Sharing common backend development knowledge.
This tutorial explains how to extend Claude's static knowledge by using tool calls, covering the full workflow from initial requests to final responses, building Python tool functions, defining JSON Schemas, handling multi‑block messages, managing multi‑tool interactions, fine‑grained streaming, and using built‑in text‑editor and web‑search tools.
This article walks through an iterative prompt‑engineering workflow—starting with a weak baseline, applying four concrete techniques (clarity & directness, specificity, XML structuring, and examples), evaluating each change with a PromptEvaluator, and showing how scores jump from 3.4 to over 9.5 using real code snippets and concrete data.
This guide walks you through constructing a full prompt‑evaluation workflow—from drafting prompts and generating a test dataset to running Claude, scoring responses with model‑ and code‑based metrics, and iterating until your prompts are data‑driven and trustworthy.
This guide walks you through Claude Code model choices, secure API key handling, Python SDK setup, request construction, multi‑turn conversation management, system prompts, temperature tuning, response streaming, and extracting clean structured data such as JSON, all with practical code examples and diagrams.
This article presents an eight‑question quiz covering Claude Code’s tool system limitations, GitHub integration permissions, planning vs. thinking modes, Claude.md file types, custom command creation, hook behavior, and hook purposes, followed by the correct answer key for self‑assessment.
This guide walks you through using Obsidian, PicGo, and Tencent Cloud COS to automatically upload local Markdown images, replace URLs, and publish notes to platforms like Feishu and WeChat without manually handling each image, saving time and avoiding clutter.
This guide explains how to use Claude Code hooks—PreToolUse and PostToolUse—to run custom commands before or after tool execution, configure them in global or project settings, and implement practical examples such as blocking .env file access, type‑checking TypeScript, and preventing duplicate queries.
This guide walks you through installing the open‑source Feishu CLI, configuring it with Claude Code, and using the resulting SKILL to let an AI agent interact with Feishu messaging, cloud docs, calendars, and other services for automated workflows.
This guide explains how to create a retrieval‑augmented generation (RAG) system that avoids embeddings by converting documents into a hierarchical tree, using an LLM to navigate, summarize, and retrieve answers, complete with a full Python implementation and a GitHub repository.
This guide translates Google Cloud Tech's Agent Skills design patterns, detailing five reusable architecture patterns—Tool Wrapper, Generator, Reviewer, Inversion, and Pipeline—that help developers create modular, maintainable, and composable AI agents using the Agent Development Kit (ADK).
