Google's Developer Relations team published a suite of Agent Skills for Google products on GitHub and outlined five rules for designing trustworthy AI evaluations. The rules emphasize understanding th…
Red5, Agora, and Bitmovin offer public AI agent skill packages that give AI coding assistants structured context and guardrails for building live streaming applications, with Red5's skills covering Re…
SlideOps, a new tool from developer glukicov, generates slide decks from a repository's code and flags when the slides drift from the code, treating documentation as a build artifact. It works as a pa…
A developer has published an open-source tutorial demonstrating how to build an AI agent skill that combines a SKILL.md file with Python scripts for validation. The tutorial, available on GitHub, show…
Warp, the AI-powered terminal and agentic development environment, has devised a self-improvement loop for its agents using Claude's Agent Skills, turning stateless user feedback into continuous refin…
Anthropic's Claude developer platform now offers multiple agent extension layers—Agent Skills, tool use, MCP connectors, browser use, and Files API—each serving distinct purposes, and developers must …
A new engineering paper argues that not every missing agent capability requires a Model Context Protocol (MCP) server, proposing a 'minimum sufficient integration principle' that favors the least comp…
Mozilla's Octonous platform now supports Agent Skills, a reusable library for storing instructions and context in Markdown files that can be shared across workspaces and attached to automations. The f…
A developer has released a Claude skill that lets coding agents like Grok Bot, Cursor Agent, Claude Code, and Codex orchestrate one another as one-shot subagents, enabling a parent agent to outsource …
GitX, a portable Git workflow skill for AI coding agents, turns working-tree changes into logical Conventional Commits and handles branches, project checks, safe pull and push workflows, GitHub pull r…
A new open catalogue, low-level-skills-trothbyte on GitHub, documents 55+ failures of AI coding agents in assembly, Rust, concurrency, and systems code, backed by independent research, but its propose…
Amazon, Cursor, Microsoft, OpenAI, and Vercel have launched Agent Plugins, an open, vendor-neutral standard for packaging reusable components into portable plugins for AI agents. Version 1.0.0 defines…
Firebase's Agent Skills library raised a coding agent's task pass rate from 31.7% to 78.0% in the company's own evaluations, according to an Aug 11 blog post by product manager Charlotte Liang. The ga…
Anthropic's Claude Developer Platform brought five capabilities to general availability on August 19, 2026: computer use, browser use, the Files API, Agent Skills with the Skills API, and Admin API us…
Bionic, an AI agent platform, now supports creating, installing, and using agent skills in the industry-standard Agent Skills (SKILL.md) format, allowing users to capture reusable knowledge and tasks.…
Prathak Malik released v0.2 of the agent-standards-as-code kit, which syncs AI coding standards across Cursor, Claude Code, Copilot, and Codex on both macOS and Windows. The kit uses the Agent Skills …
A major Canadian freight railroad spanning roughly 20,000 route miles and moving over C$250 billion in goods annually used Databricks' Genie Code, Unity Catalog, custom Agent Skills, and a Streamlit a…
A product manager's guide to organizing Claude Code, created by Adam Faik, went viral on Hacker News, arguing that results with AI agents depend more on file organization than prompting. The guide, wh…
Cohere Health, a clinical intelligence company, built Cohere Policy Studio using Amazon Bedrock AgentCore to digitize clinical policies into structured, machine-readable data, addressing the manual pr…
Amazon Web Services (AWS) introduced a suite of six Agent Skills for Amazon Bedrock Automated Reasoning checks, enabling coding agents to build, test, deploy, and validate policies end to end. The ski…