Eric L. Goldstein

Dynamic workflows, in my personal opinion, is the state of the art today for reliably using agents to complete medium - large projects. For extra large projects, I especially like using workflows with /loop.

You can also set "/effort ultracode", a new effort level that runs at xhigh and lets Claude decide on its own when a task warrants a dynamic workflow.

Introducing: Specter Supercharge Agentic Engineering with - Typescript Framework for Specs that compile, execute, and scaffold your app - Vertical Slices that can be built, tested, and operated independently Agents can finally work on large complex codebases reliably

Spotify's Chief Architect just showed how they ship 4,5K deployments /day with Claude at Anthropic stage 27-minutes. free. By #1 music app dev "More than 99% of our engineers use AI coding tools. Adoption took off after Opus 4.5" Worth more than any $500 vibe-coding course.

This is the best site on the internet to learn harness engineering walkinglabs.github.io/learn-harness-…

Introducing React Review Bot PR review that catches broken React code before you merge - Unnecessary useEffects - Fix UI bugs + race conditions - Catch performance issues

@tannerlinsley Yes critical CSS, that's what I thought the announcement meant. Thanks for the clarification.

@EricLGoldstein This feels like you’re referring to critical CSS in lining and that is a little bit different and not totally compatible with a streaming model. However, we could investigate doing something like this for pre-rendered content.

CSS Inlining is 🔥!

GitHub may have just killed vibe coding. Their new repo “spec-kit” already has 92k+ stars — and it reveals where AI-driven development is actually heading. Instead of telling your AI: “Build me a todo app” and hoping for the best… You run 6 commands that turn your idea into an executable specification: • "/speckit.constitution" → defines project rules (quality, testing, UX) • "/speckit.specify" → explains WHAT to build, not the tech • "/speckit.clarify" → AI asks questions to remove ambiguity • "/speckit.plan" → choose the stack and architecture • "/speckit.tasks" → generates dependency-ordered tasks • "/speckit.implement" → the agent builds it The deliverable is no longer the code. It’s a living specification your AI can read, debate, and execute. Works with Claude Code, Copilot, Cursor, Codex, Gemini, and 25+ other agents. The shift most people still don’t see: “AI writes code” → “AI executes specifications.” Intent-driven development is the next era of software development. Repo👇

In celebration of @rolldown_rs 1.0 🎉 Announcing `comptime` — a Zig-inspired build-time evaluation primitive, exposed as Vite and Rolldown plugins This allows you run code at build time, replacing the call site(s) with the evaluated output value. github.com/lukeed/comptime

The official pnpm rewrite in Rust >pacquet is a port of the pnpm CLI from TypeScript to Rust > pacquet is under active development and not yet ready for production use. github.com/pnpm/pacquet

@gnukeith MRU tabs don't work consistently anymore. Please fix? 🙂

I see this question a lot, so Brave stable (red one) is what 99% of our users are using, it just works Brave Nightly (purple one) is the one I work on, it has experimental features, bunch of cool stuff that we are working on that might eventually end up in stable if the feedback is positive I do not recommend using Nightly as a daily driver, but you can and if you do, you can tag me and let me know what you think of it ^^

@trueadm Compiler king be praised 🙂 Really glad to hear more from you

Can't wait to talk to Ryan about all things compilers/reactivity/frameworks/UI etc. Such good vibes :)

@ctatedev Wow this is great! We've been using mkcert for SSL and app.localhost locally manually until now. Have to give this a try!

Portless killed :3000 Dev servers got stable names like myapp.localhost Agents could use worktrees in parallel without stepping on each other Now it's easier than ever in v0.11 Just run: portless Zero config. Zero args. Zero code changes.

@nexxeln @RyanCarniato @aidenybai skills, github.com/aidenybai/soli…

@devagrawal09 If it somehow uses Solid 2.0 async primitives I'm all for it. The more excuses I have to use them the better. 🙂

how would you guys like a "build your own sync engine" video series

Man, I just love Symbol.asyncDispose. Makes my tests so much more straightforward. Thanks @kettanaito for turning me onto this. And with the right guidelines (a testing-principles.md linked to from agents.md), my agent is "using" (pun intended), this feature perfectly 🔥

⚡️ New in Vitest 4.1: "fast-forward" mode. One line. Faster tests. No more fake timers hell. 👉 @younesjd.dev/new-in-vitest-4-1-skip-timer-delays-with-fast-forward-mode-b66edc8b3a44" target="_blank" rel="nofollow noopener">medium.com/@younesjd.dev/…

if your skill depends on dynamic content, you can embed !`command` in your SKILL.md to inject shell output directly into the prompt Claude Code runs it when the skill is invoked and swaps the placeholder inline, the model only sees the result!

Speed up rendering with content-visibility: auto ⚡ This CSS property skips rendering off-screen content until needed, giving massive performance wins on long pages. ⋅ Pairs with contain-intrinsic-size ⋅ Zero-effort lazy rendering Learn more 👇 developer.mozilla.org/en-US/docs/Web…