AIAny
AI Agent2025
Icon for item

OpenSkills

Installs Claude Code-format skills into agents without native support — Cursor, Windsurf, Aider, Codex — by writing the same <available_skills> XML into their AGENTS.md. Skills stay plain files, so no MCP server is needed.

Introduction

Anthropic shipped Agent Skills as a Claude Code feature, but the format is really just folders of Markdown plus a manifest — nothing in it is actually bound to Claude. OpenSkills bets on that portability: it takes those skill folders and makes any AGENTS.md-aware agent load them, turning a single-vendor feature into a cross-tool convention.

What Sets It Apart
  • Files, not a server. Unlike MCP, which needs a running server to expose tools, skills compile into the agent's instructions as plain text. So what: zero infra to run, works offline, and the whole skill set version-controls inside your repo.
  • One source, many agents. It emits the identical <available_skills> XML block that Claude Code uses, written into AGENTS.md, so Cursor, Windsurf, Aider, and Codex all read the exact same skill catalog.
  • Stays on the official spec. It implements Anthropic's Agent Skills format rather than inventing a parallel one, so a skill authored here keeps working inside Claude Code itself instead of becoming a fork.
Who It's For

Great fit if you maintain a library of reusable agent instructions and want them to behave the same across more than one coding tool, or if you've skipped MCP purely because of the server overhead. Look elsewhere if you only ever use Claude Code — native skills already cover you — or if you need runtime tool execution and live API calls, since skills are static instruction files, not a protocol. Worth knowing: this is an independent community project, explicitly not affiliated with Anthropic, so it can trail the upstream spec when that changes.

Information

  • Websitegithub.com
  • AuthorsNumman Ali
  • Published date2025/10/26

More Items

Hugging Face
AI Model2026

Open-weights LLM fine-tuned for phone-based voice agents that prioritizes low latency and reliable tool/function calling. Based on NVIDIA Nemotron 3 Nano (30B total, 3.5B active), supports very long contexts (262,144 tokens) and recommends temperature=0 with thinking disabled for deployment.

GitHub
AI Agent2026

A curated collection of production-ready Agent Skills that turn tasks—presentation production, image generation, local KB retrieval, article assembly, and web-design—into agent-loadable skill folders. Uses a SKILL.md contract, supports multiple agent runtimes (Claude Code, Cursor, Codex), and offers modular install paths with pinned release zips.

GitHub
AI Agent2026

Provides a ruleset and skills that make AI coding agents prefer the simplest correct implementation: reuse existing code, prefer stdlib/native features, and only write minimal new code. Cuts generated LOC, tokens, cost and time while preserving validation and safety.