Agent Skills Hub

agent-canvas

Orchestrate visual communication by drawing diagrams, flowcharts, and annotations on a TLDraw canvas via CLI. Ideal for architectural planning, PR reviews, and logging agent output.

karpathy-guidelines

Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.

backend-core

Language-agnostic backend architectural patterns covering API design, authentication, security protocols, and database modeling.

risk-based-testing

Focus testing effort on highest-risk areas using risk assessment and prioritization. Use when planning test strategy, allocating resources, or making coverage decisions.

overview

Foundational mental model and operational rules for using TraceMem to ensure secure, auditable, and compliant AI agent execution.

tasks-documentation

A specialized skill for generating high-quality technical documentation, code comments, API specs, and README patterns. Automates standard documentation workflows for C# and TypeScript projects.

clawhub

ClawHub is the official registry and CLI tool for managing OpenClaw AI agent skills. Search, install, version-control, and publish custom skills to your local OpenClaw workspace.

monitor

Automated PR CI monitoring and failure resolution agent.

claude-md-enhancer

Automated toolkit for creating, maintaining, and enhancing CLAUDE.md files to ensure your project's AI-assisted development guidelines are always accurate, modular, and best-practice compliant.

jlens-mcp

Expert-level Java codebase analysis and Maven dependency management skill. Enables deep bytecode inspection, multi-version dependency conflict resolution, and automated project building via MCP integration.

draw-io

Specialized skill for creating, editing, and maintaining .drawio diagrams. Supports XML manipulation, layout optimization, AWS icon usage, and automated PNG conversion for documentation.

npm

Automate non-interactive npm package installations by piping shell confirmations to bypass prompts.