Skip to main content

Zero-Shot Log

Hands-on notes on Generative AI × Development

View All Posts

Latest Updates

View Archive
Claude Code Routines × GitHub: Pitfalls and Workarounds
claude-code routines mcp github automation

Claude Code Routines × GitHub: Pitfalls and Workarounds

A breakdown of timeout limits and sandbox authentication constraints I hit when saving files via the GitHub MCP from Claude Code Routines, along with workarounds for each.

> _
codex hooks ai

Enabling and Using Codex's experimental Hooks

How I discovered Codex's experimental Hooks feature, enabled it, and reverse-engineered its config structure and supported events by reading the source.

> _
claude-code ai automation cron

Hands-on with Claude Code's /loop Feature

Using Claude Code's /loop to define recurring jobs in natural language. Practical patterns for API and issue monitoring, gotchas around auto-compact and interval design, and how it interacts with Hooks.

Claude Code Agent Teams: Reusing Existing Skill and Agent Knowledge
claude-code agent-teams multi-agent prompt-engineering

Claude Code Agent Teams: Reusing Existing Skill and Agent Knowledge

An overview of Agent Teams, how it differs from traditional subagents, the current state of reusing existing skills and agent definitions, and what token consumption actually looks like.

Lost in the Middle — Prompt Design that Beats LLM Position Bias
llm prompt-engineering context-engineering rag lost-in-the-middle

Lost in the Middle — Prompt Design that Beats LLM Position Bias

LLMs tend to overlook the middle of long prompts (the Lost in the Middle problem). This post covers the cause and practical countermeasures — tail checklists, the sandwich strategy, XML-tag structuring, and more.

> _
design ai-tools claude

Escaping the AI-Generated 'Purple Gradient'

I redesigned my tech blog using a workflow that combines Claude Code, Playwright MCP, and Stitch AI — and worked around the typical AI-generated design clichés.