Agent Skills Specification

Headlines · 1

1. Nov 3
   ETF Agent Skills Architecture Separates Methods from Execution

   ETF Agent authors describe an architecture in which Skills define reusable research methods while models select and synthesize them, the Host controls capabilities and source authorization, deterministic programs handle calculations, and the Runtime manages budgets, execution, and recovery. The article also covers progressive loading, differing Skill visibility for Entry, Main, and Child agents, receipt-based verification, version governance, and a reproducible public v0.2 demo. The internal fund-research bundle and private-portfolio workflow remain vendor-described, while the public implementation supports only a narrower synthetic-guide example.

   掘金 · 人工智能 · 🔥 0

Experience and discussion from the community

Share my Agent Skills Specification experienceAsk about Agent Skills Specification

All

skills•4d Pinned

skills: A collection of self-contained Agent Skills that extend Claude with repeatable instructions for specialized tasks.

What problem it solves Specialized tasks often require organization-specific guidance, reusable workflows, and supporting resources. This repository provides examples and reference implementations that teach Claude how to complete such tasks consistently. Key features Reusable skill structure — Each skill is self-contained in a folder with a `SKILL.md` file containing the instructions and metadata…

github.comhttps://github.com/anthropics/skills