惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园 - 叶小钗
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Microsoft Security Blog
Microsoft Security Blog
罗磊的独立博客
大猫的无限游戏
大猫的无限游戏
美团技术团队
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
aimingoo的专栏
aimingoo的专栏
腾讯CDC
WordPress大学
WordPress大学
Apple Machine Learning Research
Apple Machine Learning Research
F
Fortinet All Blogs
G
Google Developers Blog
MongoDB | Blog
MongoDB | Blog
Microsoft Azure Blog
Microsoft Azure Blog
小众软件
小众软件
Engineering at Meta
Engineering at Meta
博客园_首页
B
Blog RSS Feed
D
Docker
M
MIT News - Artificial intelligence
爱范儿
爱范儿
I
InfoQ

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
Agents with Taste
dglzab · 2026-04-22 · via Hacker News - Newest: "AI"

An engineer has never been more leveraged than today thanks to a fleet of agents. But when it comes to more visual work, like animations, coding agents don’t quite know what great feels like.

My way of getting there is to create a skill file for each aspect of the interface. If you know what great feels like, describe the rules, then give them to your agents so they can follow them.

The result is an AI that has your taste and knowledge and can produce significantly better results, like the interactive Linear logo I made with Claude Code:

Transferring taste

With enough experience, you can not only tell what feels better, but also why. By then you’ve not only built your taste, but also the ability to articulate it.

The correct animation below feels right, because it animates from a higher initial scale value. It makes the movement feel more gentle, natural, and elegant.

scale(0) on the left feels wrong because it looks like the element comes out of nowhere. A higher initial value resembles the real world more. Just like a balloon, even when deflated it has a visible shape, it never disappears completely.

That’s the why. There’s no magic involved. Almost every “taste” decision has a logical reason if you look close enough. This applies to any other discipline really.

Of course the more creative part of the job is still up to you, but the more you can package into a skill, the more leverage you can get out of your agents.

Since we know how to articulate why something feels good, we can use that knowledge to guide the agents, just like you would guide a less experienced designer. In this case the scale trick and many others live under “Practical Tips” in my skill:

## Practical Tips | Scenario | Solution | | ------------------------------- | ----------------------------------------------- | | Make buttons feel responsive | Add `transform: scale(0.97)` on `:active` | | Element appears from nowhere | Start from `scale(0.95)`, not `scale(0)` | | Shaky/jittery animations | Add `will-change: transform` | | Hover causes flicker | Animate child element, not parent | | Popover scales from wrong point | Set `transform-origin` to trigger location | | Sequential tooltips feel slow | Skip delay/animation after first tooltip | | Small buttons hard to tap | Use 44px minimum hit area (pseudo-element) | | Something still feels off | Add subtle blur (under 20px) to mask it |

Practical tips for building better animations.

Another example is choosing the right easing, the most important part of any animation. This is strict so the agent doesn’t have to guess or make up its own rules. It just follows the flowchart and picks the right easing according to my philosophy.

## Easing Decision Flowchart Is the element entering or exiting the viewport? ├── Yes → ease-out └── No ├── Is it moving/morphing on screen? │ └── Yes → ease-in-out └── Is it a hover change? ├── Yes → ease └── Is it constant motion? ├── Yes → linear └── Default → ease-out

Choosing the right easing has never been easier.

We can then cover all other ingredients of an animation so that the agent knows exactly what to do in each scenario. Duration is another animation piece:

## Duration Guidelines | Element Type | Duration | | --------------------------------- | --------- | | Micro-interactions | 100-150ms | | Standard UI (tooltips, dropdowns) | 150-250ms | | Modals, drawers | 200-300ms | **Rules:** - UI animations should stay under 300ms - Larger elements animate slower than smaller ones - Exit animations can be ~20% faster than entrance - Match duration to distance - longer travel = longer duration

Duration guidelines for UI animations.

You can package any “taste” decision into a skill in this way, whether it’s layout, icons, or color theory. Here are some rules on typography in one of my skill files:

## Typography 1. Cap body text at about 65ch instead of stretching full width so line length stays comfortable to read. 2. Apply `tabular-nums` to price columns so digits align and the column reads cleanly. 3. Use the `…` character instead of `...` in markup so truncation follows the container instead of snapping at a fixed character count. 4. Loosen letter-spacing on uppercase labels; tight uppercase reads cramped. 5. Declare a fallback stack whose x-height and weight match the primary face so loading does not cause layout shift. 6. Reserve underlines for links; emphasize non-link text with weight or color so underline stays a reliable affordance and people are not tempted to click inert copy. 7. Prefer bold for interface emphasis and keep italic for citations and linguistic stress in prose — italic hierarchy reads like print editorial, not UI hierarchy.

So take a step back, ask yourself why you made a certain decision, articulate clearly why something has to be done this way, set the rules, be strict. To make this process easier, I use the skill-creator skill from Anthropic.

After you’ve packaged your taste into a skill, you can feed it to your coding agents.

Here’s me asking Claude Code to improve a dialog animation using my animation skill. It gives me a clear list of issues based on the rules I defined and a before and after table of what has changed:

Try it out

I turned my blog articles into one big design engineering skill that you can try out below. It covers animations, component design, principles from my open source projects like Sonner, and more.

npx skills add emilkowalski/skill