Agent Skills Hub

langchain-chat-models

A unified interface for integrating and managing LLM chat providers like OpenAI, Anthropic, Google, Azure, and Bedrock within LangChain applications.

self-improve

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

milady-development

Self-modify your Milady agent by managing plugins. Edit code, rebuild, and restart the runtime to develop new capabilities or improve agent workflows locally.

security-review

A comprehensive security auditing and hardening assistant that applies best practices for authentication, input validation, secrets management, and SQL injection prevention to your codebase.

cross-plugin-detective

Standardized detective skill integration for agent roles. Maps agents to code-analysis skills and enforces claudemem usage for memory-indexed code investigation.

web-artifacts-builder

A toolkit for developing and bundling complex, multi-component React/TypeScript web artifacts using Vite, Tailwind CSS, and shadcn/ui.

audit-skills

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

claude-oracle

Automated tool and MCP server discovery for Claude Code. Searches 17+ registries to find relevant skills, plugins, and tools before planning or when errors occur.

google

Search the web for real-time information, technical documentation, or research topics using WebSearch and WebFetch tools.

regression-testing

Strategic regression testing with intelligent test selection, impact analysis, and continuous regression management for faster, more reliable software delivery.

refly

Base ecosystem skill for Refly. Creates, discovers, and runs domain-specific skills, routes user intent to workflows via symlinks, and automates multi-step pipelines via the Refly CLI.

avoid-feature-creep

A framework for software teams and AI agents to prevent feature creep, enforce scope discipline, and ship focused MVPs by applying strict validation, backlog hygiene, and clear decision-making processes.