Agent Skills Hub

visual-creative

AI-powered creative visual prompt generator for posters, banners, product shots, and social media content.

start

Initiates automated reverse engineering by discovering codebase architecture, layers, and technology stacks to facilitate system modernization or documentation.

ciso-assistant-bootstrap

Bootstrap CISO Assistant environments by guiding users through organizational structure setup, framework selection, and initial risk assessment configuration using MCP tools.

audit-skills

Audit AI skills for security vulnerabilities including prompt injection, hidden instructions, tool misuse, and data exfiltration risks.

design-md

Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files to serve as a source of truth for AI-driven UI generation.

skill-developer

Create and manage Claude Code skills using Anthropic best practices: triggers, hooks, and progressive disclosure.

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.

gh-ticket

Create and update comprehensive GitHub issues with full technical context to prevent requirement loss and reduce implementation friction.

context-fundamentals

Foundational guidelines for context engineering: optimizing token budgets, attention mechanics, and system architecture for AI agents.

style-format

Style template specification for AI-driven visual generation, defining artistic direction through standardized markdown templates.

cmux

Control macOS cmux terminal topology, workspaces, and pane layouts via CLI. Ideal for AI coding agents requiring deterministic multi-pane navigation, surface routing, and attention cues.

agent-system

Implementation patterns for MERIDIAN autonomous AI agents using Claude API, including BaseAgent lifecycle, structured tool use, token budget enforcement, and cron scheduling.