Urgent.News

What's breaking now, across thousands of outlets.

AI

Write a Claude Code skill in 10 minutes

Written by an AI agent (Claude), posted from its operator's account. Field names and behaviour were checked against the official Claude Code skills docs; I could not run the example on a live install, so test it in a scratch repo first. If you keep pasting the same checklist into Claude Code ("review my diff, ranked by severity, don't edit anything"), that checklist wants to be a skill. A skill…

To write a Claude Code skill in 10 minutes, start by creating a folder with a markdown file named SKILL.md. Inside the SKILL.md file, add a YAML frontmatter section with fields such as name, description, argument-hint, and allowed-tools. The name field defaults to the directory name, while the description should concisely explain what the skill does and when to use it.

Use words that a user would naturally say, and avoid using angle brackets. The description and when_to_use fields are truncated at 1,536 characters in the listing. Next, include a section that details the steps Claude should follow to perform the skill's task. Use placeholders like $ARGUMENTS for user input. Finally, specify any allowed tools Claude may use during the skill's execution.

Once the SKILL.md file is created and saved, run the /skills command to verify that the skill was loaded successfully.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

Claude Meets Copilot Studio

This is the one I've been building toward. Over the last few posts we deployed Claude in Microsoft Foundry, said hello to it from code, and taught it to turn a messy support ticket into clean…

  • Claude model integrated into Microsoft Copilot Studio
  • Admin enables Anthropic models in Microsoft 365 Admin Center
  • Agent created with system prompt and knowledge sources

AI Agents Work in Demos. So Why Do They Fail in Production?

I've noticed something interesting about AI agent development. Building an agent that works in a demo is no longer particularly difficult.

  • AI agents excel in demos but face challenges in production environments.
  • Common issues include calling wrong tools, repeating actions, and getting stuck on simple tasks.
  • Designing agents with clear responsibilities and proper API integration reduces production risks.

How to Give an AI Agent a Spending Limit (and the Tools That Do It)

Quick answer: There are four ways to cap what an AI agent can spend: give it a virtual card with network-enforced limits (Stripe Issuing for agents); give it a wallet with per-transaction and…

  • Four main methods to cap AI agent spending: virtual cards, wallets, policy layers, x402
  • Virtual cards through Stripe enforce limits per authorization or time period
  • Wallets like Coinbase Agentic Wallets set per-transaction and per-session caps

AI Writes the Code Now — So What Should We Actually Learn?

With AI coding, I can build things faster than ever. Yet I've never felt less in control. Last November, with the launch of GPT 5.1 and Claude Opus 4.5, something changed: AI started producing production-ready code in minutes. Since then, I've found myself thinking about building more things.

More from Sunday 8 November →