Engineering Manager / Technical Lead
A topic hub collecting every article tagged Claude Code. Use it to explore related posts and follow this theme across the site.
20 articles
An architecture blueprint for translating Ultracode's high-effort planner, parallel workers, verification, state, and guardrails into Cursor or a custom agent harness.
Running one workspace agent in the cloud is a trick; running ten reliably is an engineering discipline. A source-backed guide to environment-as-code, secrets, private submodule auth, fan-out topology, and the review capacity that actually limits throughput.
A practical guide to the full vibe-coding loop — explore with Ask mode and OpenSpec, install skills, generate with Plan mode or spec-driven tools, review with Bugbot and /simplify, verify in the browser with Playwright MCP, deploy with MCP, and capture lessons in custom skills.
Why OpenSpec's explore → propose → apply loop is a better default than built-in Plan Mode: lighter ceremony, durable repo-native plans, and guardrails that keep exploration agnostic until you choose to commit.
A practical guide for engineers and PMs on what belongs in the main AI coding conversation, what can be delegated to subagents, and what the real tradeoffs look like in Cursor and Claude Code.
A practical guide to publishing, reviewing, and sharing SKILL.md agent skills inside a company, inspired by how public directories like skills.sh work.
The grill-me skill is a tiny prompt pattern with a big payoff: make the agent interview you before it builds. This guide explains how it works, how to create your own project skill, and how to fit it into a practical agentic development workflow.
A practical research audit for engineers and PMs: when agent skills improve coding agents, when default agents plus repo context are enough, and how to evaluate the tradeoff.
A simple, source-backed guide for engineers and PMs to start with GitHub Spec Kit, understand the main commands, and use the workflow cleanly in Cursor or Claude Code.
A source-backed follow-up on routing GitHub Spec Kit phases across fast drafting models, deeper planning models, and stronger implementation models without treating all steps as the same kind of work.
A practical engineer-first guide to turning a messy enterprise feature into specs, acceptance criteria, Beads task graphs, git worktrees, and parallel delivery across Cursor and Claude Code.
A grounded look at how Cursor's subagents and skills fit with Claude Code's subagents, worktrees, and the new /simplify command for research, implementation, and cleanup.
How AI agents are collapsing the gap between 'I wonder how X works' and 'I have a working implementation of X' — and the research workflows that actually hold up under pressure.
A research-checked comparison of Claude Code, Cursor, and Beads for planning, execution, persistence, and async collaboration in modern product development.
Learn Git from scratch — essential commands, GitHub CLI installation, and how to use Claude Code or Cursor to run Git for you. Five levels of depth for every type of learner.
How AI-assisted engineering workflows mature from a simple system prompt into skills, MCP tools, and full plugins — with real engineering examples at every stage.
How to build a workflow that groups git worktrees from multiple repositories into a single feature folder — then use Claude Code's agent teams to generate changes and PRs across all of them in parallel.
A deep comparison of four approaches to building AI agents — OpenAI with raw fetch, Vercel AI SDK, Claude Agent SDK, and Agno with FastAPI — and which one you should pick.
Claude Code now runs on iOS and Android. Here's how to kick off tasks, review diffs, and ship pull requests without touching your laptop — using Remote Control and the Claude mobile app.
A practical guide to building and shipping a full-stack app using Lovable for UI, Claude Code for logic, and Cloudflare for deployment.
Quick find
Search by topic, title, framework, or pattern.