Gemini CLI Weekly Update [v0.26.0]: Skills, Hooks and the ability to take a step back with /rewind

[srithreepo]

Here is Gemini CLI’s January 26th weekly update for v0.26.0

• 🧩Skills: Introducing Agent Skills that allow you to extend Gemini CLI with specialized expertise, procedural workflows, and task-specific resources. (vid, pr by NTaylorMullen)
  • Introduced the built-in skill-creator for generating tools
  • added security consent prompts to ensure safer, easier management of agent capabilities.
• 🪝 Hooks: Now officially enabled by default, hooks provide a way to fully control and customize the agentic loop. (gif, work by @Edilmo and @abhipatel12)
  • Learn how to tailor Gemini CLI to your workflow with hooks
• 🎉 Gemini CLI Extensions:
  • Supabase
    • Connect AI assistants directly to Supabase projects to manage tables, run migrations, and query data seamlessly without context switching. gemini extensions install https://github.com/supabase-community/supabase-mcp
• ⏪ New /rewind Command: Implemented the /rewind slash command, including a confirmation dialog and a new viewer component for navigating past states. If something goes wrong you now have the ability to revert both history and changes to a previous point in time. (pr by @Adib234)
• Persistent "Always Allow" Policies: Users can now save "Always Allow" decisions for tool executions, with granular control over specific shell commands and multi-cloud platform tools. (pr by @allenhutchison)
• Folder Trust:
  • Opening Gemini CLI in a folder for the first time will now surface a trust dialog (pr by @shrutip90)
  • Enable or disable checking folder trust holistically with folderTrust in your settings.json. (docs, pr by @shrutip90)
• Small features, Polish, Reliability & Bug Fixes: A large amount of changes, smaller features, UI updates, reliability and bug fixes + general polish made it in this week!

[aniruddhaadak80]

From my point of view, this release is where the product starts moving from a single assistant into a configurable execution environment, and that makes the safety model much more important than the feature list alone. Hooks, skills, and rewind all expand user power, but they also expand the number of ways a session can diverge from defaults. A short note on recommended usage patterns for teams versus solo workflows would make a release like this easier to adopt responsibly.