drinks-sommelier – I created an open-source skill that turns any AI agent into a personal sommelier
Summary
An open-source skill that turns any AI agent into a personal sommelier, allowing users to get drink recommendations based on taste preferences and food pairings, with local privacy and no external dependencies.
Similar Articles
Leonxlnx/taste-skill
Taste Skill is an open-source framework of portable Agent Skills that upgrade AI-built interfaces with stronger layout, typography, motion, and spacing, targeting tools like Codex, Cursor, and Claude Code.
@oliviscusAI: MICROSOFT JUST OPEN-SOURCED SELF-EVOLVING AGENT SKILLS. it's called skillopt. skills that improve themselves the same w…
Microsoft open-sourced SkillOpt, a tool that enables AI agent skills to self-improve by automatically evaluating and rewriting their instructions, outperforming hand-crafted prompts and other optimizers with no model lock-in.
@tom_doerr: Searches local databases and the web to surface expert best practices for building AI agent skills. https://github.com/…
Skill-from-masters is an open-source tool that searches local databases and the web to surface expert best practices before generating AI agent skills, helping users incorporate proven methodologies from domain experts.
How I built an open-source skill that forces AI agents into principal-architect mode
A developer describes creating an open-source skill that forces AI agents to adopt a principal-architect mode, enhancing their reasoning and design capabilities.
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
This paper presents COLLEAGUE.SKILL, an open-source system for automatically distilling person-grounded AI skills from heterogeneous traces into inspectable, correctable, and portable skill packages, enabling LLM agents to carry bounded representations of human expertise and interaction style.