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 - 【当耐特】
小众软件
小众软件
S
SegmentFault 最新的问题
GbyAI
GbyAI
量子位
爱范儿
爱范儿
L
LangChain Blog
Vercel News
Vercel News
A
About on SuperTechFans
腾讯CDC
博客园_首页
酷 壳 – CoolShell
酷 壳 – CoolShell
月光博客
月光博客
博客园 - 聂微东
Stack Overflow Blog
Stack Overflow Blog
H
Help Net Security
U
Unit 42
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
V
V2EX
V
Visual Studio Blog
美团技术团队
D
DataBreaches.Net
The GitHub Blog
The GitHub Blog
N
Netflix TechBlog - Medium

Vercel News

Vercel Open Source Program: Winter 2026 cohort How Notion Workers run untrusted code at scale with Vercel Sandbox How we run Vercel's CDN in front of Discourse From idea to secure checkout in minutes with Stripe Building Slack agents can be easy Scaling redirects to infinity on Vercel Advancing Python typing Gamma builds design-first agents with Vercel How Avalara turns pipe dreams into patent-pending with v0 Keeping community human while scaling with agents How OpenEvidence built a healthcare AI that physicians actually trust Security boundaries in agentic architectures Skills Night: 69,000+ ways agents are getting smarter Video Generation with AI Gateway We Ralph Wiggumed WebStreams to make them 10x faster How Stably ships AI testing agents in hours, not weeks How we built AEO tracking for coding agents Anyone can build agents, but it takes a platform to run them Introducing Geist Pixel The Vercel AI Accelerator is back with $6m in credits Making agent-friendly pages with content negotiation The Vercel OSS Bug Bounty program is now available Introducing the new v0 Run untrusted code with Vercel Sandbox, now generally available How Stripe built a game-changing app in a single flight with v0 How Sensay went from zero to product in six weeks AGENTS.md outperforms skills in our agent evals Agent skills explained: An FAQ Testing if "bash is all you need" AWS databases are now live on the Vercel Marketplace and v0
Use skills in your AI SDK agents via bash-tool - Vercel
Malte UblCTO, Vercel · 2026-01-21 · via Vercel News

Skills support is now available in bash-tool, so your AI SDK agents can use the skills pattern with filesystem context, Bash execution, and sandboxed runtime access.

This gives your agent a consistent way to pull in the right context for a task, using the same isolated execution model that powers filesystem-based context retrieval.

This allows giving your agent access to the wide variety of publicly available skills, or for you to write your own proprietary skills and privately use them in your agent.

import {

experimental_createSkillTool as createSkillTool,

createBashTool,

} from "bash-tool";

import { ToolLoopAgent } from "ai";

// Discover skills and get files to upload

const { skill, files, instructions } = await createSkillTool({

skillsDirectory: "./skills",

});

// Create bash tool with skill files

const { tools } = await createBashTool({

files,

extraInstructions: instructions,

});

// Use both tools with an agent

const agent = new ToolLoopAgent({

model,

tools: { skill, ...tools },

});

Example of using skills with bash-tool in an AI SDK ToolLoopAgent

Read the bash-tool changelog for background and check out createSkillTool documentation.