Ajmal

Check it out live at ajmalafif.com/uses/

In 14 minutes, this Anthropic engineer who wrote "Building Effective Agents" will teach you more about building them right than most developers figure out on their own in months. Bookmark this for the weekend. Then read the builder's guide below.

帅气！以前都不知道看个啥！击剑世界大赛将引入“剑尖可视化系统”。该系统由日本人开发，曾在东京奥运会中使用，无需标记即可追踪并呈现剑尖的运动轨迹。

UIデザインパターンを 全部1ページにまとめた 辞典サイトを作りました！ ハンバーガーメニュー、カンバン、OTP入力、ボトムシート…108種のUIパターンを「名称 × ミニチュア実物」で一覧できます。 「あのUI、名前なんだっけ？」 そんな疑問が一発で解決します。 検索・カテゴリ別表示・詳細モーダル付き ───────────────── Webサイトはプロフィールに掲載している リンクからアクセスすることができます。 アクセス → ヘッダーの「ツール」をクリック → UI Design Dictionaryをクリック

Introducing Tegaki, a handwriting animation library for the web. Works with any font or text.

こんな感じでplaywrightを用いて全てのe2eをプロダクトカスタマージャーニー全体として可視化しながらテストするのが良い。 人間の目視、直感に勝るものは無い。

Rendering HTML into a canvas… then projecting it on to a @threejs scene! Live link: cullenwebber.github.io/three-html-to-… Source code: github.com/cullenwebber/t… #threejs #webdev #shaders

i gave every train in new york an instrument 🎧 sound on trainjazz.com

Gemma 4 looks at a parking lot. Decides what to ask. Calls SAM 3.1. "Segment all vehicles." 64 found. "Now just the white ones." 23 found. One model reasoning and orchestrating. One model executing. Both running locally on a MacBook. MLX. No cloud. No API.

Advice to fellow side project tinkerers: don't forget to set up aggressive logging! (OTel traces + manual event capture + Vercel log drain into Axiom works great for me) I can fix most bug reports by pasting the user's email into an LLM connected to the Axiom MCP. Between events and traces, the model can replay nearly any timeline of activity and figure things out with a high level of detail. Don't forget to scrub PII. Over-log at first and trim back as you build confidence in different areas of the code. MCPs are still fine, ignore the haters. This works fine at a small scale, ofc.

the Shopify AI Toolkit is here manage your store with your favorite agent Claude Code, Codex, Cursor, VS Code, and more

legit curious why would @claudeai mobile app kept auto-renaming session even AFTER i renamed them manually?

I turned a lot of the information and functionality from oklch fyi into a skill. It can convert your entire project, convert individual colors, generate palettes, check contrast and more. oklch.fyi/skill

Apple is working on an iOS 26.4.1 update with bug fixes and other improvements. It will likely be released within the next 1-2 weeks.

anyone @claudeai dispatch just stop replying? how do i fix this?

Conversations tend to go better with a face and a voice. That’s why we’re thrilled to release the beta version of the first video chat skill for ANY agent, powered by our new real-time model, PikaStream1.0. The skill preserves memory and personality, and enables real-time adaptability. And if you use it with your Pika AI Self, they’ll be able to execute agentic tasks during the call 💅

Introducing cmux SSH: `cmux ssh user@remote` You can now drag images into SSH'd Claude Code sessions, and cmux will automatically upload them via scp. And when you start a dev server on the remote machine, the browser pane in cmux can reach it at localhost:3000 without port forwarding. The workspace kinda becomes the remote machine, so split panes/new tabs automatically open remote shells. Out in the latest version of cmux (0.63).

‼️Do not npm install or deploy anything right now Supply chain attack on axios 1.14.1 - even if you don’t use axios it may be a nested dep. Pin versions or wait until this is resolved

Project’s at github.com/chenglou/prete… `npm`/`bun install @chenglou/pretext` and throw your AI into making cool demos for it!

Introducing Expect Let agents test your code in a real browser 1. Run Claude Code / Codex to QA your app 2. Watch a video of every bug found 3. Fix and repeat until passing Run as a CLI or agent skill. Fully open source