Agent Skills
PulseAugur coverage of Agent Skills — every cluster mentioning Agent Skills across labs, papers, and developer communities, ranked by signal.
- 2026-10-27 product_launch Anthropic's AI workflow standard, Agent Skills, has joined the Agentic AI Foundation to promote reuse of instructions across AI agents. source
- 2026-10-25 product_launch Anthropic donated the Agent Skills open standard to the Agentic AI Foundation. source
- 2026-10-25 partnership Anthropic donated the Agent Skills standard to the Linux Foundation's Agentic AI Foundation for neutral governance. source
- 2026-10-25 product_launch Anthropic donated the Agent Skills open standard to the Agentic AI Foundation under the Linux Foundation. source
- 2026-10-22 product_launch Anthropic open-sourced its Agent Skills format, a framework for AI add-ons. source
- 2026-08-09 product_launch Agent Skills has been launched, providing production-grade engineering capabilities for AI coding agents. source
17 day(s) with sentiment data
-
Agentic AI Foundation expands to 10 projects, raising security questions
The Agentic AI Foundation (AAIF), a Linux Foundation project, has expanded to ten projects, covering various layers of AI agent operations. While the AAIF addresses governance by consolidating projects under one umbrell…
-
Anthropic's Claude Code detailed for diverse coding workflows
Several articles detail how to use Anthropic's Claude Code, an AI coding assistant, for various development tasks. Guides cover building first applications with "vibe coding," mapping codebases with plugins like Floorpl…
-
Security flaws found in combined AI agent skills, even when individual skills are safe
A new paper published on arXiv has identified significant security vulnerabilities in agent skills, even when individual skills are marked as safe. Researchers analyzed 13,598 skills from the ClawHub marketplace and dis…
-
Anthropic donates Agent Skills to Agentic AI Foundation
Anthropic has donated its Agent Skills to the Agentic AI Foundation, which operates under the umbrella of the Linux Foundation. This move aims to foster broader development and accessibility of these AI agent capabilities.
-
Tencent Map opens agent capabilities to developers via MCP
Tencent Map has released its agent capabilities to developers, enabling them to integrate features like route planning, place search, and ride-hailing. This move is facilitated through their MCP platform, Agent Skills, …
-
AI agents to gain real-world skills for enhanced functionality
This article discusses the concept of "Agent Skills," which aims to equip AI agents with the necessary capabilities to interact effectively with the real world. It poses a question to the audience about which skill they…
-
Agent Skills: Writing effective descriptions for AI agent utilization
This article explains how to write effective descriptions for Agent Skills, which are crucial for ensuring that AI agents can correctly identify and utilize these skills. The key is to provide a clear, concise, third-pe…
-
AgentKit introduces Agent Skills for organized tool management
AgentKit has introduced a new feature called Agent Skills, which allows users to organize tools within a folder structure. Each skill includes a `skill.md` file that defines its name and description, which are loaded at…
-
Anthropic's Agent Skills standard joins Agentic AI Foundation
Anthropic's AI workflow standard, known as Agent Skills, has been adopted by the Agentic AI Foundation. This initiative aims to enable teams to reuse instructions across various AI agents, fostering greater interoperabi…
-
Anthropic donates Agent Skills standard to Linux Foundation's AAIF
Anthropic has donated its Agent Skills standard and related assets to the Agentic AI Foundation (AAIF), which is now under the Linux Foundation. This move aims to establish a neutral home for the standard, which has see…
-
Anthropic donates Agent Skills to Linux Foundation for open standard
Anthropic has donated its Agent Skills framework to the Agentic AI Foundation, a project under the Linux Foundation. This move aims to establish Agent Skills as an open standard for AI agents. The donation includes the …
-
OpenAI scales ChatGPT infrastructure, partners on AI safety, and blurs product lines · 1 source tracked
OpenAI has detailed its infrastructure scaling efforts to support billions of ChatGPT users, emphasizing architectural improvements like global caching and Azure Cosmos DB for faster data retrieval. The company is also …
-
Anthropic's Claude Code introduces efficient 'skills' for task automation
Claude Code utilizes a system of "skills" that are essentially folders containing a SKILL.md file. This file includes YAML frontmatter for defining the skill's name and description, which helps Claude determine when to …
-
Anthropic donates Agent Skills standard to Linux Foundation for neutral governance
Anthropic has donated its Agent Skills open standard to the Agentic AI Foundation, a Linux Foundation initiative. This standard allows AI agents to perform specific tasks and is supported by over 70 platforms, including…
-
Anthropic Agent Skills spec gains 26,000 GitHub stars
The Anthropic Agent Skills specification has achieved significant popularity on GitHub, reaching 26,000 stars. This specification enhances AI agents by enabling them to utilize folders and markdown files for new capabil…
-
AI agent skills for home buying emphasize transparency about limitations
A developer has created a set of AI agent skills called HousingWizard, designed to assist homebuyers with tasks like due diligence, offer negotiation, and contract review. A key principle in its design is transparency a…
-
AgentKitCo releases Claude Code subagent tool
AgentKitCo has released a new MIT-licensed tool called write-subagent within its Agent Skills repository. This tool is designed to automate the creation of Claude Code subagent files, which are used for specific, repeat…
-
Anthropic open-sources Claude add-on format used by ChatGPT
Anthropic has open-sourced its Agent Skills format, a framework for AI add-ons that is currently utilized by ChatGPT and over 70 other AI tools. This format, which enables enhanced functionality for AI models, has been …
-
China-aligned hackers use agentic AI in cyberattacks; new foundation projects launched
A China state-aligned hacking group, Storm-0940, has been observed using agentic AI to conduct cyberattacks, with one instance showing nearly 3,000 sign-in attempts per minute during a breach of ConnectWise. In parallel…
-
Open-source skills boost AI coding agents into disciplined engineers
Open-source skill collections are enhancing AI coding agents, transforming them into more disciplined engineers. Projects like Jesse Vincent's Superpowers methodology, Matt Pocock's composable engineering skills, and Ad…