Rifandani ⚛️

The Iranian regime devastated Arad and Dimona by deliberately striking civilians with missiles. Over 100 people were injured, including children. A blatant war crime. Pure terrorism.

@Saboo_Shubham_ Is this a "deployed" anthropic's skill-creator skills?

Self-improving AI Agent skills using Gemini 3. Just upload your skills and watch it improve in real-time. 100% Opensource. Launching soon.

@jamonholmgren I like the v2 of Anthropic's skill-creator skills that could eval my existing skills

Agent skills feel over-engineered to me. I still haven’t found a reason why I’d use them over an agent router (index) and documentation. I’ll keep my mind open. But they feel like the type of overengineered solution that programmers love to come up with.

@code Ralph mode!

🤖 Try Autopilot (Preview) in VS Code! With Autopilot enabled, the agent stays in control of the workflow. It can run tools, retry on errors, and continue working until the task is complete. Learn more: aka.ms/VSCode/Autopil…

@andrii_sherman 5x engineer

Rate my new PlanetScale setup

@matteocollina GOAT 👍

🎯 After years of building with Node.js, I've organized my hard-won knowledge into skills: a collection of best practices, workflows, and deep expertise my AI assistant uses to write code to my standard. No more repeating myself on every code review. 👇

@mattpocockuk oxlint + oxfmt 👍

I'm in the phase of my Ralph journey where I'm happy with the quality and now optimising for speed tsc -> tsgo Task caching with turborepo Let's get SHIPPING

@cnakazawa How's your workflow? Did u use something like ralph, beads, GSD, etc?

Used up 70% of my (doubled) weekly codex limit in 24 hours. Have not opened VS Code. Shipped a lot, but every day is way more intense, too. My recommendation is to work intensely for 5-6 weeks at a time, then take a week off. Touch grass/snow, not tokens.

@RhysSullivan Doesn't they shipped docs into the node_modules? And u can use their skills to make sure the agent look for it

easily the best ai coding tip i have is to know good repos and tell your agent to clone them into /tmp/ to learn from them

@KevinVanCott @Deepaktvit @tannerlinsley They're asking something like unhead/react

@Deepaktvit @tannerlinsley What does a dedicated SEO library offer? I see so many people ask this and I don't even know what they're asking for.

Hey @tannerlinsley, are there any plans for a dedicated TanStack SEO library in the future?

@karpathy What's agent teams?

Cool chart showing the ratio of Tab complete requests to Agent requests in Cursor. With improving capability, every point in time has an optimal setup that keeps changing and evolving and the community average tracks the point. None -> Tab -> Agent -> Parallel agents -> Agent Teams (?) -> ??? If you're too conservative, you're leaving leverage on the table. If you're too aggressive, you're net creating more chaos than doing useful work. The art of the process is spending 80% of the time getting work done in the setup you're comfortable with and that actually works, and 20% exploration of what might be the next step up even if it doesn't work yet.

@hugorcd @AxiomFM @posthog @sentry Cool

The new landing page for evlog.dev is live After a month of building, here's where we're at: Frameworks & runtimes: • First-class Nuxt, Next.js & TanStack Start • Hono, Cloudflare Workers, Bun, Node & more Drain to anywhere: • @axiomfm, @posthog, @sentry, @BetterStackHQ • OTLP, custom adapters • Batching, retries, fan-out Core features: • Wide events with full context • Structured errors with why/fix suggestions • Smart sampling (head + tail) • AI-ready output • Client to server transport

@posthog Awesome ❤️

Introducing Logs by PostHog - Free, up to 50 GB for free every month - $0.25 per GB ingested, (or $0.15 per GB at 300 GB+) - 14-day retention, no per-seat pricing, no query fees. - Frontend and backend context, linked to users and sessions. - Uses standard OpenTelemetry – no proprietary SDKs. - Structured logs you can pivot around, not raw text you scroll through.

@ctatedev Can it generate playwright test code?

Now available: agent-browser v0.10 ‐‐𝚜𝚎𝚜𝚜𝚒𝚘𝚗‐𝚗𝚊𝚖𝚎 auto save/restore cookies + localStorage, encrypted at rest 𝚜𝚝𝚊𝚝𝚎 𝚕𝚒𝚜𝚝/𝚜𝚑𝚘𝚠/𝚛𝚎𝚗𝚊𝚖𝚎/𝚌𝚕𝚎𝚊𝚛/𝚌𝚕𝚎𝚊𝚗 session state management commands ‐‐𝚊𝚞𝚝𝚘‐𝚌𝚘𝚗𝚗𝚎𝚌𝚝 discover and attach to an already-running Chrome ‐‐𝚗𝚎𝚠‐𝚝𝚊𝚋 click opens link in a new tab instead of navigating current page ‐‐𝚎𝚡𝚊𝚌𝚝 forwarding properly passed for role, label, and placeholder locators 𝚗𝚙𝚖 𝚒 ‐𝚐 𝚊𝚐𝚎𝚗𝚝‐𝚋𝚛𝚘𝚠𝚜𝚎𝚛

@sporadica I still like their Debug mode, helps me a lot

fr though is Cursor cooked or what

@threejs Do we have three.js agent skills?

6M downloads/week 🚀

@hugorcd @posthog @sentry @AxiomFM Awesome work 👍

Been having a lot of fun pushing evlog lately: zero‑dependency core, wide events, structured errors, and fresh adapters for @posthog, @sentry, OTLP, @axiomfm & Workers. Into observability with good DX? This might be your new favorite logging layer → dub.sh/better-log

@saltyAom It's so much faster than hono? 🤯 Do you have a migration guide? I want to migrate from hono

How we made Elysia fast Wrote a thing about we made Elysia fast and likely as one of the fastest JavaScript frameworks Explaning about JIT "Compiler" and "Sucrose"

@mattpocockuk What is the difference between the write-a-skill and the skill-creator?

Skills I'm currently running: - write-a-prd - make-refactor-request - tdd - design-an-interface - write-a-skill

@aisdk Does this works in monorepo? From the markdown seems doesn't

The AI SDK skill is now available. ▲ ~/ npx skills add vercel/ai Visit skills.sh to learn more. skills.sh/vercel/ai/ai-s…