Hands-on tutorials for Claude Code, AI agents, cloud and system design
TL;DR 30 sec5 min coredeep dive optional Agent Skills is Addy Osmani’s MIT-licensed pack of 25 production-grade engineering skills that make AI coding agents write specs, run tests, review changes, and check security instead of skipping all four. 100,390 stars and 10,547 forks since its first commit in February 2026, and the repo accepted a… Continue reading
TL;DR 45 sec5 min coredeep dive optional Scion is the source-control system Anthropic built when agents pushed its monorepo past 30,000 merges a day. It trades git’s distributed design for one authoritative server, a write-ahead changeset log, and review tooling built for machine-scale concurrency. Merges grew from roughly 2,500 a day in May 2026 to… Continue reading
Claude Code and Codex are the two terminal coding agents most developers are actually choosing between. They have converged on a strikingly similar shape, so the real differences sit in the safety model, the pricing structure and whether a free tier exists at all. Codex vs Claude Code: What You’ll Learn This comparison covers what… Continue reading
TL;DR 30 sec3 min coredeep dive optional Anthropic shipped seven Claude Code releases in six days (2.1.235–2.1.241, August 18–23 2026), with two changes that affect real money and real workflows: a migration command for the Python SDK 1.x break, and plugin sync from claude.ai. The seven releases span 2.1.235 on Aug 18 through 2.1.241 on… Continue reading
TL;DR 30 sec3 min coredeep dive optional Anthropic shipped 23 Claude Code releases in three weeks (2.1.243 through 2.1.273, August 24 to September 15 2026), and the month belongs to three stories: Fable 5.1 became the default Fable model, prompt-cache stability work touched at least ten releases, and permission deny rules were extended twice and… Continue reading
TL;DR 30 sec4 min coredeep dive optional Claude Code Projects relaunched on September 17, 2026 as a beta that replaces the old project folder with one coordinator conversation and a pool of parallel agent threads, each a full cloud session on its own branch. The beta runs at claude.ai/code, in the desktop app’s Code tab,… Continue reading
TL;DR 30 sec6 min coredeep dive optional Awesome Claude Code is the ecosystem’s master index: a hand-curated GitHub list of 54.5k stars that organizes the best Claude Code guides, tools, skills, and harnesses by the job you need done. The list groups roughly 30 categories, from learning guides and agent orchestration to observability and security…. Continue reading
TL;DR 30 sec7 min coredeep dive optional Learn Claude Code is a 77,000-star repository that teaches agent harness engineering by rebuilding a working Claude Code-style agent in 17 progressive lessons, from one tool and one loop up to multi-agent task graphs. Each lesson adds exactly one harness mechanism: the loop, tool dispatch, permissions, hooks, planning,… Continue reading
MCP Course by Hugging Face is the official Model Context Protocol curriculum, built in partnership with Anthropic. Alex Notov, Anthropic Technical Partner Enablement Lead, co authored Unit 3. Four units plus bonus. Free. Two certificates, Fundamentals for completing Unit 1, Completion for completing Units 2 and 3. Capstone is a PR Agent Workflow Server that… Continue reading
Learn what Claude Code is, install it, authenticate, set up your terminal and IDE, and run your first session.
Continue reading
Learn to use Claude Code’s built-in slash commands for context management, session control, and configuration.
Continue reading
Understand how Claude Code remembers context across sessions using CLAUDE.md files and auto memory.
Continue reading
Configure Claude Code for a new or existing project with CLAUDE.md, permissions, and settings.
Continue reading
Master advanced Claude Code commands: context management, bundled skills, fast mode, keyboard shortcuts, and power features.
Continue reading
Learn to design and build effective Claude Code skills with progressive loading, dynamic context, and invocation control.
Continue reading
Automate your Claude Code workflow with hooks that react to events like tool usage, session stops, and file changes.
Continue reading
Connect Claude Code to external services via MCP servers for live data access from GitHub, databases, Slack, and more.
Continue reading
Delegate complex tasks to specialized AI agents with isolated context windows and custom system prompts.
Continue reading
Master planning mode, extended thinking, auto mode, sandboxing, headless usage, and enterprise configuration.
Continue reading
Build CI/CD integrations, scheduled tasks, and multi-step automation workflows with Claude Code.
Continue reading