Xiaolong Cloud Tech Team
The author demonstrates how to convert an OCR API specification into a reusable Skill using Claude’s Skill Creator, explains the advantages of Skill’s hierarchical exposure over traditional MCP prompts, outlines a three‑step workflow, and argues that such capabilities may spawn a new ‘Skill Engineer’ position in AI teams.
This article documents a hands‑on experiment that uses AI tools to design, prototype, and develop a full‑stack inventory‑management web application—from initial UI sketches to a working front‑end, back‑end, database, and AI chat assistant—while analyzing tool choices, challenges, and the limits of current large‑model programming capabilities.
The article analyzes how loading thousands of tool definitions overwhelms an agent's context window, and demonstrates that letting the agent generate code to call MCP tools reduces token consumption from 150,000 to 2,000 (a 98.7% improvement) while also improving privacy, state persistence, and control‑flow flexibility.
The article examines the practical difficulties of constructing AI agents, covering SDK selection pitfalls, explicit caching strategies, heavy reliance on reinforcement, failure isolation techniques, virtual file‑system coordination, output‑tool quirks, model trade‑offs, and the ongoing struggle to devise reliable testing and evaluation methods.
The article shows how Gemini (even the older Gemini 2.5) can cut a product manager's documentation workload by over 90% through FeatureList drafting, Mermaid diagram generation, and HTML‑based PRD creation, while arguing that failing to embed large‑model tools will make product managers redundant.
The article surveys five open‑source AI agents—MobiAgent, Mobile‑Agent, Droidrun, AppAgent, and mobile‑use—that let AI perceive screen content and perform cross‑app actions on Android/iOS devices, describing their architectures, example use cases, benchmark results, and GitHub links.
This article explains why buying pre‑made API keys is risky, then walks through checking key status, faking a US billing address, obtaining a virtual credit card, adding payment, upgrading to the paid tier, testing Gemini 3 Pro and Nano Banana Pro, and avoiding common pitfalls.
The article recounts Liang Wenfeng’s journey from coding quant strategies in a Chengdu apartment to founding DeepSeek, explaining how AI‑assisted high‑frequency trading leverages compounding, near‑perfect success rates, and thousands of tiny profit‑making trades to generate exponential wealth.
This step‑by‑step guide shows how to install Cursor and Playwright‑MCP, configure the MCP server (including Windows path fixes), generate a test plan from CSV files, run automated tests with Playwright, and produce a detailed test report with screenshots and issue analysis.
Google’s newly released Gemini 3 Pro shows more than a 20% improvement in coding ability over Gemini 2.5 Pro, achieves state‑of‑the‑art results across multiple benchmarks, and can generate complete React apps, visual designs, physics simulations, and simple games, though its new antigravity IDE currently suffers login issues.
