mirror of
https://github.com/kamranahmedse/developer-roadmap.git
synced 2026-03-12 17:51:53 +08:00
chore: sync content to repo (#9635)
Co-authored-by: kamranahmedse <4921183+kamranahmedse@users.noreply.github.com>
This commit is contained in:
github-actions[bot]
committed by
GitHub
GitHub
parent
de1ba25adc
commit
4ae63e69fa
@@ -1,3 +1,3 @@
|
||||
# Ask AI to write tests
|
||||
# Ask AI to write tests
|
||||
|
||||
Every time the AI builds a new feature, ask it to write tests for that feature before moving on. One particularly valuable type of test is an end-to-end test, often called an E2E test, which simulates a real user going through your app — clicking buttons, filling in forms, navigating between pages — and checks that everything works as expected from start to finish. Having E2E tests in place means you can make changes to your code with confidence, knowing that if something breaks the user experience, a test will catch it immediately.
|
||||
@@ -9,5 +9,5 @@ Visit the following resources to learn more:
|
||||
- [@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 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)
|
||||
@@ -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)
|
||||
@@ -1,3 +1,3 @@
|
||||
# If you have style/coding preferences, document them for AI
|
||||
|
||||
Every developer has preferences — maybe you like a specific way of naming variables, a certain folder structure, or a particular way of handling errors. The problem is that AI doesn't remember these preferences between sessions unless you tell it. That's why it's important to write them down in dedicated instruction files, like a CLAUDE.md, and share it with the AI at the start of each session. Over time, this document becomes your personal coding rulebook, and it saves you from having to correct the same things over and over again every time you start a new chat.
|
||||
Every developer has preferences — maybe you like a specific way of naming variables, a certain folder structure, or a particular way of handling errors. The problem is that AI doesn't remember these preferences between sessions unless you tell it. That's why it's important to write them down in dedicated instruction files, like a [CLAUDE.md](http://CLAUDE.md), and share it with the AI at the start of each session. Over time, this document becomes your personal coding rulebook, and it saves you from having to correct the same things over and over again every time you start a new chat.
|
||||
@@ -1,3 +1,5 @@
|
||||
# undefined
|
||||
|
||||
Once tests are in place, refactor regularly
|
||||
|
||||
One of the biggest benefits of having a good test suite is that it gives you the freedom to refactor your code without fear. Refactoring means cleaning up and reorganizing the code without changing what it does — breaking large files into smaller ones, removing duplicate logic, improving performance. Without tests, refactoring is risky because you can't easily tell if you've accidentally broken something. With tests, you can make sweeping improvements and immediately know if anything has gone wrong because the tests will fail. Once your tests are in place, make refactoring a regular part of your workflow and let the AI do the heavy lifting while your tests keep everything in check.
|
||||
@@ -1,3 +1,5 @@
|
||||
# undefined
|
||||
|
||||
#Plan what you need to develop (MVP, Different Phases)
|
||||
|
||||
Start by planning your MVP — your Minimum Viable Product. This is the simplest version of your idea that still works and solves the core problem. For example, if you're building a task manager app, your MVP might just be the ability to add, view, and delete tasks — nothing more. Don't try to build everything at once. Break your project into phases, where phase one is the basic working version and later phases add more features like user accounts, notifications, or analytics. This keeps things manageable for you and AI, gives you something working early on, and makes it much easier to track progress without feeling overwhelmed.
|
||||
|
||||
@@ -5,5 +5,5 @@ Prompting is the skill at the heart of vibe coding. It's how you communicate wit
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@roadmap@Visit the Dedicated Prompt Engineering Roadmap](https://roadmap.sh/prompt-engineering)
|
||||
- [@video@RAG vs Fine-Tuning vs Prompt Engineering: Optimizing AI Models](https://www.youtube.com/watch?v=zYGDpG-pTho)
|
||||
- [@article@Vibe Coding Like A Pro](https://leonnicholls.medium.com/vibe-coding-like-a-pro-de18aa1a0cce)
|
||||
- [@article@Vibe Coding Like A Pro](https://leonnicholls.medium.com/vibe-coding-like-a-pro-de18aa1a0cce)
|
||||
- [@video@RAG vs Fine-Tuning vs Prompt Engineering: Optimizing AI Models](https://www.youtube.com/watch?v=zYGDpG-pTho)
|
||||
@@ -4,5 +4,5 @@ Your context document is a file where you store everything the AI needs to know
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@article@# Writing a good CLAUDE.md](https://www.humanlayer.dev/blog/writing-a-good-claude-md)
|
||||
- [@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)
|
||||
@@ -1,3 +1,5 @@
|
||||
# undefined
|
||||
|
||||
The vibe coder mindset
|
||||
|
||||
AI is a collaborator, not just a tool. Think of it less like a search engine and more like a junior developer sitting next to you. You don't just ask it one question and walk away — you have a back-and-forth conversation with it. You give it context, review what it produces, push back when something looks wrong, and guide it toward what you actually want. The more clearly you explain your idea, the better it performs. This is a big shift from traditional programming, where you had to know exactly what to type and in what order. With AI, your job changes from writing the code to directing it — you become the decision maker who sets the vision, checks the output, and keeps things on track. You still need to understand the basics, but you no longer need to memorize syntax or spend hours figuring out how to implement every small detail from scratch.
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
# Use "act as" framing when helpful
|
||||
# Use "act as" framing when helpful
|
||||
|
||||
Sometimes you don't just want code — you want a specific kind of thinking. Telling the AI to "act as a UX researcher," or "act as a senior backend developer," or "act as a product manager" shifts the way it approaches your question. It starts thinking from that perspective and gives you more relevant, role-specific advice. This is especially useful when you're making decisions rather than building things — like when you want feedback on your app's user flow, or you want someone to poke holes in your idea before you start building.
|
||||
@@ -1,3 +1,3 @@
|
||||
# Use `git commit` regularly
|
||||
# Use git commit regularly
|
||||
|
||||
Make it a habit to run a Git commit every time the AI completes a task successfully and the result looks good. If the next task goes badly wrong, you lose nothing more than that one task, rather than hours of work. Over time, your commit history also becomes a useful record of how your project evolved, which can help when you need to understand why a certain decision was made or when something first started breaking.
|
||||
@@ -4,6 +4,6 @@ One of the most powerful features of modern AI tools is the ability to extend wh
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@course@Agent Skills with Anthropic](https://www.deeplearning.ai/short-courses/agent-skills-with-anthropic/)
|
||||
- [@article@Agent Skills - Claude](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview)
|
||||
- [@article@Agents Skills](https://agentskills.io/home)
|
||||
- [@course@Agent Skills with Anthropic](https://www.deeplearning.ai/short-courses/agent-skills-with-anthropic/)
|
||||
- [@article@Agents Skills](https://agentskills.io/home)
|
||||
@@ -4,8 +4,8 @@ Vibe coding is a modern software development approach in which developers use AI
|
||||
|
||||
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? - 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? 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)
|
||||
Reference in New Issue
Block a user