Skip to main content
Back

Anthropic unveils Claude Agent Skills for modular task automation

Google's Gemini CLI now interactive, Claude's Microsoft 365 MCP, Google's open-source edge platform, Perplexity's langua

October 17, 2025 4 min read

Hey

Welcome to AlphaSignal, the most read source of news by AI engineers and researchers.


Every day, we identify and summarize the top 1% of news, papers, models, and repos, so you’re always up to date.


Here’s today’s roundup:

Together with:

alpha_signal_image_2

Summary

Read time: 4 min 43 sec

Top News

▸ Anthropic adds Agent Skills enabling Claude to load specialized workflows

Work OS

▸ Replace fragile API keys and ship secure MCP Auth with WorkOS

Signals

▸ Google debuts interactive shell in Gemini CLI, enabling full terminal apps

▸ Anthropic integrates Claude with Microsoft 365 via new MCP connector

▸ Google unveils Coral NPU, an open-source full-stack edge AI platform

▸ Perplexity expands beyond search with interactive language learning features

▸ Microsoft integrates Copilot Voice, Vision, and Actions to Windows 11

Trending Papers

▸ One language for scalable, interpretable AI reasoning

▸ Stanford shows simple prompting boosts variety without retraining models

▸ Meta introduces ScaleRL, a recipe for predictable RL training

How To

▸ Enforce brand rules consistently with Claude

Top News

Anthropic introduces Claude Haiku 4.5, a small-scale model built for efficient coding performance

alpha_signal_image_3

Anthropic introduced Agent Skills, a new way to extend Claude’s capabilities with modular, task-specific resources. Skills are organized folders containing instructions, scripts, and files that Claude can load dynamically, making it more effective at specialized tasks like document editing, spreadsheets, or branded content creation.

Key Features

  • Contextual loading: Claude only loads a skill when relevant to a task.

  • Composable: Multiple skills can stack together for complex workflows.

  • Portable: Skills work across Claude apps, Claude Code, and API.

  • Efficient: Only the required files load, keeping Claude fast.

  • Executable: Skills can include scripts for reliable code execution.

How It Works

  • Each skill is a directory with a SKILL.md file containing metadata, instructions, and references.

  • Claude preloads metadata and loads detailed files only if needed.

  • Additional files like forms.md allow modular context, keeping core instructions lean.

  • Code bundled in skills can execute directly in Claude’s sandboxed environment for efficiency.

How To Get Started

  • Enable Skills in Claude app settings (Team/Enterprise require admin setup).

  • Use the built-in “skill-creator” to scaffold new skills.

  • Explore docs, Help Center, or cookbook examples on GitHub for customization.

Access & Availability

  • Available across Claude.ai, Claude Code, the Claude Agent SDK, and the Claude Developer Platform.

  • Included for Pro, Max, Team, and Enterprise users; Team/Enterprise require admin setup.

  • API access via the new /v1/skills endpoint with programmatic versioning and management.

  • Skills require the Code Execution Tool beta for secure script execution.

  • Explore docs, Help Center, or cookbook examples on GitHub for customization.

Try now
alpha_signal_image_4

Secure MCP Servers Easily With WorkOS Connect Authorization

The MCP Registry helps LLMs discover tools, but discovery isn’t enough. Tools need secure, delegated access and API keys don’t cut it. They’re hard to scope, break user flows, and weaken integration.


WorkOS Connect delivers a fully compliant OAuth 2.1 flow with PKCE, scopes, user consent, and secure token issuance built in.


See how you can:

  • Replace fragile API keys with secure delegated authorization

  • Comply with MCP OAuth 2.1 requirements out of the box

  • Handle redirects, user consent, and scopes automatically

  • Ship production-ready secure auth flows faster with WorkOS Connect

Start secure auth

partner with us

Signals

Google presents Gemini CLI interactive shell, keeping workflows in context without switching terminals

1,882 Likes

Anthropic expands Claude with enterprise-wide search and new Microsoft 365 MCP connector integration

1,439 Likes

Google announces Coral NPU, an open-source platform for standardized edge AI development across hardware

1,095 Likes

Perplexity launches language learning with flashcards, phrase practice, and interactive study tools

1,179 Likes

Microsoft adds wake words, Copilot Vision, and agentic Actions to enhance Windows 11 AI experiences

1087 Likes

Papers

One language for scalable, interpretable AI reasoning

1,628 Likes

The paper proposes Tensor Logic, combining symbolic reasoning with tensor operations. It reduces diverse AI methods into one formalism, suggesting a path to scalable reasoning and unified model architectures.

Stanford shows simple prompting boosts variety without retraining models

3,363 Likes

Stanford introduces Verbalized Sampling, a prompting method that bypasses alignment-driven mode collapse. It boosts diversity up to 2.1×, recovers base model variance, and improves quality without retraining or fine-tuning.

Meta introduces ScaleRL, a recipe for predictable RL training

1,123 Likes

The paper shows not all RL recipes scale equally. Meta presents a systematic RL scaling study over 400,000 GPU-hours. They fit compute-performance curves, analyze design choices, and propose ScaleRL, a recipe that predicts and improves large-scale RL for LLMs.

How To

Enforce Brand Rules Consistently with Claude

alpha_signal_image_5

You don’t want to repeat your brand rules in prompts every time. A Skill packages your brand colors, fonts, logo usage, and tone so Claude applies them automatically when generating external-facing content.


Step 1
Create a folder named Brand-Guidelines and add a Skill.md file inside it.


Step 2
Add YAML frontmatter to Skill.md:


---
name: Brand Guidelines
description: Apply official colors, fonts, logos, and tone
version: 1.0.0
---

Step 3

Write clear instructions in Skill.md covering typography (fonts/sizes), logo usage (spacing/placement), tone/voice, and when to apply the rules.


Example section:


## Instructions  
- Use color #FF6B35 for primary headings, #004E89 for accents  
- Headers: Montserrat Bold, Body: Open Sans Regular
- Always include 0.5 inch clear space around the logo
- Use formal but approachable tone in external docs

## Example  
Input: “Draft external partner proposal slide”
Output: Slide with brand colors, correct typography,
logo in corner, tone aligned with guidelines.

Step 4
Put assets in a resources/ subfolder (logos, fonts, templates) and reference them from Skill.md.


Step 5
Zip the folder so the archive root contains Brand-Guidelines/Skill.md and resources/ if present.

Step 6
In Claude, open Settings → Capabilities → Skills and upload the ZIP, then enable the skill.

Learn more

At Alpha Signal, our mission is to build a sharp, engaged community focused on AI, machine learning, and cutting-edge language models, helping over 200,000 developers stay informed and ahead. We’re passionate about curating the best in AI, from top research and trending technical blogs to expert insights and tailored job opportunities. We keep you connected to the breakthroughs and discussions that matter, so you can stay in the loop without endless searching. We also work closely with partners who value the future of AI, including employers and advertisers who want to reach an audience as passionate about AI as we are.


Our partnerships are based on shared values of ethics, responsibility, and a commitment to building a better world through technology.Privacy is a priority at Alpha Signal. Our Privacy Policy clearly explains how we collect, store, and use your personal and non-personal information. By using our website, you accept these terms, which you can review on our website. This policy applies across all Alpha Signal pages, outlining your rights and how to contact us if you want to adjust the use of your information. We’re based in the United States. By using our site, you agree to be governed by U.S. laws.

Looking to promote your company, product, service, or event to 250,000+ AI developers?

Work with us