pytest and unittest are both powerful and popular testing frameworks for Python, but they have different philosophies and approaches. Choosing between them often comes down to personal preference, project needs, and a trade-off between simplicity and built-in availability. unittest is Python's built-in testing framework, inspired by Java's JUnit. It's part of the standard library, meaning … Continue reading Pytest and Unittest

With the rise of powerful AI tools, it's time to rethink how we work—moving away from traditional methods and embracing AI-augmented workflows. One of the biggest challenges I face is navigating complex, domain-specific codebases within large organizations—including my own. These often contain undocumented quirks, legacy bugs, and hidden logic that can be difficult to uncover, … Continue reading Efficient Way to Peruse a Codebase and Apply to My Workflow

Directory Navigation Problems (My Main Concern): Claude Code frequently has trouble maintaining the correct working directory, often resetting to previous project directories or failing to change directories properly [BUG] wrong working directory · Issue #5038 · anthropics/claude-code +2. This is one of the most reported issues: Wrong Working Directory: Users report Claude Code starting in … Continue reading Pitfalls in Using Claude Code

JavaScript was born for browser, it's the the only language that browsers natively understand for client-side scripting. // JavaScript was literally created for web browsers in 1995 <script> document.getElementById("myButton").onclick = function() { alert("Hello World!"); }; </script> In 2009, it was expanded to run on servers by node.js runtime, which was built on Chrome’s V8 engine. … Continue reading Why JavaScript Dominates Both Frontend and Backend (But Python Can’t Do Frontend)

Prompt generator: prompt template contain fixed and variable content, leverage prompt generator and template, for example Be clear and direct Use examples (multishot) Let Claude think (chain of thought) Use XML tags These can be realized by prompt improver, Notice how the improved prompt: Guides Claude through the analysis process Adds clear step-by-step reasoning instructions … Continue reading How to prompt engineer

 Model Context Protocol (MCP), an open-source standard for AI-tool integrations. MCP servers give Claude Code access to your tools, databases, and APIs. More and more companies are strategically developing arrays of MCP servers to provide their services to millions of users. This dynamic business model is gaining momentum, and soon, I will launch and offer … Continue reading Sharpening Skills to Use Claude Code 06: MCP

Plan to outline output style, claude code hooks, github action and configuration including memory management. https://docs.anthropic.com/en/docs/claude-code/cli-reference About hooks, Hooks in Claude Code are configurable shell commands that execute in response to events like tool calls. Here's how to use them: Available Hook Types Stop/SubagentStop: Runs when responses finish Configuration PreToolUse: Runs before a tool executes … Continue reading Sharpening Skills to Use Claude Code 05

Build custom AI agents with the Claude Code SDK, it provides automatic prompt caching and performance optimizations, rich tool ecosystems, advanced permissions and production essentials such as error handling, session management and monitoring. Key Advantage: You get Claude Code's battle-tested tool ecosystem (file ops, bash, web search, etc.) plus the ability to add your own … Continue reading Sharpening Skills to Use Claude Code 04: Leverage SDK

The common workflow provided by Claude Code itself: understanding new codebasesfix bugsrefactor codeuse sepecialized subagentswork with testscreate pull requsetshandle documentationwork with imagesreference files and dirctoriesuse extended thinkingresume conversationrun parallel sessions with git worktreesuse claude as a unix-style utilitycreate custom slash commandsask claude code itself It recommend to clone development container implementation from github repo. ✅ … Continue reading Sharpening Skills to Use Claude Code 03: Workflow

Custom subagents in Claude Code are specialized AI assistants that can be invoked to handle specific types of tasks. They enable more efficient problem-solving by providing task-specific configurations with customized system prompts, tools and a separate context window. When Claude Code encounters a task that matches a subagent’s expertise, it can delegate that task to … Continue reading Sharpening Skills to Use Claude Code 02: Subagents