慣性聚合 高效追讀感興趣之博客、新聞、科技資訊
閱原文 以慣性聚合開啟

推薦訂閱源

博客园 - 司徒正美
V
V2EX
T
Tailwind CSS Blog
有赞技术团队
有赞技术团队
aimingoo的专栏
aimingoo的专栏
Apple Machine Learning Research
Apple Machine Learning Research
IT之家
IT之家
Blog — PlanetScale
Blog — PlanetScale
A
About on SuperTechFans
月光博客
月光博客
T
The Blog of Author Tim Ferriss
宝玉的分享
宝玉的分享
Martin Fowler
Martin Fowler
博客园 - 聂微东
The GitHub Blog
The GitHub Blog
V
Visual Studio Blog
WordPress大学
WordPress大学
酷 壳 – CoolShell
酷 壳 – CoolShell
Engineering at Meta
Engineering at Meta
GbyAI
GbyAI

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant Common SOC 2 Failures (Real World) Stop Vibe-Checking Your AI App: A Practical Guide to Evals How to Use SonarQube and SonarScanner Locally to Level Up Your Code Quality Your Next To-Do App Is Dead — I Replaced Mine with an OpenClaw AI Sign a Nostr event in 60 lines of Python using coincurve — no nostr-sdk, no nbxplorer, no rust toolchain ITGC Audit Explained Like You’re in Big 4 Patch Tuesday abril 2026: Microsoft parcha 163 vulnerabilidades y un zero-day en SharePoint Stop scraping everything: a better way to track competitor price changes Listing on MCPize + the Official MCP Registry while routing payments OUTSIDE the marketplace — how I kept 100% of my x402 revenue Building an AI-Powered Risk Intelligence System Using Serverless Architecture Why We Ripped Function Overloading Out of Our AI Toolchain Testing AI-Generated Code: How to Actually Know If It Works SaaS Churn Is Killing Your Business. Here Is What to Do About It (Without a Support Team) The Speed of AI Is No Longer Linear - And Self-Improving Models Are Why How to Implement RBAC for MCP Tools: A Practical Guide for Engineering Teams From Standard Quote to Persuasive Proposal: AI Automation for Arborists I built a CLI that scaffolds complete multi-tenant SaaS apps Axios CVE-2025–62718: The Silent SSRF Bug That Could Be Hiding in Your Node.js App Right Now The dashboard that ended our friendship Data Pipelines Explained Simply (and How to Build Them with Python)
众皆言双子座3.5闪存之事。然谷歌IO2026之实情,实乃技能文件耳。
Sreejit Prad · 2026-05-24 · via DEV Community

此乃投献于谷歌I/O写作挑战


众皆言归,谈 Google I/O 2026 之 Gemini 3.5 Flash 基准。Veo 3. Gemini Omni 事多模物理。如常之要旨甘醴。佳物也。所期。

然若欲解之何哉此 I/O 实则更易开发者之建 — 非在理论,而在生产,今周 — 汝当观开发者主旨之语,或得四句。

Markdown文件名唤作SKILL.md.

未尝闻之,余亲试焉。其实乃如是也。


抗重力CLI究竟生成何物(非幻灯片所言)

凡所阅之I/O总纲,皆称AGENTS.md为代理配置之素朴。洁。简。一册而已。

此言非尽然。今观/agents于Antigravity CLI 1.0.2之新会,于实项目中所显:

Create New Agents
  Workspace: C:/Users/sreej/Downloads/Projects/SoilSense AI/.agents/agents/{agent_name}/agent.json
  Global:    C:\Users\sreej\.gemini\antigravity-cli\agents\{agent_name}\agent.json

▼ Available Agents
  • /default   Default agent

入全景模式 出全景模式

代理之定义乃JSON,非Markdown也。Markdown存于下级——于技能:

Skills  
129 skills

Create new skills
  Workspace: ~/Downloads/Projects/SoilSense AI/.agents/skills/{skill_name}/SKILL.md
  Global:    ~/.gemini/antigravity-cli/skills/{skill_name}/SKILL.md
  Shared:    ~/.gemini/skills/{skill_name}/SKILL.md

入全屏模式 出全屏模式

故其实结构如是:

your-project/
└── .agents/
    ├── agents/
    │   └── {agent_name}/
    │       └── agent.json      ← agent behavior (JSON)
    └── skills/
        └── {skill_name}/
            └── SKILL.md        ← reusable capabilities (markdown)

入全屏模式 出全屏模式

而反重力飞船自带129内置技能已备——自agency-agentic-search-optimizeragency-code-reviewer汝非自零始,乃延库之基也。

此非小修正,乃心象迥异于讲词所寓也。


吾试之於实案

吾以之试於SoilSense AI——一Capacitor/Android之应用,其有既存之代码库,git之史迹,及一src/之目录,满贮React之组件。非演示之案,乃实案也。

一提示:

create a skill for SoilSense AI that reviews any new component 
for accessibility issues before committing

入全景模式 出全屏模式

随之而来者,非自动补全也。代理者:

  1. 阅之package.json欲通栈理
  2. 扫描src/src/lib/docs/PROJECT_STRUCTURE.md
  3. 已核验ListPermissions— 已确认读写权限
  4. git status通晓今状
  5. 拟混和之法,请先示可而后行

所拟之策:

  • 寰宇智能之能事soilsense-accessibility-reviewer)—也SKILL.md此令使代理以大语言模型之理,审 git 已暂存之件。
  • 独立之Python检核器check-a11y.py) 静态WCAG规则之执行
  • A pre-commit 之钩,阻绝含要害违者之提交

吾所书 proceed。此乃所成:

Create(~/.gemini/config/skills/soilsense-accessibility-reviewer/SKILL.md)
Create(~/.gemini/config/skills/soilsense-accessibility-reviewer/scripts/check_a11y.py)
Create(SoilSense AI/scripts/check-a11y.py)
Create(SoilSense AI/.git/hooks/pre-commit)

入全屏模式 出全屏模式

继而——未请吾意——创伪破件,含意违,暂存之,复以钩自验

果:

5 Critical issues detected:
  - Missing alt tags
  - Custom clickable divs lacking tabIndex/onKeyDown handlers  
  - Empty button
  - Unlabeled form inputs

3 Warnings:
  - Redundant alt terms
  - Positive tabIndex anti-patterns
  - Unlabelled decorative SVG/Lucide icons

→ Commit blocked. Fix critical issues or use --no-verify to bypass.

入全景模式 出全景模式

察得实违,阻其提交,显效于控制台之表,复洁伪组件,复 git 之状。预提交钩今已启于 SoilSense AI 之库.

一令足矣。无编排之码。无手撰之配置文。

此乃众人未解之要旨于I/O之覆:技能之文非惟更易代理所知,亦更易代理于汝之库所之行事


此乃藏于Antigravity 2.0公告之详Gemini CLI于六月十八日停用消费者层级.此非可择之选也.免费层级、AI Pro、AI Ultra,皆同此讯.

尔所迁者何:

Gemini CLI Antigravity CLI
Node.js运行时 Go二进制——无运行时之倚
GEMINI.md AGENTS.md / agent.json
.gemini/skills/ .agents/skills/{name}/SKILL.md
唯Gemini模型而已 双子座3.5闪存+克劳德+GPT-OSS
以聊为主 以代理统筹为先
开源 闭源软件

多模路由之议,当稍驻足焉。反重力CLI,既支Claude,复支GPT-OSS,同途而异轨——汝非囿于Gemini于CLI之层。管理代理API,专指Gemini 3.5 Flash,然于地,汝有模型之择焉。

末行者,吾思之所在也。Gemini CLI,素为开源。众Contributors万计,Forks,Extensions皆建于其上。Antigravity则闭之。Google移开发者之工具于其Monetization stack,谓之升级。此言不虚。然亦不全也.


129内置技能,实何所指

/skills 显百二十九技,吾略览之。其间数者,

  • agency-agentic-search-optimizer — 审智役能否实成于尔之域(WebMCP 之备)
  • agency-ai-data-remediation-engineer — 自愈数据之渠,用离隙之局 SLM
  • agency-autonomous-optimization-architect — 影测 API 之效,而持金之制
  • agency-codebase-onboarding-engineer — 助新工解不习之码基

此非自动补全之进益也。乃行止——即代理被唤时,其能自主行之事务也。技之簿乃指令之集。代理者,执行之主也.

吾为SoilSense AI所建之可及性审察者,今为技之百卅。其居~/.gemini/config/skills/soilsense-accessibility-reviewer/SKILL.md。是项目今后之Antigravity会话,皆可唤之。

此乃本源,非为功能。乃智能体行为之可组合单元,存于版本控制之中。


吾所持异议之处

有数事,吾未及为所热捧。

闭源之弊,实为真切。 Gemini CLI为开源,故社群可检视此工具有无权涉及其代码库之文件系统。Antigravity则非。其所设之pre-commit hook,运行代码于~/.gemini/config/skills/——此路径内容,Google于安装时掌控。个人项目,无妨。企业级应用,则需先明此代理运行时于汝代码,可为何不可为,而后方敢提交。

proceed 事甚繁。 代理请示而后行。吾未览全策,即键入 proceed 。遂于四处立檩,改 git 之钩,复行之。git commit 面对真实库。此流程之设,乃假汝细察其策。然临限压,众匠鲜能如之。此乃治权之失,非技之弊——然实为酿祸之源。

技能蔓延,易如反掌。 可及性审阅之技,寰宇通用——存乎其处。~/.gemini/config/skills/非在土壤感知之项目目录中。是故,其在,遍于反重力之会,历 于此机作业,甚便。然亦因此,致六十项全球技能互斥,调试维艰。反重力之技能优先系统(工作区→全球→共享)可解此困,然必先知其存在也。


初试(以 Windows 为例,盖余所实用也)

# Download from https://antigravity.google.com/download
# Or via winget (if available in your region)
winget install Google.AntigravityCLI

# Navigate to your project
cd "C:\Users\you\Projects\your-project"

# Launch
agy

# Inside the shell — explore what's available
/skills    # See 129 built-in skills + any you've created
/agents    # See available agents (just /default to start)

# Create your first skill with a plain English prompt
# Example: "create a skill that enforces our API response schema before any PR"

入全屏模式 出全屏模式

必先以/skills始,所求或已存于129内置之中。造技之流程(白话入文→使能建SKILL.md及辅脚本与测试),乃速成实行之径也。


真实之得

谷歌未于I/O 2026发布更优之自动补全功能。其发布者乃代理行为之运行时,且以文本文件为配置之接口。

一令以抗重 CLI,成 WCAG 无障碍审者,Python 静态析引擎,git 预提交钩,及自验之试——皆于吾所建之真 Android/Capacitor 项也。钩今已启。其将阻次无障碍违于入仓之前。

双子座3.5闪电测试,半载之内将成过时。一技能之书,于每项提交皆行团队之规,此乃相乘之效。

此平台令人叹为观止。第一百三十项技能,方为其实之所在。

若君之建首制之能——抑或为审文之则,抑或为述引之器,抑或为君之技具所专?尤欲闻若辈有得于工场之能,与普适之能共济而无碍者。