Saucebox Registry
← Browse

@jeremylongshore/windsurf-cascade-onboarding

A

'Configure Cascade AI agent for new team projects. Activate when users

skillclaude

Install

agr install @jeremylongshore/windsurf-cascade-onboarding --target claude

Writes 1 file into .claude/skills/, pinned to git-bfd2e331.

  • .claude/skills/windsurf-cascade-onboarding/SKILL.md

Document

name: windsurf-cascade-onboarding description: 'Configure Cascade AI agent for new team projects. Activate when users mention

"setup cascade", "configure windsurf ai", "initialize cascade agent", "new windsurf project",

or "onboard team to windsurf". Handles agent configuration, context settings, and team defaults. Use when working with windsurf cascade onboarding functionality. Trigger with phrases like "windsurf cascade onboarding", "windsurf onboarding", "windsurf".

' allowed-tools: Read,Write,Edit,Bash(cmd:*),Grep,Glob version: 1.0.0 license: MIT author: Jeremy Longshore jeremy@intentsolutions.io tags:

  • saas
  • skill-databases
  • windsurf-cascade compatibility: Designed for Claude Code, also compatible with Codex and OpenClaw

Windsurf Cascade Onboarding

Overview

This skill enables rapid onboarding of projects to Windsurf with optimized Cascade AI configuration. It covers creating .windsurfrules, setting up project context, configuring team defaults, and establishing best practices for AI-assisted development.

Prerequisites

  • Windsurf IDE installed for all team members
  • Active Cascade AI subscription
  • Project documentation (architecture, conventions)
  • Team lead or admin access for configuration
  • Understanding of project structure and patterns

Instructions

  1. Initialize Windsurf Rules
  2. Configure Cascade Context
  3. Set Up Team Defaults
  4. Train Team Members
  5. Iterate Based on Feedback

See ${CLAUDE_SKILL_DIR}/references/implementation.md for detailed implementation guide.

Output

  • Configured .windsurfrules file
  • Project context documentation
  • Team snippet library
  • Onboarding guide for new members

Error Handling

See ${CLAUDE_SKILL_DIR}/references/errors.md for comprehensive error handling.

Examples

See ${CLAUDE_SKILL_DIR}/references/examples.md for detailed examples.

Resources

Trustgrade A

  • passBody integrity

    Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.

  • passType matchnot applicable to this artifact type

    Whether the artifact is really the kind of thing its metadata claims it is.

  • passFreshness

    How long since the source repository was last pushed to.

  • passPrompt injection

    Scans the artifact's own text for instructions aimed at your agent rather than at you.

  • passLicense

    Whether the source repository declares an SPDX license permissive enough to redistribute.

How the grade is calculated

Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:

  • Aevery check passed
  • Bone warning
  • Ctwo warnings
  • Dprompt injection or body integrity failed, or three warnings
  • Fone of those failed, and something else is wrong

These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.

Versions

  • git-bfd2e3315ce52026-07-31