Geek头条(2026-08-23)

Skills for Real Engineers. Straight from my .agents directory.

https://aihero.dev/skills

1. Skills For Real Engineers

My agent skills that I use every day to do real engineering - not vibe coding.

Developing real applications is hard. Approaches like GSD, BMAD, and Spec-Kit try to help by owning the process. But while doing so, they take away your control and make bugs in the process hard to resolve.

These skills are designed to be small, easy to adapt, and composable. They work with any model. They’re based on decades of engineering experience. Hack around with them. Make them your own. Enjoy.

If you want to keep up with changes to these skills, and any new ones I create, you can join ~60,000 other devs on my newsletter:

Sign Up To The Newsletter

1. Installation (30-second setup)

Two ways in, two philosophies. The Claude Code plugin installs the whole set as a managed, read-only bundle that updates when I ship, so you subscribe rather than fork. skills.sh copies editable skill files into your project, so you can hack on them and ma…

Visualize your year in travel using your Google Location History (Timeline) data

1. Timeline Visualizer

한국어 안내 · 日本語

Turn your Timeline file into an animated travel video on your Android phone. Choose exact dates, preview the Journey, and create an MP4 ready to watch or share.

1. Use on iPhone

Open the iPhone web app in Safari. There is no app to install and no Timeline file is uploaded.

• In Google Maps, open profile picture → Settings → Personal content → Export Timeline data and save Timeline.json in Files.

• Return to the web app and select Choose Timeline.json.

• Choose a month range or ex…

利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

1. MoneyPrinterTurbo 💸

2. 一站式 AI 短视频生成工具

只需提供视频主题或关键词，即可自动生成视频脚本、匹配素材、生成字幕和背景音乐，并合成高清短视频。

简体中文 | English | 日本語 | 版本发布 | 问题反馈

1. 界面预览 🖥️

2. WebUI

3. API

4. 特别感谢 ❤️

![Kimi 赞助 MoneyPrinterTurbo](https://gcdn.m...

⚡️A native, local-first alternative to Logitech Options+, written in Rust 🦀 — remap buttons, DPI, and SmartShift over HID++. No account, no telemetry.

https://openlogi.org

Warning

OpenLogi is under active development and not yet stable — features and config may still change. Give the repo a Star ⭐ and Watch 👀 it to get notified when a new release lands.

English | 简体中文 | 日本語 | Deutsch | Français | 한국어

1. OpenLogi

⚡️ A native, local-first alternative to Logitech Options+, written in Rust 🦀Unlock the full capabilities of Logitech mice, keyboards, and webcams over HID++ and UVC

![GitHub downloads](https://img.shields.io/github/downloads/...

🦔 PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP.

https://posthog.com

Docs - Community - Roadmap - Why PostHog? - Changelog - Bug reports

1. PostHog is the open source platform for building sel…

Go 语言前技术负责人 Russ Cox 近日在 ACM 深度专访中，借用《软件设计哲学》中的“战术龙卷风”概念对 AI 编程热潮发出尖锐警示：如果管理者缺乏审慎判断，盲目追求代码产出速度，AI Agent 极易演变为疯狂堆砌技术债与复杂度的“终极战术龙卷风”。结合 Peter Naur 关于“编程即理论构建”的经典洞察，文章剖析了为何缺乏连贯架构思维的 AI 会加速“程序之死”，并重申了 Go 语言“用约束换简单”的工程哲学与自动化测试作为 AI 时代安全底座的决定性价值。

很多人说使用 AI 辅助开发，无脑选 mac ，其中 AI 应用的功能是一方面，还有些系统底层的原因没有多少人提到，本文从 AI 辅助并行开发角度进行分析分享，只要不是单仓单分支单线程开发的新手，都可以了解下。

git 的多人合作机制基于 commit ，我们可以理解 commit 是一次差异快照，描述了本次提交修改了哪些内容，如果两个 commit 对同一个文件的内容修改产生重合即会产生冲突，冲突是阻碍并行开发的原因。

为避免冲突，人在协作时分了 origin 仓，fork 仓，不同仓下有独立 main 分支，feature 分支，fix 分支等。以往对单人来说同一时刻只需要单仓单分支即可满足大多数需求，如果个人要同时进行多种可能性方向的研究，则可以使用 worktree ，可以理解为分支的分支，也有人直接把文件夹单独拷贝一份，在同一分支进行不同修改，建议了解下 worktree ，直接拷贝和 worktree 行为是相似的。

有些模型虽然聪明，但速度较慢，在同一文件夹内开多个会话修改，很容易导致冲突，缓存命中问题等，这时适合使用 worktree 为每个 agent 创建自己的工作空间，不会被其它 agents 修改。

创建 worktree 时，git 会选择一个 branch checkout 到新的文件夹，多个 worktree 的绝大部分文件都相同，如果文件系统支持 COW （ copy on write ）功能，这些相同文件…

https://github.com/xixu-me/xget

还想下载一下 huggingface 的模型来着

父辈建立百亿公司，他接手面临一个新世界。

具身大脑走向 “大一统”。

1. What’s Changed

• perf(adk): stop session replay at replacement boundary by @shentongmartin in #1202

Full Changelog: v0.10.0-alpha.19…v0.10.0-alpha.20

在 AI 代码极度普遍的当下，一直告诫开发者要严肃对待自己编写的代码的 Uncle Bob，如今已经彻底放弃对 AI 代码逐行人工评审，转而在搭建一套依靠指标与约束条件的管控框架，这一做法在工程师群体当中引发激烈争论。

一个已经训完的大模型，不换参数、不做微调，究竟还能榨出多少性能？

先跑起来的人，会先被看到。

AI产品经理入行指南

style(test): format release plan cache assertion

One of the memes on Twitter is that “programming is solved now.” I’m not sure to what degree it is, but one thing is pretty clear: the act of familiarizing yourself with a language no longer matters and some of the friction that mattered for humans does not matter for agents.

As a result, LLMs make language choice much less consequential than it used to be. If you don’t like the choice, you can seemingly rewrite it in another language and you can make it pick a language that you, as a programmer, are entirely unfamiliar with.

Which in turn means that people can, and do, choose based on the marketing of languages much more. As a long-term Rust programmer I found it quite fascinating to see people now ship Rust code who previously might not have chosen it. I attribute at least one part of this to two recent vibe shifts: there is a lot more talk about wanting fast software, and about LLMs being exceptional at optimizing code without regressing behavior.

Folks like Mitchell Hashimoto, Charlie Marsh, Jarred Sumner, Daniel Lemire and quite a few others always carried a certain level of obsession with fast and performant software and they also all happen to be receptive to agents writing code. Maybe as a result, or unrelated others are now joining in. That’s because with things like autoresearch you don’t even necessarily need to know all the tricks: you just need to put an agent on it — t…

Rust 官方 Vision Doc 项目组用一年时间完成 4200 份问卷与 70 场深度访谈，试图回答“学 Rust到底难在哪”。调研发现，真正的障碍往往不是语法，而是从 C++、Java 等语言带来的思维惯性；编译器报错本身就是最好的老师；LLM 正在降低 Rust 的学习门槛，甚至让无编程背景的人也能成长为 Rust 工程师。与此同时，大量学习者在受挫后悄悄离开，从未在社区发声——这部分“沉默的大多数”，可能是 Rust 生态最该关注、却始终缺失的一块拼图。

Suggested patches open in Claude Code on the web, using the models your team already uses. These updates are part of our work to give defenders greater access to Mythos results without requiring direct access to the model: the model runs behind the scan and returns findings only. Scans are billed as standard token usage under your existing plan.💬7🔄8❤️307👀88727📊32⚡ Powered by xgo.ing

It’s one of several steps to bring frontier capability to more defenders: we’re working with partners to integrate Mythos 5 into their security products and services, our new Defender Advantage Fund provides $35M in credits for open-source security, and we’re expanding our Cyber Verification Program in the coming weeks. Read more: claude.com/blog/bringing-…💬4🔄3❤️242👀75135📊26⚡ Powered by xgo.ing