#test-driven development AI
141 related articles
Tutorials·2 min
Claude Code Installation Guide: Configuration for China-Based Users & Superpowers Plugin in Practice
Complete guide to installing Claude Code in three commands, configuring models for China-based users via manual setup or CCSWITCH, and using the Superpowers plugin with TDD to boost AI code quality.
Read more →
Deep Dives·1 min
Factory Missions Architecture Deep Dive: How a Multi-Agent System Runs Continuously for 16 Days
Deep dive into Factory Missions multi-agent architecture: how validation contracts, serial execution, and structured handoffs enable an AI coding system to run 16 days without losing context.
Read more →
Expert Opinions·2 min
A Critical Look at AI Coding: Copilot Is Not a Developer's Replacement
An in-depth look at how to properly use AI coding tools like GitHub Copilot, exploring hybrid development, prompt evolution, and the risk of eroding developer learning abilities.
Read more →
Expert Opinions·2 min
The Faster AI Generates Code, the Faster Your Project Dies: Trust Engineering Is the Real Bottleneck
AI programming drives code generation cost to zero, but verifying correctness is the ultimate bottleneck. GitClear data shows 10x copy-paste surge. Developers must shift from writing to verifying code.
Read more →
Expert Opinions·3 min
Claude Code Creator Shares 3 Battle-Tested Tips: Treat AI Like a Team
Claude Code creator Boris Cherny shares 3 power tips: parallel multitasking, Loop execution, and self-verification feedback loops. Transform your AI from a passive tool into a 24/7 automated dev team.
Read more →
Product Reviews·2 min
Qoder 1.0 In-Depth Review: How Good Is This AI Autonomous Coding Platform Really?
In-depth review of Alibaba's Qoder 1.0: Quest task units, Multi-Agent expert teams, Knowledge Engine, and comparison with Codex, Claude Code, and other competitors.
Read more →
Deep Dives·2 min
Hermes Agent: Complete Breakdown of 87 Built-in Skills — 7-Layer Architecture & Priority Guide
Deep dive into Hermes Agent V0.13.0's 87 Built-in Skills reorganized into 7 functional layers with priority guidance. Find the 17 core Skills worth learning first.
Read more →
Tutorials·4 min
Harness Engineering in Practice: A Three-Layer Architecture for Taming AI Agent Development
A detailed guide to Harness Engineering's three-layer architecture for controlling AI Agent code generation quality, covering the Information, Constraint, and Automation layers with practical setup and pitfall avoidance tips.
Read more →
Tutorials·5 min
Can't Use Claude Code? Hands-On Guide to Accessing Opus 4 via Cursor and Windsurf
Can't use Claude Code in China? This hands-on guide tests Cursor and Windsurf as alternatives for accessing the Opus 4 model, both supporting Alipay payment with no overseas phone number required.
Read more →
Tech Frontiers·2 min
llm-echo 0.5a0: A Testing Powerhouse for Simulating Chain-of-Thought LLM Output
Simon Willison releases llm-echo 0.5a0 with a new thinking option to simulate LLM chain-of-thought output. Learn how this testing plugin streamlines AI development workflow automation.
Read more →
Product Reviews·4 min
Get Shit Done: Full Breakdown of the 60K-Star Claude Code Meta-Prompting & Spec-Driven Development System
Deep dive into Get Shit Done (GSD), a 62K-star GitHub project built for Claude Code. Covers meta-prompting, context engineering & spec-driven development.
Read more →
Tutorials·4 min
Gemini CLI Custom Commands Tutorial: Complete Workflow from Creation to Practice
Complete guide to Gemini CLI custom commands with a UI component generation example. Covers TOML configuration, parameter passing, TDD workflow integration, and best practices for reusable automation.
Read more →
Product Reviews·4 min
Claude Code In-Depth Review: Installation, Configuration & Comparison with Cursor and TRAE
In-depth analysis of Claude Code's core advantages including full-project context understanding, code generation accuracy comparison, and automated debugging, plus detailed installation guide and comparison with Cursor, TRAE, and Codex.
Read more →
Tutorials·4 min
Avoiding Pitfalls in Agent Skill Maintenance: A Practical Guide to Defending Against Perplexity's "Action at a Distance" and Building Evaluation Systems
Deep dive into Perplexity's "Action at a Distance" risk in Agent Skill maintenance, covering precise fixes for three failure types, the Gotcha flywheel, and a four-layer evaluation system.
Read more →
Tutorials·3 min
Superpowers in Practice: Making AI Coding Follow Software Engineering Standards
Learn how Superpowers solves five major AI coding problems through a standardized seven-step workflow. Practical Vue3 comparison shows dramatic code quality improvements.
Read more →
Tutorials·4 min
Vibe Coding Practical Guide: SDD (Specification-Driven Development) Reshaping Full-Stack Programming Workflows
In-depth analysis of SDD (Specification-Driven Development), the core methodology of Vibe Coding in 2025, covering the full workflow from requirements to deployment with tools like Claude Code.
Read more →
Tutorials·4 min
Vibe Coding Practical Guide: SDD Methodology Explained with 4 Enterprise-Level AI Programming Projects
Deep dive into SDD specification-driven development methodology with 4 enterprise-level Vibe Coding projects including Chat BI and multimodal knowledge bases, covering Cursor, Claude Code, and Prompt Engineering.
Read more →
Expert Opinions·4 min
Rejecting Vibe Coding: Matt Pocock's Engineering-Driven Approach to AI Programming
TypeScript expert Matt Pocock's open-source Skills repo earned 80K+ GitHub Stars, using TDD and Domain-Driven Design to solve AI programming's three biggest pain points.
Read more →
Product Reviews·2 min
Roo Code Arena Mode and Plan Mode Explained: New Ways to Use Your AI Coding Assistant
Roo Code launches Arena Mode for blind AI model comparison and Plan Mode for plan-first coding workflows, enhancing AI-assisted programming control and evaluation.
Read more →
Tech Frontiers·2 min
SWE-bench Opens Evaluation Environments and Training Recipes: Dramatically Lowering the Barrier to AI Coding Agent Development
SWE-bench opens evaluation environments, task sets, trajectories, and training recipes, dramatically lowering the barrier to AI coding agent development.
Read more →