Chrome Skills: Save and Reuse AI Prompts as One-Click Tools

Google has launched Skills in Chrome, a feature that allows users to save and reuse AI prompts as one-click tools directly in the browser. This addresses the repetitive task of re-entering the same prompts across different webpages.
How Skills Work
When you write a prompt you want to reuse, you can save it as a Skill directly from your chat history. To run a saved Skill, select it in Gemini in Chrome by typing forward slash (/) or clicking the plus sign (+) button. The Skill will execute on the currently viewed page and any other selected tabs.
Practical Use Cases
Early testers have used Skills for various tasks including:
- Health & Wellness: Quickly calculating protein macros for recipes
- Shopping: Generating side-by-side spec comparisons across multiple tabs
- Productivity: Scanning lengthy documents for important information
Skills Library and Customization
Google is launching a library of ready-to-use Skills for common tasks. Examples include breaking down product ingredients online or selecting gifts by cross-referencing budget with recipient interests. Users can add these Skills and customize them by editing the prompts.
Security and Availability
Skills utilize Chrome's security and privacy safeguards, including confirmation prompts for actions like adding calendar events or sending emails. They benefit from Chrome's layered protections including automated red-teaming and auto-update capabilities.
Skills are rolling out to Gemini in Chrome on Mac, Windows, and ChromeOS for users with Chrome language set to English-US. Saved Skills are available on any signed-in Chrome desktop device and can be managed by typing forward slash (/) in Gemini in Chrome and clicking the compass icon.
📖 Read the full source: HN AI Agents
👀 See Also

WebClaw: Open-Source MCP Server for Web Extraction with Claude
WebClaw is an open-source MCP server built with Claude Code that provides web extraction tools for Claude Desktop and Claude Code, solving Claude's built-in web_fetch limitations with TLS fingerprinting and content optimization.

Logseq Brain v0.6.0: Persistent Memory Plugin for Claude Code Adds Journey Log and Section-Targeted Reads
Logseq Brain v0.6.0 adds a journey log for all operations, section-targeted reads for token savings, and progressive disclosure for skill files.

Atelier v0.3 adds targeted markdown revisions with Claude Code
Atelier v0.3 is a free VS Code extension that lets you highlight sections of markdown documents and send them to Claude Code for revisions. The agent responds with targeted edits in the editor, and you can track which feedback each revision addresses.

Hypura: Storage-tier-aware LLM inference scheduler for Apple Silicon
Hypura is a Rust-based inference scheduler that places model tensors across GPU, RAM, and NVMe tiers to run models exceeding physical memory on Apple Silicon Macs. It enables running a 31GB Mixtral 8x7B on a 32GB Mac Mini at 2.2 tok/s and a 40GB Llama 70B at 0.3 tok/s where vanilla llama.cpp crashes.