Personal sharing
This guide explains what Claude Code Skills are, categorizes nine common skill types with concrete examples, and shares nine practical tips for designing, testing, distributing, and iterating on Skills to maximize their usefulness for AI agents and development teams.
The article examines Chrome 146’s WebMCP standard, showing how declarative and imperative APIs let large language models interact with real browser sessions directly, outperforming prior screenshot‑or‑Playwright tricks in success rate, token cost, speed, and robustness while exposing new challenges for anti‑bot systems.
This guide walks you through downloading the correct WorkBuddy installer, avoiding the CodeBuddy trap, completing a default installation with all optional tasks selected, logging into your WeChat account, configuring the WeChat Customer Service integration, and starting real‑time chats, while noting current model‑switching limitations.
The article examines why Web3 remains cold and unattractive to ordinary users, critiques its limited use cases and trust issues, and proposes that its true potential may lie in serving AI agents as a foundation for a forthcoming Web4 ecosystem where machines become autonomous economic participants.
The article traces the eight‑year controversy surrounding Go's proposal for short function literals, explaining the technical friction, community arguments, proposed syntax variants, and why the decision remains pivotal for Go's future language design.
Your device’s time comes from a worldwide hierarchy of atomic clocks and GPS satellites managed by the US Naval Observatory, but the NTP protocol lacks authentication, exposing SSL certificates, financial transactions, Kerberos authentication, and distributed databases to serious clock‑drift attacks.
This article explains why AI agents lose recall after prolonged use, analyzes three core flaws in current markdown‑based memory designs, reviews recent research, and presents a deterministic, zero‑cost three‑layer architecture—including short‑term, daily, and long‑term storage, a lightweight knowledge graph, and active forgetting mechanisms—to maintain reliable agent memory.
This article summarizes Go Podcast Episode 72, comparing container runtimes, web servers, database CLIs, AI‑assisted coding, and deployment strategies, while highlighting how tool choices reflect engineers' workflows, performance needs, and discipline in modern Go development.
An analysis of 2,430 Claude Code responses reveals the AI assistant overwhelmingly favors a handful of tools—Vercel, Stripe, shadcn/ui, GitHub Actions—while ignoring widely used alternatives, exposing how AI-driven recommendations can act as covert advertising that reshapes developer ecosystems.
A Go‑based online game using SSH generated hundreds of packets per keystroke due to OpenSSH's keystroke‑timing obfuscation, and the author traced, diagnosed, and solved the issue by disabling the extension on the server side, cutting CPU and bandwidth usage in half.
