chore: sync content to repo (#9628)

Co-authored-by: kamranahmedse <4921183+kamranahmedse@users.noreply.github.com>

src/data/roadmaps/vibe-coding/content/ask-ai-to-handle-your-git-and-github-cli-tasks@vDSSzh5TwZ8zzY0rWRXu4.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/ask-ai-to-keep-the-code-modular-and-aim-for-smaller-modulesfiles@FoQ15wo0cV2Tntru6jV-1.md

@@ -0,0 +1,7 @@
+# Ask AI to keep the code modular and aim for smaller modules/files
+
+From the start, tell AI to split the code into small, focused files rather than putting everything in one place. Smaller files are easier to read, easier to fix, and easier for AI to work with in future sessions without getting confused.
+
+Visit the following resources to learn more:
+
+- [@article@Vibe Coding Principles: Modularity & Coupling Principles](https://blog.synapticlabs.ai/what-is-modular-programming-loose-coupling)

src/data/roadmaps/vibe-coding/content/ask-ai-to-use-subagents-if-possible@n5JxUpashrHKai2XESdd-.md

@@ -0,0 +1,8 @@
+# Use subagents
+
+Subagents are specialized agents that handle specific tasks in their own isolated context. Using them keeps each part of the work focused, reduces token usage, and produces cleaner results than trying to do everything inside one long conversation.
+
+Visit the following resources to learn more:
+
+- [@article@Create custom subagents - Claude Code](https://code.claude.com/docs/en/sub-agents)
+- [@video@Claude Code NEW Sub Agents in 7 Minutes](https://www.youtube.com/watch?v=DNGxMX7ym44)

src/data/roadmaps/vibe-coding/content/ask-ai-to-write-tests-e2e-tests-can-help-build-a-stable-product@WLOx62vbIhIlv73jcT8zM.md

@@ -0,0 +1,3 @@
+# 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 actual experience before they reach real users.

src/data/roadmaps/vibe-coding/content/ask-for-one-task-at-a-time-rather-than-five-different-items@HpbG5bcOEIZxYlVl9pwod.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/based-on-your-previous-coding-sessions-tell-ai-what-not-to-do@3lHMW2Uje5tQawetE4I21.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/be-specific-about-what-you-want-rather-than-high-level-vague-instructions@JXtLbQ1JUQOPZorFy1ctF.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/claude-code@wr5ddjutC-fX_ixysTHaT.md

@@ -7,7 +7,5 @@ Visit the following resources to learn more:
 - [@roadmap@Visit the Dedicated Claude Code Roadmap](https://roadmap.sh/claude-code)
 - [@official@Claude Code Overview](https://code.claude.com/docs/en/overview)
 - [@article@Claude Code: From Zero to Hero](https://medium.com/@dan.avila7/claude-code-from-zero-to-hero-bebe2436ac32)
-- [@article@Claude Code: A Guide With Practical Examples](https://www.datacamp.com/tutorial/claude-code)
 - [@video@Introducing Claude Code](https://www.youtube.com/watch?v=AJpK3YTTKZ4)
-- [@video@laude Code Tutorial for Beginners](https://www.youtube.com/watch?v=eMZmDH3T2bY)
-- [@video@Claude Code Clearly Explained (and how to use it)](https://www.youtube.com/watch?v=zxMjOqM7DFs&t=82s)
+- [@video@Claude Code Tutorial for Beginners](https://www.youtube.com/watch?v=eMZmDH3T2bY)

src/data/roadmaps/vibe-coding/content/consider-test-driven-development-tdd@Gr9WJ0tNmSsVHSA0Cx3xY.md

@@ -0,0 +1,8 @@
+# Consider Test-driven development (TDD)
+
+With TDD, you write the test before the code. Ask AI to first write a test that describes the expected behavior, then write the code that makes it pass. This forces clarity about what you are building and results in cleaner, more reliable code.
+
+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)

src/data/roadmaps/vibe-coding/content/context@0ZJrFxKo5HyD9OgzG5LWp.md

@@ -0,0 +1,7 @@
+# Context
+
+Context is everything when working with AI. The AI only knows what you tell it; it has no memory of your project, your past decisions, or your preferences unless you provide that information in the current session. Keep sessions focused, start fresh for unrelated tasks, and use subagents when possible to keep context clean and costs low.
+
+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)

src/data/roadmaps/vibe-coding/content/cursor@MWhoqhNnBaoeCdN_8i15k.md

@@ -5,8 +5,6 @@ Cursor is an AI-powered code editor designed to enhance developer productivity.
 Visit the following resources to learn more:
 
 - [@official@Cursor](https://cursor.com/)
-- [@official@Cursor Learn](https://cursor.com/learn)
 - [@official@Cursor Docs](https://cursor.com/docs)
-- [@article@Cursor AI: A Guide With 10 Practical Examples](https://www.datacamp.com/tutorial/cursor-ai-code-editor)
 - [@video@Cursor AI Tutorial for Beginners](https://www.youtube.com/watch?v=3289vhOUdKA)
 - [@video@Cursor Tutorial for Beginners (AI Code Editor)](https://www.youtube.com/watch?v=ocMOZpuAMw4)

src/data/roadmaps/vibe-coding/content/debugging@mHChjJd39ofwPBS-v_sQY.md

@@ -0,0 +1,7 @@
+# Debugging
+
+AI is very good at fixing errors when you give it the right information. Paste the error message directly, let it diagnose the problem, and if it keeps failing after a few attempts, ask it to list all possible causes instead of guessing. Use logs to trace exactly where things go wrong, and when available, use MCP tools to give AI direct visibility into what is happening inside your app in real time.
+
+Visit the following resources to learn more:
+
+- [@video@Vibe Debugging](https://laracasts.com/series/vibe-coding-workshop/episodes/9)

src/data/roadmaps/vibe-coding/content/explicitly-ask-ai-to-perform-a-security-audit-of-the-application@8VL5XHFrQUjin1pdAi7WZ.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/explicitly-tell-ai-to-think-or-brainstorm-before-complex-problems@17nFgML7zVjQYiHIOSLlK.md

@@ -0,0 +1,7 @@
+# Explicitly tell AI to "think" or "brainstorm" 
+
+For tricky problems, don't ask AI to jump straight to a solution. Tell it to think through the options first and explain its reasoning before writing any code. This simple instruction often leads to much better results on complex tasks.
+
+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)

src/data/roadmaps/vibe-coding/content/for-unrelated-tasks-proactively-clean-and-start-new-sessions@phtVEKzIUv9E1abazort0.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/gemini@hzeEo8COf2l07iu5EdlFo.md

@@ -6,4 +6,4 @@ Visit the following resources to learn more:
 
 - [@official@Google Gemini](https://gemini.google.com/)
 - [@official@Google's Gemini Documentation](https://workspace.google.com/solutions/ai/)
-- [@video@elcome to the Gemini era](https://www.youtube.com/watch?v=_fuimO6ErKI)
+- [@video@Welcome to the Gemini era](https://www.youtube.com/watch?v=_fuimO6ErKI)

src/data/roadmaps/vibe-coding/content/give-ai-mockups-reference-files-and-material-that-can-help-it@6kVVt2lihBW8tPGV-ll3_.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/if-ai-fails-after-3-prompts-stop-and-start-a-fresh-chat@ikp1O_sss_6hDGl6p8LNJ.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/if-errors-persist-ask-al-to-create-a-list-of-possible-causes@cz--AlEn0cc2-keXeuk9g.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/if-you-have-stylecoding-preferences-document-them-for-ai@QBeh16mppfb2s4OGt4aPy.md

@@ -0,0 +1,4 @@
+# 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)  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.

src/data/roadmaps/vibe-coding/content/if-you-need-to-revert-use-git-rather-than-ai-native-revert-functionality@upZAMDEtzq1VklqTKG5mV.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/illustrate-ai-with-examples-mockups-code-samples-images@ODqMzOAN1je004chwATTl.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/install-and-ask-ai-to-use-mcp-eg-playwright-for-browser-when-possible@KVb_TAsSD8Kgafij4iEXc.md

@@ -0,0 +1,8 @@
+# Install and ask AI to use MCP
+
+MCP tools let AI interact directly with your app — for example, using Playwright to test it in a real browser. This gives AI actual visibility into what is happening rather than guessing from the code alone, which makes debugging much faster and more accurate.
+
+Visit the following resources to learn more:
+
+- [@article@What is the Model Context Protocol (MCP)?](https://modelcontextprotocol.io/docs/getting-started/intro)
+- [@opensource@Playwright MCP](https://github.com/microsoft/playwright-mcp)

src/data/roadmaps/vibe-coding/content/leverage-long-context-window-when-available-and-necessary@CMnz6UFUGbxIGSH06ZdgH.md

@@ -0,0 +1,7 @@
+# Leverage long context windows 
+
+Some AI tools allow you to paste in a lot of information at once. When working on something complex, prompt AI with all the relevant files, notes, and context at once. The more the AI understands about your project upfront, the better decisions it will make throughout the session.
+
+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)

src/data/roadmaps/vibe-coding/content/master-version-control@q5lkCO_uGmkcJopjltg8j.md

@@ -0,0 +1,8 @@
+# Master Version Control
+
+Version control is the system you use to track changes to your code over time. Version control tools like Git are especially important for vibe coders because AI can sometimes make sweeping changes that break things unexpectedly, and having a recent save point means you never lose too much progress.
+
+Visit the following resources to learn more:
+
+- [@roadmap@Visit the Dedicated Git and GitHub Roadmap](https://roadmap.sh/git-github)
+- [@video@Vibe Coding Course 7 – Version Control Basics (Git)](https://www.youtube.com/watch?v=qUE-nVUrpq4)

src/data/roadmaps/vibe-coding/content/never-hardcode-or-credentials-use-env-variables-instead@aRnpJbSUg_rr9Z00RafYt.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/once-tests-are-in-place-refactor-regularly@9BSermDg6ODL2MSRQiDZo.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/pick-a-popular-tech-stack-rather-than-newniche-ones@7mAZMKyiuZiEpKhrydp8J.md

@@ -0,0 +1,7 @@
+# Pick a popular tech stack rather than new/niche ones
+
+Use popular tech stacks like React, Next.js, Tailwind, and Supabase. AI has been trained on a lot of code using these tools, so it gives better results. If you use something niche or very new, AI will make more mistakes, and you will spend more time fixing things. Popular stacks also have more tutorials and community support, which helps when you get stuck.
+
+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/)

src/data/roadmaps/vibe-coding/content/plan-before-you-code@pfgsxuQ-D7dTMPNWKG9OY.md

@@ -0,0 +1,8 @@
+# Plan before you Code
+
+Before you start coding with AI, have a plan. Define your MVP and break the project into phases. Don't try to build everything at once; work step by step. Give AI examples like mockups, screenshots, or code samples so it understands what you want. You can even use AI itself to help you plan. Tell it your idea, let it help you refine it, and break it into phases. Little planning at the start saves many hours of fixing later.
+
+Visit the following resources to learn more:
+
+- [@video@Vibe Planning: The Smarter Way to Code with AI Agents](https://www.youtube.com/watch?v=B4uD9z6i_IU)
+- [@article@From vibe coding to vibe planning](https://tessl.io/blog/from-vibe-coding-to-vibe-planning/)

src/data/roadmaps/vibe-coding/content/plan-what-you-need-to-develop-mvp-different-phases@OPHuAD0L-GZ6zRhIhbmPL.md

@@ -0,0 +1,3 @@
+# Plan what you need to develop
+
+Don't try to build everything at once. Start with your MVP, the simplest version that works. If you are building a task manager, that might just be adding, viewing, and deleting tasks. Nothing else. Then break the rest into phases. Maybe phase two is user accounts, phase three is notifications. This way you always have something working, and the AI gives better results when you give it smaller, focused tasks instead of asking it to build a whole app in one go.

src/data/roadmaps/vibe-coding/content/prompt-the-error-message-and-let-ai-do-the-rest@GW5I1z7D1945AxqYHbW6F.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/prompting-best-practices@6GvIXEzWbSD8q6Qt-BsHP.md

@@ -0,0 +1,9 @@
+# Prompting Best Practices
+
+How you talk to AI determines the quality of what you get back. Ask for one thing at a time, be specific, show examples, tell it what to avoid, and use a context document so you don't repeat yourself every session.
+
+Visit the following resources to learn more:
+
+- [@roadmap@Visit the Dedicated Prompt Engineering Roadmap](https://roadmap.sh/prompt-engineering)
+- [@article@Prompt Engineering Best Practices: Tips, Tricks, and Tools](https://www.digitalocean.com/resources/articles/prompt-engineering-best-practices)
+- [@video@RAG vs Fine-Tuning vs Prompt Engineering: Optimizing AI Models](https://www.youtube.com/watch?v=zYGDpG-pTho)

src/data/roadmaps/vibe-coding/content/regularly-ask-the-ai-to-review-and-refactor-the-codebase@NtQDPno95SYo5E88ls4v1.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/regularly-update-your-context-document-eg-claudemd@WypEm84Rr0t-IzCZiU92q.md

@@ -0,0 +1,8 @@
+# Regularly update your context document
+
+Every time you make an important decision about your project, add it to your context document, like your CLAUDE.md. This keeps sessions shorter, reduces repeated explanations, and saves tokens, which saves money, especially when working with agents that consume tokens fast.
+
+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)

src/data/roadmaps/vibe-coding/content/security-best-practices@2omItZjkVFW9kMiNXdt-h.md

@@ -0,0 +1,8 @@
+# Security Best Practices
+
+Security is easy to overlook when you are focused on building, but the consequences of ignoring it can be serious. Always use environment variables for sensitive information like API keys and passwords, and before going live, explicitly ask AI to audit your app for vulnerabilities.
+
+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)

src/data/roadmaps/vibe-coding/content/start-each-new-feature-with-a-clean-git-slate@ScizaxaDFQ_OBiFZ540Xs.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/tech-stack-and-coding@GC4vVcOcFWE1RByD-sd4G.md

@@ -0,0 +1,5 @@
+# Tech Stack and Coding
+
+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.

src/data/roadmaps/vibe-coding/content/tell-ai-to-add-logs-to-find-the-error-faster@vnm51qAe2C1cszHfh-o6P.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/testing@4bJRhuZzVc32x2Y0gGGrh.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/the-vibe-coder-mindset@LkLQ8GjBXDuw1XsrE4Cjj.md

@@ -0,0 +1,10 @@
+# The Vibe Coder Mindset
+
+AI is more like junior developer working next to you. You don't ask one question and leave. You have conversation with it. You give context, check what it gives back, tell it when something is wrong, and guide it to what you need. If you explain your idea clearly, it works better.
+
+This is very different from traditional programming where you must know exact syntax and write everything yourself. With AI, your role changes; you become the person who directs, not the person who types code. You set the vision, review output, and keep project going in right direction. You still need to understand basics of programming, but you don't need to memorize syntax or figure out every small detail on your own anymore.
+
+Visit the following resources to learn more:
+
+- [@article@The Unbearable Lightness of Coding](https://towardsdatascience.com/the-unbearable-lightness-of-coding/?utm_source=roadmap&utm_medium=Referral&utm_campaign=TDS+roadmap+integration)
+- [@video@What is Vibe Coding?](https://www.youtube.com/watch?v=5OWurmg41tI)

src/data/roadmaps/vibe-coding/content/use-act-as-framing-when-helpful-eg-act-as-a-ux-researcher@h2oehkZSKfMqlVBAgt46P.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/use-git-commit-regularly-eg-after-every-successful-ai-task@wWs2PxN7T2-gDZNJJ1vTq.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/use-skills-created-by-others@bnpY9GX1BGjDPJXwTFWTX.md

@@ -0,0 +1,9 @@
+# Use skills created by others
+
+There is a growing ecosystem of skills — pre-built AI capabilities developed as an open standard — that you can plug into your AI tool to extend what it can do. Before building something from scratch, check if a skill already exists for it. It saves time and often gives better results than starting from zero.
+
+Visit the following resources to learn more:
+
+- [@official@Agent Skills](https://agentskills.io/home)
+- [@article@Agent Skills - Claude](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview)
+- [@course@Agent Skills with Anthropic](https://www.deeplearning.ai/short-courses/agent-skills-with-anthropic/)

src/data/roadmaps/vibe-coding/content/what-is-vibe-coding@lzHnwx_3gftRZbstk6INB.md

@@ -1,11 +1,8 @@
 # Vibe Coding
 
-Vibe coding is a modern software development approach in which developers use AI agents and large language models (LLMs) to generate, build, and iterate on applications via natural language prompts, rather than writing code manually. Coined by Andrej Karpathy, this method focuses on the "vibe" or overall intent of the application, often involving rapid prototyping and minimal manual code review, making software development more accessible and faster.
+Vibe coding" is software development method where you use AI and LLMs to generate code through natural language prompts instead of writing it by hand. Term was coined by Andrej Karpathy. The idea is you describe what you want the application to do, and AI builds it. Good for fast prototyping. You don't need to review every line of code. Makes development faster and more accessible for people who are not traditional programmers.
 
 Visit the following resources to learn more:
 
-- [@article@hat is vibe coding? - Google](https://cloud.google.com/discover/what-is-vibe-coding)
-- [@article@What is vibe coding? - IBM](https://www.ibm.com/think/topics/vibe-coding)
-- [@article@Human Won’t Replace Python](https://towardsdatascience.com/human-wont-replace-python/?utm_source=roadmap&utm_medium=Referral&utm_campaign=TDS+roadmap+integration)
 - [@video@hat Is Vibe Coding? Building Software with Agentic AI](https://www.youtube.com/watch?v=Y68FF_nUSWE)
 - [@video@What is Vibe Coding?](https://www.youtube.com/watch?v=5OWurmg41tI)

src/data/roadmaps/vibe-coding/content/when-you-find-a-bug-ask-ai-to-write-a-breaking-test-and-then-fix@r-LrA1cGR1XMu1p2xIsN0.md

@@ -0,0 +1,3 @@
+# 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.

src/data/roadmaps/vibe-coding/content/windsurf@Xsl8mx6J182TxPPtNP471.md

@@ -6,6 +6,5 @@ Visit the following resources to learn more:
 
 - [@official@Windsurf](https://windsurf.com/)
 - [@official@Windsurf Docs](https://docs.windsurf.com/windsurf/getting-started)
-- [@article@Windsurf AI Agentic Code Editor: Features, Setup, and Use Cases | DataCamp](https://www.datacamp.com/tutorial/windsurf-ai-agentic-code-editor)
 - [@video@Windsurf Tutorial for Beginners (AI Code Editor) - Better than Cursor??](https://www.youtube.com/watch?v=8TcWGk1DJVs)
 - [@video@Windsurf AI Tutorial for Beginners](https://www.youtube.com/watch?v=x1VCmB__TDo)

src/data/roadmaps/vibe-coding/content/work-step-by-step-rather-than-trying-to-build-everything-at-once@CJV5OV_Whoz4_7L8yhDG1.md

@@ -0,0 +1,3 @@
+# 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.