Agent Skills Hub

claude

Anthropic Claude AI models for high-performance coding, large-context analysis, and GUI interaction.

self-improve

Self-maintaining skill for OpenCode agents to update documentation, capture learnings, and extend tool/agent capabilities dynamically.

Damage Control

Defense-in-depth protection for Claude Code. Manage security hooks to block dangerous commands, enforce file access controls, and protect sensitive paths across global or project-specific scopes.

vscode-playwright

Automated high-quality VS Code screenshot capture using Playwright and serve-web for documentation, slide decks, and visual technical content.

planning-with-files

Implements Manus-style persistent markdown planning for complex workflows, project tracking, and research management to optimize agent attention and memory.

github

Manage GitHub workflows, issues, and pull requests directly from your terminal using the gh CLI within OpenClaw.

skill-reinforcement

An automated meta-learning skill that improves agent workflows by capturing patterns, failures, and shortcuts after each task execution.

phone-agent-skill

Automate Android device operations using AI AutoGLM Phone Agent. Enables natural language control for app testing, data collection, and UI interactions like tapping, scrolling, and inputting text.

youtube-transcribe-skill

Extract YouTube video subtitles or transcripts directly into local text files using yt-dlp or browser automation.

rds

AWS RDS management for provisioning, scaling, and operational maintenance of managed relational databases including MySQL, PostgreSQL, and Aurora.

proactive-agent

Transform AI agents into proactive partners using WAL Protocol, persistent memory buffers, and autonomous cron scheduling to anticipate needs and improve performance.