Author

Linyb Geek Road

Tech notes

155

Articles

Likes

423

Views

Comments

Latest from Linyb Geek Road

100 recent articles max

Linyb Geek Road

Jul 23, 2026 · Artificial Intelligence

Achieving 94% AI Code Generation: How a Single Skill Automates the Entire Development Pipeline

This article details how a structured "Skill" pipeline transforms AI‑assisted coding from a flaky helper into a reliable end‑to‑end development engine, achieving a 94% code‑generation rate by breaking the workflow into eight verifiable stages, building a three‑level knowledge base, and enforcing strict red‑line rules.

AI code generationKnowledge Basepipeline engineering

0 likes · 34 min read

Achieving 94% AI Code Generation: How a Single Skill Automates the Entire Development Pipeline

Linyb Geek Road

Jul 23, 2026 · R&D Management

How Specification‑Driven Development Tames AI‑Generated Code with Three Loops and Six Human Checks

The article explains a specification‑driven development workflow that anchors AI‑generated code to a living requirements document through six closed‑loop stages—requirement authoring, clarification, code generation, cross‑compilation, download verification, and issue fixing—highlighting three iterative cycles and six human decision points that keep the process traceable and safe for industrial control projects.

AI code generationSpecification-Driven Developmenthuman-in-the-loop

0 likes · 6 min read

How Specification‑Driven Development Tames AI‑Generated Code with Three Loops and Six Human Checks

Linyb Geek Road

Jul 22, 2026 · Artificial Intelligence

How to Structure Specs for Complex Multi‑Agent Tasks

The article explains how to design a structured spec for complex, multi‑agent workflows by separating an orchestrator from dedicated executors, defining thin entry contracts, organizing rules, docs, and skills into distinct directories, and layering skills into orchestrator, phase, and atom levels to ensure traceability and maintainability.

AI workflowSkill Designdocs

0 likes · 18 min read

How to Structure Specs for Complex Multi‑Agent Tasks

Linyb Geek Road

Jul 22, 2026 · R&D Management

From Spec to Production: A 24‑Week Harness Engineering Playbook

The article explains how to turn a well‑written spec into reliable AI‑driven code by introducing Harness Engineering’s five‑layer architecture, five precise human‑intervention moments, three‑tier third‑party documentation, and a detailed 24‑week rollout plan that boosts success rates and reduces release failures.

AI automationCI/CDHarness Engineering

0 likes · 12 min read

From Spec to Production: A 24‑Week Harness Engineering Playbook

Linyb Geek Road

Jul 21, 2026 · Artificial Intelligence

13 Proven Claude Code Practices to Turn AI into a Team Productivity Engine

Boris Cherny outlines 13 concrete engineering practices—spanning standardization, automated verification, workflow acceleration, and feedback loops—that transform Claude Code from a clever code generator into a reliable, cost‑effective productivity tool for software teams, complete with real‑world metrics and step‑by‑step guidance.

AI toolingCI/CDClaude Code

0 likes · 29 min read

13 Proven Claude Code Practices to Turn AI into a Team Productivity Engine

Linyb Geek Road

Jul 21, 2026 · Industry Insights

How AI Agents Turn Engineering Experience into Machine‑Readable Infrastructure

The article explains how AI programming agents expand automation from simple tools to the entire software engineering workflow, converting tacit developer knowledge into documented rules and files like CLAUDE.md, thereby turning team experience into reusable, machine‑understandable infrastructure that continuously boosts productivity.

AI agentsAI programmingengineering knowledge

0 likes · 10 min read

How AI Agents Turn Engineering Experience into Machine‑Readable Infrastructure

Linyb Geek Road

Jul 20, 2026 · Artificial Intelligence

Understanding Agent Harness: An Architecture Guide for Java Developers

The article deep‑dives into Agent Harness, comparing it to Spring’s IoC container, explains its five‑layer design, lifecycle management, skill registration, memory handling, security sandboxing, checkpointing, multi‑model routing, and multi‑agent collaboration, and even provides a minimal 20‑line implementation for Java developers.

AI agentsAgent HarnessJava

0 likes · 16 min read

Understanding Agent Harness: An Architecture Guide for Java Developers

Linyb Geek Road

Jul 19, 2026 · R&D Management

Choosing and Matching Superpowers Skills Effectively in Real-World Development

The article outlines a systematic approach to selecting Superpowers skills across development stages, risk levels, task coupling, and problem types, provides concrete scenario examples and a decision table, and highlights common pitfalls to avoid over‑use or mis‑application of these skills.

R&D ManagementSoftware DevelopmentTest‑Driven Development

0 likes · 11 min read

Choosing and Matching Superpowers Skills Effectively in Real-World Development

Linyb Geek Road

Jul 18, 2026 · Cloud Native

How to Shrink Spring Boot Docker Images with JLink

This guide explains how to use JLink together with jdeps and a multi‑stage Docker build to create a minimal custom Java runtime, reducing Spring Boot Docker image size from over 200 MB to under 50 MB while improving startup speed and security.

DockerJLinkJava

0 likes · 10 min read

How to Shrink Spring Boot Docker Images with JLink

Linyb Geek Road

Jul 18, 2026 · Cloud Native

How to Accelerate Spring Boot Startup on Kubernetes Using CRaC

This guide walks through enabling CRaC in a Spring Boot application, building a CRaC‑compatible Docker image, creating a checkpoint job in Kubernetes, restoring the snapshot at pod start, and comparing the startup speed with GraalVM native compilation.

Azul ZuluCRaCDocker

0 likes · 11 min read

How to Accelerate Spring Boot Startup on Kubernetes Using CRaC