Ongoing

Skill Sommelier: Claude Code Plugin

AI Engineer·2026·1 person·2 min read·Updated ·github.com (opens in new tab)

A curated plugin that discovers, manages, and distributes Claude Code skills from GitHub.

Claude CodeClaude Code Plugin MarketplaceGitHub ActionsSKILL.md (Agent Skills Specification)

Overview

A personalized self-improving Claude Code skills manager. Discovers skills from GitHub, ranks them to your profile, and uses its own skills to validate, optimize, and evolve the collection.

Problem

Finding quality Claude Code skills across GitHub is manual and time-consuming, and it is difficult to tell which skills are good and which are not.

Approach

Built a Claude Code plugin repository. It includes meta-skills for personalized skill discovery, automated skill creation and consolidation, and ongoing tuning and optimization.

Constraints

  • No application code, purely text-driven

Key Decisions

Pure text architecture

For fun, and explore alternatives way of `coding` in a low risk environment.

Alternatives:Script-based plugin with CLI commandsMCP server integration

Self-evolving meta-skills

Including skills that discover, craft, and update other skills creates a self-improving ecosystem without manual curation.

Claude Code plugin marketplace distribution

The marketplace provides a standard install path, making adoption frictionless for Claude Code users.

Alternatives:Manual git clone installation

Benchmark-driven skill tuning inspired by karpathy/autoresearch

Manual prompt tuning is guesswork. A fixed-evaluation iterative loop turns skill quality into a measurable optimization problem.

Alternatives:Manual A/B testing of skill variantsUser feedback-driven iteration

Result & Impact

Streamlined my own Claude Code workflow by providing reusable skills for common tasks like Python project setup, slide creation, and repository simplification.

Learnings

  • A text-only architecture can be surprisingly powerful when the consumer is an LLM.
  • Meta-skills that improve the skill collection itself create a compelling self-evolving loop.
  • Borrowing the fixed-eval iterative loop from ML training (à la autoresearch) works surprisingly well for prompt optimization.