LLM & Agents

Use when creating, improving, or troubleshooting Claude Code slash commands. Expert guidance on command structure, arguments, frontmatter, tool permissions, and best practices for building effective custom commands.

Enterprise Mermaid diagramming skill for Claude Code using MCP Playwright

Advanced LLM jailbreaking techniques, safety mechanism bypass strategies, and constraint circumvention methods. Use for comprehensive safety testing.

Test quality inspection framework for reviewing test coverage, identifying gaps, and ensuring comprehensive validation

Create reusable agent skills that provide domain-specific expertise through progressive disclosure

Guide for creating valid hooks. This skill should be ALWAYS used when users want to create a new hook or update an existing hook that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use it everytime you need to modify anything in ".claude/hooks" folder

Quick reference for invoking the 11 CasareRPA agents. Shows agent names, capabilities, and example Task tool invocations.

Build embeddable chatbot widgets for web applications. Use when creating chat UIs, iframe embeds, or widget-based AI interfaces.

Guide for creating effective subagents (custom agents). Use when users want to create a new subagent that can be dispatched via Task tool for autonomous work. Covers frontmatter fields (name, description, tools, model, permissionMode, skills), prompt design, and when to use subagents vs skills.

Manages, consolidates, and optimizes project documentation following research-backed docs-as-code principles. Use this skill when documentation becomes scattered, duplicated, or contradictory after development work. Also use when user explicitly requests "tidy docs", "consolidate documentation", "clean up docs", or "organize documentation". Applies Diátaxis framework, enforces YAML front matter, resolves conflicts using evidence-based rules, and generates machine-readable manifest for AI agents. NEVER modifies CLAUDE.md.

Agent with comprehensive Gemini safety settings configured for all categories

Creates and configures Streamable HTTP Model Context Protocol (MCP) server connections for OpenAI Agents SDK

This skill should be used when the user asks to "plan the implementation", "break down the tasks", "explore the codebase", or as Phase 2 of the /dev workflow after brainstorming. Creates task breakdown from codebase exploration.

Use when user asks to "create a skill", "build a skill", or "design a skill". Guides through requirements, solution design, and implementation of token-efficient Claude Code skills.

Run an autonomous coding agent that builds applications from specifications. Use when asked to "build an app autonomously", "run autonomous agent", or "create application from spec".

This skill should be used when the user asks to "generate Rails code", "create a model", "create a controller", "add a migration", "write Rails tests", "set up background jobs", "configure Rails app", or discusses Rails conventions, best practices, ActiveRecord patterns, Hotwire/Stimulus, ViewComponent, RSpec testing, or Ruby on Rails development. Based on Evil Martians' AGENTS.md.

Official Anthropic SDK for Claude AI with chat, streaming, function calling, and vision capabilities. Use when integrating Claude AI into applications, implementing AI-powered features, using tool use patterns, or processing images with vision models.

This skill should be used when the user asks about "Rails testing", "RSpec", "Minitest", "request specs", "system specs", "FactoryBot", "fixtures", "test coverage", "testing controllers", "testing models", "integration tests", or needs guidance on writing effective tests for Rails 7+ applications.

Write automated tests following a pragmatic, integration-focused philosophy. Use when writing tests for new features, writing tests for bug fixes, adding test coverage, or deciding what/how to test. Emphasizes confidence over coverage, real objects over mocks, integration over isolation, and simplicity over dogma.

Build and deploy this Next.js LangChain retrieval agent application with Supabase vector store. Use when building, deploying, setting up vector store, or preparing the project for production.