Claude Got Skills banner
liam-jons liam-jons

Claude Got Skills

Development community

Description

Claude Code plugins and skills — capabilities awareness and multi-agent codebase review

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

claude-got-skills

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) [![Claude Code](https://img.shields.io/badge/Claude_Code-plugins-blueviolet)]() [![GitHub last commit](https://img.shields.io/github/last-commit/liam-jons/claude-got-skills)]()

Plugins and skills for Claude Code that extend what Claude can do — from keeping its knowledge current to running full codebase quality reviews.

Quick install

/plugin marketplace add liam-jons/claude-got-skills

Then install whichever plugins you need:

Plugin What it does Install
Assistant Capabilities Keeps Claude's knowledge of its own features accurate and current across all platforms /plugin install claude-got-skills@assistant-capabilities
Codebase Review Multi-agent codebase quality review with parallel analysis and adversarial verification /plugin install claude-got-skills@codebase-review

Skills can also be installed standalone via [skills.sh](https://skills.sh):

npx skills add liam-jons/claude-got-skills --skill assistant-capabilities

Assistant Capabilities

Claude's training data has a cutoff. New features ship faster than training data updates. This plugin ensures Claude has accurate, current knowledge of its own capabilities — models, pricing, API features, extension patterns, platform availability, and more.

**How it works:** A two-tier architecture injects a condensed reference (~90 lines) into every session via a SessionStart hook, with a full on-demand skill (2,700+ lines across 6 reference files) loaded when deeper detail is needed.

**Evaluated results:** Tested against a baseline (no skill) across 43 prompts using Haiku 4.5. The always-on tier delivers +80-167% accuracy lift across categories; the full skill delivers +75-500% lift.

Category Baseline With Plugin Lift
Architecture Decisions 1.67 3.33 +100%