AI Engineering Tool BuilderI build AI engineering tools, developer workflows, and knowledge systems for serious software work.
Public tools shaped around agents, database investigation, and skill distribution.
The package manager for AI agent skills. Install, update, sync, and govern skills across coding agents.
Problem
AI coding agents are becoming part of daily development, but their reusable skills are still scattered across repos, local folders, and different agent ecosystems.
Provides
skill-hub turns skills into manageable packages so they can be installed, updated, synchronized, and governed across Codex, Claude, Gemini, and similar workflows.
Read-only database CLI skill for Codex.
Problem
Real production debugging often needs schema lookup, safe read-only SQL, and cross-environment comparison without turning an AI session into an unsafe database client.
Provides
database-cli gives Codex a controlled database investigation workflow: inspect schema, search metadata, run read-only queries, and compare records with guardrails.
Long-running notes on tool building, engineering efficiency, and Obsidian workflows.
Notes on CodeGraph, skill-hub, agent frameworks, and AI-assisted development practice.
Backend systems, development environments, deployment entry points, and engineering toolchain practice.
How agents, Obsidian, and knowledge graphs can form a durable knowledge workflow.
Browse the real connections between posts, tags, and knowledge notes.
Recent writing on agent coding, engineering workflows, and knowledge systems.
CodeGraph 的价值不是替代 grep，而是让 Agent 在真实代码库里先看定义、调用方、被调用方和影响面，减少盲搜、误判入口和漏改调用链的问题。
Agent 与 Obsidian 结合后，个人知识库不再只是静态笔记仓库，而可以成为可检索、可整理、可复用、可输出的长期知识工作台。
深入对比 OpenClaw 和 Hermes Agent 两个开源 AI Agent 框架，探讨它们在渠道覆盖、记忆系统、插件生态等方面的设计差异与适用场景。
