Author

大转转FE

Regularly sharing the team's thoughts and insights on frontend development

Articles

Likes

292

Views

Comments

Latest from 大转转FE

61 recent articles

大转转FE

Jun 25, 2026 · Backend Development

Refactoring a 1,000‑Line Untested Core File with AI: My Proven Workflow

The author refactors a 1,021‑line, zero‑test IM conversion module that is referenced in five places by building a characterization‑test net with esbuild stubs, generating 130 exhaustive samples, recording a golden baseline, applying three systematic code transformations, and verifying behavior and a 2.77× speedup, all without touching business logic.

AICharacterization TestJavaScript

0 likes · 16 min read

Refactoring a 1,000‑Line Untested Core File with AI: My Proven Workflow

大转转FE

Jun 15, 2026 · Artificial Intelligence

Programmers’ Skill Shift in the AI Era – Highlights from Frontend Weekly #199

This issue of Zhuanzhuan Frontend Weekly curates five industry articles that examine AI‑driven skill transformation for developers, the rise of Frontline Deployment Engineers, the three‑layer Agentic Engineering model, the distinction between Loop and Harness engineering, and cloud‑native AI‑Native multi‑agent architectures.

AIAI-nativeAgentic Engineering

0 likes · 4 min read

Programmers’ Skill Shift in the AI Era – Highlights from Frontend Weekly #199

大转转FE

Jun 11, 2026 · Artificial Intelligence

From PRD to Verified Code: Building a Closed‑Loop AI Development Process

The article outlines a structured AI‑coding framework for React Native projects that turns product requirements, API specs, and Figma designs into a traceable development pipeline using prompts, sub‑agents, rule‑based gates, code generation, compile verification, visual audit, and experience deposition to ensure verifiable, high‑quality output.

AI codingcode generationprompt engineering

0 likes · 14 min read

From PRD to Verified Code: Building a Closed‑Loop AI Development Process

大转转FE

Jun 4, 2026 · Mobile Development

Starship: iOS Test Device Proxy Management in Practice

The article details the design and implementation of “Starship,” an internal iOS tool that automates proxy configuration for shared test devices, eliminating manual Wi‑Fi settings, providing real‑time status, domain‑based routing, and health checks, while comparing existing solutions and sharing practical lessons.

NetworkExtensionQR CodeSwift

0 likes · 19 min read

Starship: iOS Test Device Proxy Management in Practice

大转转FE

Jun 4, 2026 · Artificial Intelligence

Captcha Recognition in Practice: Front‑End Engineers Skip UI to Train Models

This article details how front‑end developers used a low‑code DDDD trainer and AI‑generated PyTorch CNN code to build high‑accuracy captcha recognizers, achieving up to 99% sequence accuracy while illustrating a workflow that lets developers shift from UI coding to model training with AI assistance.

AICNNFrontend

0 likes · 15 min read

Captcha Recognition in Practice: Front‑End Engineers Skip UI to Train Models

大转转FE

May 28, 2026 · Artificial Intelligence

How MCP Gives AI a Universal USB‑C Port to Bridge the Last Mile of Test Automation

The article explains how the Model Context Protocol (MCP) lets AI tools like Cursor read PRDs, generate validated Midscene YAML test cases, and upload them to the HAL‑9000 platform through a unified three‑primitive architecture, choosing stdio or HTTP transport, while ensuring security and scalability.

AI integrationCursorHAL-9000

0 likes · 17 min read

How MCP Gives AI a Universal USB‑C Port to Bridge the Last Mile of Test Automation

大转转FE

May 21, 2026 · Artificial Intelligence

Why AI Buzzwords Multiply Faster Than My Hair Falls

The article maps three generations of AI engineering—Prompt Engineering, Context Engineering, and Harness Engineering—explaining their core capabilities, key terms like LLM, RAG, Agent, and evaluation methods, while offering practical tips, pitfalls, and a concise three‑question checklist to stay grounded amid the rapid influx of new AI jargon.

AIAgentHarness

0 likes · 19 min read

Why AI Buzzwords Multiply Faster Than My Hair Falls

大转转FE

May 14, 2026 · Artificial Intelligence

Zero‑Code Multi‑Platform Regression Testing Powered by Xmind and AI Visual Recognition

The article explains how a B2B team transformed its three‑platform regression workflow—from manual, repetitive clicks to a reusable, AI‑driven testing asset—by converting Xmind mind‑maps into Midscene YAML scripts, eliminating selector maintenance and enabling zero‑code test case creation across PC, app and mini‑program environments.

AI visual testingMidsceneMulti‑platform regression

0 likes · 18 min read

Zero‑Code Multi‑Platform Regression Testing Powered by Xmind and AI Visual Recognition

大转转FE

May 7, 2026 · Artificial Intelligence

Running AI Inference Directly in the Browser with WebNN

WebNN brings hardware‑accelerated AI inference to web pages, letting developers run millisecond‑level face detection, real‑time filters, and semantic segmentation locally without cloud calls, while improving latency, privacy, and cost through a unified JavaScript API that maps to CPUs, GPUs or NPUs.

AI inferenceBrowserEdge

0 likes · 16 min read

Running AI Inference Directly in the Browser with WebNN

大转转FE

Apr 22, 2026 · Artificial Intelligence

Cut Claude Code Token Costs: 4 Strategies, Real Benchmarks, and Hidden Pitfalls

This guide dissects why Claude Code sessions can waste from 3 k to 30 k tokens, explains the four key cost drivers, and provides concrete techniques—such as prompt caching, precise prompts, single‑turn queries, and infrastructure tweaks—backed by detailed token measurements and real‑world examples.

AIProgrammingClaudeCostManagement

0 likes · 23 min read

Cut Claude Code Token Costs: 4 Strategies, Real Benchmarks, and Hidden Pitfalls