Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
software-testing
Software testing guidance with decision tree. Use when: (1) Writing or improving tests, (2) User asks about testing approaches, (3) Need guidance on test scope or assertions, (4) Working with specific test frameworks. Routes to specialized testing strategies via reference files.
moogah/claude_skills
-
bead-creator
Create self-contained Beads issues for work tracking. Use when creating new beads for bugs, tasks, questions, or follow-up work - whether from specifications, discovered during implementation, or standalone requests. Handles proper formatting, labeling, dependencies, and ensures beads are actionable with embedded context.
moogah/claude_skills
-
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
moogah/claude_skills
-
test-auth-helpers
Implement authentication testing patterns with RSpec, FactoryBot, and test helpers for Rails applications. Use when writing controller specs, system tests, or request specs that require authenticated users and multi-tenant account context.
rbarazi/agent-skills
-
multi-tenant-accounts
Implement multi-tenant architecture using an Account model as the tenant boundary. Use when building SaaS applications, team-based apps, or any system where data must be isolated between organizations/accounts.
rbarazi/agent-skills
-
user-management
Implement user CRUD operations within an account with permission controls and feature flags. Use when building team member management, user administration, or account user settings in multi-tenant Rails applications.
rbarazi/agent-skills
-
oauth21-provider
Implement an RFC-compliant OAuth 2.1 authorization server in Rails applications. Use when building apps that need to authorize third-party clients (like MCP clients, API consumers, or external integrations) using industry-standard OAuth flows with PKCE, dynamic client registration, and token management.
rbarazi/agent-skills
-
password-reset-flow
Implement secure password reset with Rails 8's built-in token generation. Use when building "forgot password" functionality with email verification and time-limited reset tokens.
rbarazi/agent-skills
-
code-pattern-extraction
Extract reusable design and implementation patterns from codebases into Skills. Use when asked to analyze code for patterns, document architectural decisions, create transferrable implementation guides, or extract knowledge into Skills. Transforms working implementations into comprehensive, reusable Skills that can be applied to new projects.
rbarazi/agent-skills
-
slack-mcp-server
Create MCP servers that interact with Slack APIs. Use when building agent tools for Slack canvases, posting messages, or other Slack operations via Model Context Protocol.
rbarazi/agent-skills
-
slack-work-objects
Create trackable Work Objects in Slack with link unfurling and flexpane details. Use when building agents that need persistent, interactive entities.
rbarazi/agent-skills
-
mcp-rails
Implement Model Context Protocol (MCP) in Rails applications. Use when building AI agents that need to connect to MCP servers, expose Rails apps as MCP servers, or manage MCP subprocess containers via Docker. Covers JSON-RPC transport, OAuth 2.1 PKCE authentication, SSE streaming, and multi-worker process coordination.
rbarazi/agent-skills
-
slack-blockkit-ui
Render rich Block Kit messages in Slack from AI agent tool results. Use when building agents that display formatted responses with sections, images, and buttons.
rbarazi/agent-skills
-
chatkit-frontend-bootstrap
Embed and initialize OpenAI's ChatKit widget in Rails views. Use when adding ChatKit to a page, configuring the openai-chatkit custom element via data attributes, syncing themes with dark/light mode, handling Turbo navigation, or setting up attachment uploads. Triggers on ChatKit embed, openai-chatkit element, chat widget initialization, or theme sync.
rbarazi/agent-skills
-
rails8-authentication
Implement Rails 8 built-in authentication with has_secure_password, session cookies, and the Authentication concern. Use when building login/logout functionality, session-based auth, or user authentication systems in Rails 8+ applications.
rbarazi/agent-skills
-
session-management
Implement database-backed session management with cookie handling, audit trails, and multiple device support. Use when building authentication systems that need session tracking, device management, or security audit capabilities.
rbarazi/agent-skills
-
slack-channel-integration
Build Slack as a communication channel for AI agents. Use when implementing Slack OAuth, webhooks, event processing, or creating agent-to-Slack messaging pipelines.
rbarazi/agent-skills
-
llm-gateway
Build a multi-provider LLM client abstraction layer for Rails applications. Use when integrating multiple LLM providers (OpenAI, Anthropic, Gemini, Ollama), implementing provider switching, feature-based model routing, or standardizing LLM responses across providers.
rbarazi/agent-skills
-
chatkit-rails-backend
Integrate OpenAI ChatKit with a Rails backend using SSE streaming. Use when building conversational AI with thread management, message streaming, widget rendering from MCP tool results, file attachments, and human-in-the-loop form interactions. Triggers on ChatKit, chat widget, thread streaming, or widget from tool result.
rbarazi/agent-skills
-
mcp-widget-authoring
Create ChatKit UI widgets in MCP servers. Use when building visual components that render in ChatKit from tool results. Covers widget templates with JSON Schema validation, WidgetTemplateService for hydration, BaseMCPServer patterns, and multi-channel support for Slack. Triggers on widget template, MCP widget, tool result widget, or ChatKit Card.
rbarazi/agent-skills
-
deep-research-prompt-builder
This skill should be used when the user asks to "build a research prompt", "create a deep research query", "enhance my research question", "structure a research prompt", "help me write a research prompt", or needs help transforming research topics into comprehensive prompts for product comparisons, technical documentation, academic literature, market analysis, or any domain requiring structured deep research.
lejoe/claude-plugins
-
twitter-thread-extractor
This skill should be used when the user asks to "extract this Twitter thread", "save this Twitter thread", "export Twitter thread to markdown", "archive this thread", "download this thread", or provides a Twitter/X URL requesting thread extraction, export, or archival into markdown format.
lejoe/claude-plugins
-
brainstorm
This skill should be used when the user asks to "brainstorm", "help me think through this", "explore ideas", "organize my thoughts", "work through this problem", or mentions needing help with complex thinking, decision-making, problem exploration, or wants a thinking partner for exploring challenges through Socratic questioning.
lejoe/claude-plugins
-
cc-sessions-review
This skill should be used when the user asks to "review my sessions", "analyze my chat history", "review my Claude Code usage", "find compounding opportunities", "improve my AI workflow", "session review", or wants feedback on Claude Code session patterns. Do NOT use for code review, PR review, or general conversation analysis.
lejoe/claude-plugins