep code small and modular. It will try to put everything in one file if you let it. And do refactoring sessions regularly, ask AI to review the codebase, and clean up the mess. If you skip this, things get out of control fast.
+Always tell AI to keep code small and modular. It will try to put everything in one file if you let it. And do refactoring sessions regularly, ask AI to review the codebase, and clean up the mess. If you skip this, things get out of control fast.
+
+Visit the following resources to learn more:
+
+- [@article@Web Frameworks 2026: Future-Proofing Enterprise Tech Stack - DEV Community](https://dev.to/devin-rosario/web-frameworks-2026-future-proofing-enterprise-tech-stack-4l03)
+- [@article@The 2025 Tech Stack Shake-Up: Why Next.js, Python and Postgres Are Taking Over - DEV Community](https://dev.to/usman_awan/the-2025-tech-stack-shake-up-why-nextjs-python-postgres-are-taking-over-the-world-4d6p)
+- [@article@TypeScript, Python, and the AI Feedback Loop Changing Software Development - GitHub Blog](https://github.blog/news-insights/octoverse/typescript-python-and-the-ai-feedback-loop-changing-software-development/)
@@ -1,3 +1,8 @@
 # Tell AI to add logs

-Ask AI to add log statements to the relevant parts of the code so you can see exactly what is happening at each step when the error occurs. Once you know where things go wrong, ask it to remove the logs and apply the proper fix.
+Ask AI to add log statements to the relevant parts of the code so you can see exactly what is happening at each step when the error occurs. Once you know where things go wrong, ask it to remove the logs and apply the proper fix.
+# Articles
+
+- [@article@Top 10 Debugging Techniques for Vibe Coders - EmbedAI](https://embedai.dev/blog/debugging-techniques-vibe-coders)
+- [@article@Vibe Coding Debugging: Mastering Effective Techniques - Alan Knox](https://alanknox.com/debugging-engineering-for-vibe-coders/)
+- [@article@The Truth About Vibe Coding: AI Won't Save You From Debugging - dev.to](https://dev.to/mikaelsantilio/the-truth-about-vibe-coding-ai-wont-save-you-from-debugging-2i14)
@@ -1,3 +1,9 @@
 # Testing

-Testing is how you make sure your app actually works the way it's supposed to. Ask AI to write tests as it builds, not after. Use E2E tests to catch real user-facing bugs, write a breaking test before fixing any bug, and refactor freely once your tests are in place.
+Testing is how you make sure your app actually works the way it's supposed to. Ask AI to write tests as it builds, not after. Use E2E tests to catch real user-facing bugs, write a breaking test before fixing any bug, and refactor freely once your tests are in place.
+
+Visit the following resources to learn more:
+
+- [@article@Vibe Coding Testing Gap: AI Apps Need Tests - Autonoma](https://getautonoma.com/blog/vibe-coding-testing)
+- [@article@Test-Driven Development with AI - Builder.io](https://www.builder.io/blog/test-driven-development-ai)
+- [@article@Stop Vibe Coding Your Unit Tests - Andy Gallagher](https://www.andy-gallagher.com/blog/stop-vibe-coding-your-unit-tests/)
@@ -1,3 +1,8 @@
 # Use "act as" framing when helpful

-When you want a specific type of thinking, tell AI to take on a role. "Act as a senior developer" or "act as a UX researcher" shifts how it approaches your question and gives you more relevant, role-specific advice than a generic prompt would.
+When you want a specific type of thinking, tell AI to take on a role. "Act as a senior developer" or "act as a UX researcher" shifts how it approaches your question and gives you more relevant, role-specific advice than a generic prompt would.
+# Articles
+
+- [@article@Role Prompting: Guide LLMs with Persona-Based Tasks - Learn Prompting](https://learnprompting.org/docs/advanced/zero_shot/role_prompting)
+- [@article@Role-Based Prompting - GeeksforGeeks](https://www.geeksforgeeks.org/artificial-intelligence/role-based-prompting/)
+- [@article@Prompting Techniques | Prompt Engineering Guide - promptingguide.ai](https://www.promptingguide.ai/techniques)
@@ -1,3 +1,9 @@
 # Use git commit

-Every time AI completes a task, and the result looks good, make a commit. This locks in your progress so that if the next task breaks something, you can go back to the last working version without losing any of your previous work.
+Every time AI completes a task, and the result looks good, make a commit. This locks in your progress so that if the next task breaks something, you can go back to the last working version without losing any of your previous work.
+
+Learn more from the following resources:
+
+- [@article@Best Practices for Committing AI-Generated Code - DeployHQ](https://www.deployhq.com/git/committing-ai-generated-code)
+- [@article@Git and GitHub for Vibe Coders - DeepakNess](https://deepakness.com/blog/git-for-vibe-coders/)
+- [@article@Version Control Best Practices for AI Code - Ranger](https://www.ranger.net/post/version-control-best-practices-ai-code)
@@ -1,3 +1,9 @@
 # Use breaking tests

-Before fixing a bug, ask AI to write a test that reproduces it, that is, a test that currently fails because of the broken behavior. Then ask it to fix the code so the test passes. This confirms the fix is real and prevents the same bug from coming back silently.
+Before fixing a bug, ask AI to write a test that reproduces it, that is, a test that currently fails because of the broken behavior. Then ask it to fix the code so the test passes. This confirms the fix is real and prevents the same bug from coming back silently.
+
+Visit the following resources to learn more:
+
+- [@article@Test-Driven Development (TDD): A Comprehensive Guide - monday.com](https://monday.com/blog/rnd/what-is-tdd/)
+- [@article@Common Bugs in AI-Generated Code and Fixes - Ranger](https://www.ranger.net/post/common-bugs-ai-generated-code-fixes)
+- [@article@How AI Will Bring TDD Back from the Dead - Momentic](https://momentic.ai/blog/test-driven-development)
@@ -1,3 +1,8 @@
 # Work step by step rather than trying to build all at once

-Build one feature at a time. Ask the AI to do it, test it, make sure it works, then move to the next one. If you ask AI to build too many things at once, things will break, and you won't know why. Small steps make debugging easy because you only changed one thing, so you know exactly where the problem is.
+Build one feature at a time. Ask the AI to do it, test it, make sure it works, then move to the next one. If you ask AI to build too many things at once, things will break, and you won't know why. Small steps make debugging easy because you only changed one thing, so you know exactly where the problem is.
+# Articles
+
+- [@article@9 Vibe Coding Best Practices - Memberstack](https://www.memberstack.com/blog/9-vibe-coding-best-practices)
+- [@article@How to Vibe Code Effectively - Replit Docs](https://docs.replit.com/tutorials/how-to-vibe-code)
+- [@article@Vibe Coding Tips: Checklist to Avoid Breaking Builds - Presta](https://wearepresta.com/vibe-coding-tips-checklist-avoid-breaking-builds/)