chase_ai

The blog.

109 posts on claude-code, page 8 of 10RSS feed

  1. GSD 2 vs Claude Code: Which AI Coding Tool Wins?

    I put GSD 2 and Claude Code head-to-head building the same app. One cost $27, the other used less than 1% of my plan. Here's the full breakdown of cost, speed, and quality.

    claude-codegsd2ai-coding-tools

  2. Claude Code Skills: How to Create, Test, and Master Custom Skills

    Claude Code skills are text prompts that customize how Claude Code handles specific tasks. Here's how to find, install, create, and benchmark your own.

    claude-codeai-skillsskill-creator

  3. Did Claude's 1M Context Window Defeat Context Rot?

    Opus 4.6's 1M token context window scores 78.3% on the eight-needle test with only a 14% drop from 256K tokens. Here's what the benchmark data actually means.

    claude-codecontext-windowopus-4-6

  4. CLI Anything + Claude Code: Agent-Native Tools

    CLI Anything lets you point at any open-source software and generate a CLI tool that Claude Code can control directly from the terminal. Here's how to set it up and why this matters.

    claude-codecli-anythingagentic-coding

  5. Google's New CLI Just Fully Unlocked Claude Code

    The Google Workspace CLI gives Claude Code complete access to Gmail, Drive, Calendar, Docs, and Sheets. Here's how to set it up securely with Model Armor and sandboxing.

    claude-codegoogle-workspace-cliai-productivity

  6. 10 Claude Code Plugins That Actually Matter in 2025

    The plugin ecosystem for Claude Code is exploding. Here are the 10 tools — CLIs, skills, and frameworks — I actually use every day, with install instructions and real use cases for each.

    claude-codeai-developmentcli-tools

  7. The 6 Levels of Claude Code Explained

    There are six distinct levels of Claude Code proficiency, from basic prompt engineer to full orchestrator of agent teams. Here's the roadmap most people are missing — and what to master at each stage.

    claude-codeai-developmentagentic-coding

  8. Claude Code Agent Loops: What They Actually Do

    Agent loops just dropped in Claude Code — and the internet is already calling it a 24/7 autonomous agent. It's not. Here's what /loop actually does, its real limitations, and when to use it vs. Claude Code Desktop scheduling.

    claude-codeai-automationdeveloper-tools

  9. Claude Code + Playwright CLI: Browser Automation Guide

    Playwright CLI is the most token-efficient way to do browser automation inside Claude Code. Here's how to install it, set up the skill, and build reusable UI testing workflows.

    claude-codeplaywright-clibrowser-automation

  10. Claude Code + NotebookLM + Obsidian Research Workflow

    Combine Claude Code, NotebookLM, and Obsidian into a single research workflow that gets smarter the more you use it. Here's the full setup, step by step.

    claude-codenotebooklmobsidian

  11. Claude Code Skill Creator: Test & Improve Skills

    Anthropic's updated skill creator plugin brings evals, benchmarking, and A/B testing to Claude Code skills — so you can stop guessing and start measuring whether your skills actually work.

    claude-codeai-toolsanthropic

  12. Claude Code + Obsidian: Persistent Memory That Works

    Claude Code forgets everything between sessions. Obsidian fixes that — for free. Here's how to set up persistent memory that makes Claude Code actually work like a personal assistant.

    claude-codeobsidianai-tools