Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
A guide and workflow collection for the Windsurf IDE and its Cascade AI agent. Covers all major features including Skills, Workflows, Memories, Rules, MCP integration, and multi-agent sessions, updated through Wave 13 (January 2026). Cascade can autonomously edit files, run terminal commands, and maintain project memory across sessions.
Windsurf combines an agentic AI with a dedicated terminal, built-in live preview, persistent memory, and a Skills system in one editor, which eliminates the need to wire together separate tools for these workflows.
When to use it
- Reviewing PR comments and committing fixes via Cascade
- Deploying to production using a slash-command workflow with safety checks
- Setting up project-specific coding rules and auto-generated memories
- Running parallel Cascade sessions on separate branches with Git worktrees
- Connecting external tools to Cascade through MCP servers
Example Workflow
Here's how your AI assistant might use this skill in practice.
User runs /deploy in Cascade to deploy a web app to production
- 1Reads the deploy.md workflow from .windsurf/workflows/
- 2Runs npm test in the dedicated zsh terminal
- 3Runs npm run build and npm run lint sequentially
- 4If all checks pass, executes npm run deploy:production
- 5Verifies deployment health checks and reports status
App deployed to production with all test, build, and lint checks confirmed passing
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.