New Gemini Skills Update Is WILD!
Google has launched Gemini Skills, a new feature allowing users to save custom instructions once and reuse them repeatedly by typing a slash command, replacing the discontinued Gems feature. Skills can include reference files, be combined together, and are built on an open file format (skill.md) that allows portability across different AI tools.
Summary
Julian Goldie presents a comprehensive overview of Google's new Gemini Skills update announced on September 30th, now available to all Gemini chat users including free tier users. Unlike the previous Gems feature that required a Google AI plan and existed only in Gemini Spark, Skills are integrated directly into regular Gemini chat.
The core functionality involves typing a slash, selecting "add skill," naming the skill, writing steps in a recipe-card format (numbered steps rather than paragraphs), and saving for repeated use. The speaker recommends structuring instructions clearly with "Step one, Step two, Step three" for better AI comprehension.
Six major skill opportunities are outlined: (1) Save Once, Use Always—creating reusable skills for repetitive tasks; (2) Skills can contain reference files (PDFs, documents, images) that Gemini accesses each time the skill triggers, enabling consistent brand voice without repeated uploads; (3) Skills can be combined within a single conversation without copying and pasting between separate spaces, functioning like LEGO pieces; (4) Chrome integration allowing skills to read and process the current webpage or multiple tabs simultaneously; (5) Gemini's emerging ability to automatically suggest creating skills based on repeated user patterns and generate skill recommendations contextually; (6) Skills use the open file format skill.md, making them portable between different AI tools like Claude, distinguishing them from Gems which were proprietary.
The speaker emphasizes that skill.md format means instructions can be transferred between tools, comparing it to a portable recipe card versus engraved kitchen walls. Practical examples include creating a "/welcome" skill for community onboarding, a "/boardroom letter" skill with attached brand voice PDFs, and combining "/brand voice" with "/YouTube description" skills for consistent output.
The transcript promotes two educational offerings: AI Profit Boardroom (paid, with 30-day skill development plan and four weekly coaching sessions) and AI Success Lab (free community with daily trainings and ready-made prompts). The speaker notes that Gems are being discontinued, creating urgency for users to migrate their work, with specific deadline information mentioned but not fully detailed in the transcript.
Key Insights
- Google announced on September 30th that Skills are now available to all Gemini chat users worldwide, including free users, whereas previously Skills only existed in Gemini Spark and required a Google AI plan
- Skills use the open file format skill.md, which is the same format other AI tools like Claude use for their skills, allowing users to create, modify, and transfer instructions between different tools rather than being locked into one platform
- Gemini can analyze user chat history and learn to automatically suggest creating skills based on repeated patterns, and can launch relevant skills proactively when users type related queries without explicit instructions
- Skills can be combined within a single conversation and switched between without copying and pasting responses between separate spaces, functioning as modular components like LEGO pieces where each small skill handles one task
- Skills created in the Gemini app currently do not sync with Workspace apps like Docs or Gmail, requiring users to create the same skill separately in each location if they want it available across platforms
Topics
Transcript
[0:00] The new Gemini skill update is simply amazing. Google just added Gemini skills. You save your instructions once, then type a slash, select a skill, and Gemini performs it over and over again as many times as you want. And on the same day, Google announced that Gems were disappearing. So, if you were creating Gems, time is running out. I'll let you know the exact dates a little later, because one of them is next month. Here is a simplified version. Most of us type the same long queries over and over again. Write it in my style. Make it short. Use these three points every time. [0:30] Skills solve that. You write the steps once, give it…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Julian Goldie SEO
Google AI Studio Just Got A Huge Security Upgrade
Google is reportedly developing a new "Security Check" mode for AI Studio that would apply secure coding practices to AI-generated applications. The feature aims to automate security verification during app development, addressing common vulnerabilities like exposed keys, weak authentication, and data access issues before deployment.
NEW Codex CLI Update Is ABSURD!
OpenAI's new Codex CLI update transforms terminal-based programming assistance by enabling multiple AI agents to work simultaneously on different tasks, visible in a full-screen control center interface. The update includes features like Agent View, work trees, voice control, and parallel task execution, fundamentally changing how AI assistance operates from sequential Q&A to autonomous team-based work management.
NEW Hermes Cloud + Agent OS is Crazy! 🤯
Hermes Cloud combined with Agent OS enables users to deploy AI agents in the cloud 24/7 using free models without API keys or local setup complexity. The system provides persistent memory, sandbox isolation, and integration with custom workflows like content research, competitor analysis, and news monitoring.
Manus 2.0 Just Changed AI Agents Forever
Manas 2.0 represents a fundamental architectural overhaul that enables users to create games, websites, videos, and automations through simple text requests, with the key innovation being editable components rather than fixed outputs. The platform uses a new Cascade engine that reduces token usage by 23% and improves task speed by 28%, while maintaining all project elements in one connected workspace.
How to Run DeepSeek V4 Flash for FREE!
A tutorial demonstrating how to use DeepSeek V4 Flash for free through Open Code and integration with agent operating systems like Hermes Agent. The speaker showcases building websites and apps using this free AI model and explains how it compares favorably to larger models despite being smaller.