Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
README - Prompt - OpenSmartRoute
Promptv1.0.0
README
A comprehensive collection of production-ready slash commands for [Claude Code](https://docs.anthropic.com/en/docs/claude-code) that provides intelligent automation and multi-agent orchestration capab
Prompt file imported from yangjrun/novellus (.claude/commands/README.md). Fill in {{arguments}} before use. Copyright stays with the author.
Claude Code Slash Commands
A comprehensive collection of production-ready slash commands for Claude Code that provides intelligent automation and multi-agent orchestration capabilities for modern software development.
Overview
This repository provides 56 production-ready slash commands (15 workflows, 41 tools) that extend Claude Code's capabilities through:
Workflows: Multi-agent orchestration systems that coordinate complex, multi-step operations across different domains
Tools: Specialized single-purpose utilities for focused development tasks
# Navigate to Claude configuration directorycd ~/.claude# Clone the commands repositorygit clone https://github.com/wshobson/commands.git# Clone the agents repository (required for workflow execution)git clone https://github.com/wshobson/agents.git
Command Invocation
Commands are organized in tools/ and workflows/ directories and invoked using directory prefixes:
# Workflow invocation/workflows:feature-development implement OAuth2 authentication# Tool invocation/tools:security-scan perform vulnerability assessment# Multiple argument example/tools:api-scaffold create user management endpoints with RBAC
Alternative Setup (No Prefixes)
To invoke commands without directory prefixes, copy files to the root directory:
cp tools/*.md .cp workflows/*.md .# Then invoke directly/api-scaffold create REST endpoints/feature-development implement payment system
Command Architecture
Workflows (15 commands)
Workflows implement multi-agent orchestration patterns for complex, cross-domain tasks. Each workflow analyzes requirements, delegates to specialized agents, and coordinates execution across multiple subsystems.
Diagnostics, root cause analysis, hotfix deployment
Tools (41 commands)
Tools provide focused, single-purpose utilities for specific development operations. Each tool is optimized for its domain with production-ready implementations.
# Complete feature with multi-agent orchestration/workflows:feature-development OAuth2 authentication with JWT tokens# API-first development/tools:api-scaffold REST endpoints for user management with RBAC# Test-driven approach/workflows:tdd-cycle shopping cart with discount calculation logic
Debugging and Performance
# Intelligent issue resolution/workflows:smart-fix high memory consumption in production workers# Targeted error analysis/tools:error-trace investigate Redis connection timeouts# Performance optimization/workflows:performance-optimization optimize database query performance
Security and Compliance
# Security assessment/tools:security-scan OWASP Top 10 vulnerability scan# Compliance verification/tools:compliance-check GDPR data handling requirements# Security hardening workflow/workflows:security-hardening implement zero-trust architecture
Test-Driven Development
Standard TDD Flow
# Complete TDD cycle with orchestration/workflows:tdd-cycle payment processing with Stripe integration# Manual TDD phases for granular control/tools:tdd-red create failing tests for order validation/tools:tdd-green implement minimal order validation logic/tools:tdd-refactor optimize validation performance
Command Composition Strategies
Sequential Execution Pattern
# Feature implementation pipeline/workflows:feature-development real-time notifications with WebSockets/tools:security-scan WebSocket implementation vulnerabilities/workflows:performance-optimization WebSocket connection handling/tools:deploy-checklist notification service deployment requirements/tools:k8s-manifest WebSocket service with session affinity
Modernization Pipeline
# Legacy system upgrade/workflows:legacy-modernize migrate monolith to microservices/tools:deps-audit check dependency vulnerabilities/tools:deps-upgrade update to latest stable versions/tools:refactor-clean remove deprecated patterns/tools:test-harness generate comprehensive test coverage/tools:docker-optimize create optimized container images/tools:k8s-manifest deploy with rolling update strategy
Command Selection Guidelines
Workflow vs Tool Decision Matrix
Criteria
Use Workflows
Use Tools
Problem Complexity
Multi-domain, cross-cutting concerns
Single domain, focused scope
Solution Clarity
Exploratory, undefined approach
Clear implementation path
Agent Coordination
Multiple specialists required
Single expertise sufficient
Implementation Scope
End-to-end features
Specific components
Control Level
Automated orchestration preferred
Manual control required
Workflow Selection Examples
Requirement
Recommended Workflow
Rationale
"Build complete authentication system"
/workflows:feature-development
Multi-tier implementation required
"Debug production performance issues"
/workflows:smart-fix
Unknown root cause, needs analysis
"Modernize legacy application"
/workflows:legacy-modernize
Complex refactoring across stack
"Implement ML-powered feature"
/workflows:data-driven-feature
Requires data science expertise
Tool Selection Examples
Task
Recommended Tool
Output
"Generate Kubernetes configs"
/tools:k8s-manifest
YAML manifests with best practices
"Audit security vulnerabilities"
/tools:security-scan
Vulnerability report with fixes
"Create API documentation"
/tools:doc-generate
OpenAPI/Swagger specifications
"Optimize Docker images"
/tools:docker-optimize
Multi-stage Dockerfile
Execution Best Practices
Context Optimization
Technology Stack Specification: Include framework versions, database systems, deployment targets
Contributions: Pull requests welcome following the development guidelines
Questions: Open a discussion in the repository
Installed into a catalogue, chosen by a router
Install README and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.