Agent Skills Hub

spec-metadata

Generates standardized metadata, including git/jj version info and timestamps, for research docs, handoffs, and implementation plans.

migrate-to-vinext

Automated migration tool for converting Next.js projects to vinext (Vite-based Next.js reimplementation), including compatibility scanning, dependency replacement, and configuration setup.

code-review-netsync

Automated code review for STYLY-NetSync, enforcing protocol parity, thread safety, and Unity C#/Python conventions.

ordercli

A command-line interface for managing food delivery orders, currently supporting Foodora with Deliveroo integration in development.

home-assistant-master

Home Assistant OS (HAOS) operations skill for agents. Features read-only diagnostics, automation design, health auditing, and safety-first configuration management.

session-logs

Search, analyze, and audit GeminiClaw session logs and memory. Use to investigate past interactions, track token usage, debug tool calls, and monitor agent performance.

ziwei-iztro-reader

Ziwei Doushu charting and layered interpretation engine. Analyzes natal, yearly, monthly, and daily horoscopes using structured data, offering systematic, evidence-based astrological insights.

token-surgeon

Audit and optimize your AI prompts with Token Surgeon. Detect 10 common waste patterns, calculate efficiency, and reduce token usage for better prompt performance.

kids-book-writer

Expert children's book writer for ages 2-9. Crafts rhyming stories, songs, and educational content with perfect rhythm, age-appropriate vocabulary, and engaging moral lessons.

smithery-ai-cli

Find, connect, and use over 100,000 MCP tools and skills via the Smithery CLI to integrate external services, manage agent workspaces, and automate workflows.

manimgl-best-practices

Best practices and code patterns for ManimGL (3Blue1Brown's OpenGL animation engine). Provides templates, rules for 3D/interactive scenes, camera control, and LaTeX math visualization for technical creators.

prompt-improver

Enriches vague prompts by performing codebase research and asking targeted questions to clarify user intent before execution.