Agent Skills Hub

security-hardening

Comprehensive security audit and hardening for AI agents: credential scanning, PII protection, prompt injection defense, and workspace config optimization.

ceo-assistant

Your AI chief of staff for startups. Includes 28 commands for idea validation, financial modeling, pitch decks, market research, and CEO operational frameworks from industry benchmarks.

session-investigator

Analyze and debug fast-agent session histories, tool execution logs, and conversation timing to resolve performance bottlenecks, tool loops, and unexpected session terminations.

playwright-cli

Token-efficient CLI for browser automation, web testing, and agentic workflows using Playwright.

request-optimizer

An intelligent gateway that analyzes, scores, and routes user requests across 27 agents, 27 skills, and 14 MCPs to optimize Claude Code execution.

explain-concepts

Explains complex concepts using master teaching frameworks like Feynman, Socratic, and Cognitive Load theory to ensure deep, clear understanding.

orchestrator

Autonomous multi-agent orchestration framework for Claude Code with memory-driven workflows, parallel-first task execution, Aristotle-based deconstruction, and multi-stage quality gates.

creative-thinking-for-research

Applies cognitive science frameworks for creative thinking to generate genuinely novel research directions in computer science and AI.

paper-writing

Full-stack automated paper writing pipeline from research narrative to polished LaTeX/PDF.

ask-user-question

Implement interactive, step-by-step user input workflows within software agents using the AskUserQuestion tool for guided decision-making and configuration.

vibe-run

A deterministic orchestration engine for autonomous coding agents, managing workflow loops, state persistence, and checkpoint-based execution.

Create New Skills

A framework for creating reusable Claude Code agent skills, following best practices for directory structure, progressive disclosure, and multi-file patterns.