Agent Skills Hub

template-nextjs-moderne

A comprehensive Next.js 15 development and project management skill for Claude Code, featuring Supabase integration, RBAC, and automated quality validation.

tldr

Token-efficient codebase analysis skill for call graphs, semantic search, impact analysis, and data flow. Saves ~95% tokens vs. raw reads.

kill-claude-mem

Kills stale claude-mem worker and MCP server processes to recover RAM and improve performance in memory-constrained environments like GitHub Codespaces.

obsidian-markdown

Create and edit Obsidian Flavored Markdown notes with wikilinks, embeds, callouts, frontmatter properties, and specialized syntax.

bmad-planner

Interactive tool for generating Business, Model, Architecture, and Design (BMAD) planning documentation for feature development.

epsimo-agent

Epsimo AI platform SDK and CLI for building agents with persistent state, Virtual Database, streaming conversations, and a React UI kit.

coding-tutor

Your personal AI coding tutor that creates customized tutorials based on your actual codebase, tracks your learning progress, and uses spaced repetition to ensure mastery.

testops-companion

An AI-powered TestOps platform and MCP server providing automated failure analysis, RCA matching, and intelligent test orchestration for CI/CD pipelines.

hf-mcp

Connect your AI agent to the Hugging Face Hub via MCP. Search models, datasets, and papers, manage repos, run cloud compute jobs, and invoke Gradio Spaces as functional AI tools.

auto-trading-strategy

Professional trading strategy and risk management toolkit for prediction markets and crypto, featuring trend analysis, position sizing, and stop-loss frameworks.

context-driven-development

Standardizes project context by managing artifacts (product, tech-stack, workflow, tracks) in a conductor/ directory. Supports project scaffolding, artifact synchronization, and AI alignment for greenfield and brownfield projects.

strategic-compact

Enhance workflow efficiency by performing manual context compaction at logical task boundaries instead of relying on unpredictable auto-compaction.