Skip to main content
skillsFirst-partyReview first Safety Privacy
Windsurf logo

Cursor Windsurf AI Code Editor Skill - Claude Code Skills

Configure and optimize Cursor and Windsurf AI code editors for maximum productivity. Set up agent mode, composer features, keybindings, and AI-powered refactoring workflows. Customize with .cursorrules and .windsurfrules for project-specific guidance.

HarnessClaude CodeCodexWindsurfGeminiCursorCLI
Level:advancedType:generalVerified:draft
Review first review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Source URLs
https://docs.cursor.com/welcome, https://github.com/JSONbored/awesome-claude/blob/main/content/skills/cursor-windsurf-ai-ide-setup.mdx
Brand
Windsurf
Brand domain
windsurf.com
Brand asset source
brandfetch
Package URL
/downloads/skills/cursor-windsurf-ai-ide-setup.zip
Package SHA256
4f8ce19de6069c834ec7a452e8c3dbf1de4ff304ce049d5665a8ad56a0e800fe
Safety notes
Setup downloads and unzips a package and changes IDE configuration files; review what it writes and run it in a trusted workspace.
Privacy notes
Cursor and Windsurf send your code and prompts to their AI backends to power completion and chat; review each editor's data-handling settings and keep API keys out of committed config.
Platform compatibility
claude-code (native-skill), codex (native-skill), windsurf (native-skill), gemini (native-skill), cursor (adapter), cli (manual-context)
Author
JSONbored
Claim status
unclaimed
Last verified
2025-10-23

Decision playbook

Ready to evaluate for your workflow

Signals are comparatively strong, but you should still validate source, privacy posture, and package provenance for your environment.

Compare context
Selected

0

Current score

96

Baseline

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Complete

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done
  • Source provenance statusRequired

    Marked as first-party.

    Done
  • Metadata reviewed

    Registry metadata indicates a reviewed listing.

    Done

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done
  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done
  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Complete

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done
  • Package verification flag

    Package marked verified.

    Done
  • Checksum metadata

    SHA-256 hash is present.

    Done

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending
  • Baseline comparison available

    No baseline peer selected yet.

    Pending
  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

Package install

Copy-ready — paste the snippet to get started.

Install command

Provided

Config snippet

Not provided

Copy snippet

Provided

Prerequisites

6 to clear

Platforms

6 listed

Difficulty

100/100

Adoption plan

Balanced adoption plan

Current risk score 0/100. Use staged verification before broader rollout.

Risk 0

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done
  • Confirm metadata review state

    Listing has review metadata.

    Done
  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done
  • Review privacy notesRequired

    Privacy notes are present.

    Done
  • Verify package integrity metadata

    Package verification/checksum metadata is available.

    Done

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending
  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending
  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Required evidence gates are covered (6/6 signals complete).

Risk 0

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Present

Review metadata is present.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Present

Package integrity metadata is present.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required evidence gates are covered for this preset.

Decision timeline

Decision timeline · balanced

6/6 steps complete with no blocking gaps for this preset.

Risk 0

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is available.

Done

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is available.

Done

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

No required blockers for this timeline preset.

Prerequisite readiness

Prerequisite readiness

6 prerequisites to line up before setup. Have accounts and credentials ready first.

0/6 ready
Account & credentials2Install & runtime1General3

Safety & privacy surface

Safety & privacy surface

1 safety and 1 privacy notes across 2 risk areas. Review closely: credentials & tokens, network access.

2 areas
  • SafetyNetwork accessSetup downloads and unzips a package and changes IDE configuration files; review what it writes and run it in a trusted workspace.
  • PrivacyCredentials & tokensCursor and Windsurf send your code and prompts to their AI backends to power completion and chat; review each editor's data-handling settings and keep API keys out of committed config.

Safety notes

  • Setup downloads and unzips a package and changes IDE configuration files; review what it writes and run it in a trusted workspace.

Privacy notes

  • Cursor and Windsurf send your code and prompts to their AI backends to power completion and chat; review each editor's data-handling settings and keep API keys out of committed config.

Prerequisites

  • Cursor IDE or Windsurf IDE
  • OpenAI API key or Anthropic API key
  • macOS/Windows/Linux
  • Cursor or Windsurf IDE installed (latest version recommended for best AI features)
  • Active internet connection for AI model access and extension marketplace
  • Sufficient system resources: minimum 8GB RAM, 2GB free disk space for workspace indexing and AI model caching

Schema details

Install type
package
Reading time
6 min
Difficulty score
100
Troubleshooting
Yes
Breaking changes
No
Package metadata
Package verified
Yes
SHA-256
4f8ce19de6069c834ec7a452e8c3dbf1de4ff304ce049d5665a8ad56a0e800fe
Skill and platform metadata
Skill type
general
Skill level
advanced
Verification
draft
Verified at
2025-10-23
Retrieval sources
https://docs.cursor.com/welcomehttps://docs.cursor.com/context/rules-for-aihttps://docs.windsurf.com/windsurf/cascade
Tested platforms
ClaudeCodexOpenClawCursorWindsurfGemini
PlatformSupportInstall path
claude-codeNative.claude/skills/<skill-name>/SKILL.md
codexNative.agents/skills/<skill-name>/SKILL.md
windsurfNative.windsurf/skills/<skill-name>/SKILL.md
geminiNative.gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md
cursorAdapter.cursor/rules/<skill-name>.mdc
cliManualAGENTS.md or tool-specific context file
Full copyable content
# Project: Next.js 15 SaaS Application

## Tech Stack
- Next.js 15.0+ (App Router, Server Actions)
- React 19.0+
- TypeScript 5.5+ (strict mode)
- Tailwind CSS 4.0+
- shadcn/ui components
- Zod for validation
- Prisma with PostgreSQL

## Coding Conventions
- Use named exports (no default exports except pages)
- Prefix server actions with 'action'
- All async functions must have error handling
- Use Zod schemas for all form inputs
- Components in PascalCase, files in kebab-case
- Max function length: 50 lines
- All props must have TypeScript interfaces

## Patterns to Follow
- Server Actions for mutations (no API routes)
- React Server Components by default
- Client components only when needed ('use client')
- Parallel data fetching with Promise.all
- Error boundaries for all async components
- Loading states with Suspense
- Form validation with Zod + React Hook Form

## Patterns to Avoid
- Don't use 'any' type (use 'unknown' if needed)
- Don't fetch in client components (use server)
- Don't bypass TypeScript with @ts-ignore
- Don't create custom hooks without jsdoc
- Don't use inline styles (use Tailwind)

## Testing
- Unit tests with Vitest
- E2E tests with Playwright
- Minimum 80% coverage
- Test file naming: *.test.ts

## Performance
- Dynamic imports for heavy components
- Image optimization with next/image
- Font optimization with next/font
- Metadata API for SEO

About this resource

What This Skill Enables

Claude can help you configure and optimize Cursor or Windsurf AI code editors for maximum productivity. Both editors provide AI-powered code completion, multi-file editing, and intelligent refactoring. Cursor excels with its Agent mode and Composer features, while Windsurf emphasizes collaborative flows and Cascade AI. From initial setup to advanced workflows, Claude handles IDE configuration and optimization.

Compatibility

Native

  • Claude Code / Claude: native skill usage via SKILL.md.
  • Codex/OpenAI workflows: compatible with Agent Skills-style SKILL.md content as reusable workflow instructions.

Manual Adaptation

  • Gemini CLI: native skill usage via .gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md where supported.
  • Cursor: use the generated .cursor/rules/*.mdc adapter for project rules.
  • OpenClaw and similar agents: use the same skill content as a reusable prompt/workflow file when native skill import is unavailable.

Prerequisites

Required:

  • Claude Pro subscription or Claude Code CLI
  • macOS, Windows, or Linux
  • Cursor or Windsurf IDE installed
  • OpenAI API key or Anthropic API key
  • Basic code editor knowledge

What Claude handles automatically:

  • Configuring API keys and model selection
  • Setting up keybindings for AI features
  • Optimizing editor settings for performance
  • Creating custom rules and context files
  • Configuring agent mode behaviors
  • Setting up workspace-specific settings
  • Implementing best practices for prompting
  • Optimizing token usage and costs

How to Use This Skill

Initial Setup & Configuration

Prompt: "Help me set up Cursor with Claude Sonnet model. Configure keybindings for: inline completion (Tab), chat (Cmd+K), composer (Cmd+I), and agent mode. Optimize for React/TypeScript projects."

Claude will:

  1. Guide API key configuration
  2. Set model to Claude Sonnet
  3. Configure keyboard shortcuts
  4. Add .cursorrules for React/TS
  5. Set up workspace settings
  6. Configure auto-complete behavior
  7. Add project context files

Optimizing Agent Mode

Prompt: "Configure Cursor Agent mode for: automatic file edits, test generation, refactoring tasks, and documentation. Set guardrails to prevent breaking changes."

Claude will:

  1. Enable agent mode settings
  2. Configure file permissions
  3. Set up test generation rules
  4. Add refactoring guidelines
  5. Create .cursorrules for safety
  6. Configure approval workflows
  7. Set token limits

Custom Rules & Context

Prompt: "Create .cursorrules file for Next.js 15 project with: TypeScript strict mode, shadcn/ui components, Tailwind CSS, server actions, and Zod validation. Include coding standards."

Claude will:

  1. Create .cursorrules file
  2. Specify tech stack versions
  3. Add coding conventions
  4. Include common patterns
  5. Set error handling rules
  6. Add performance guidelines
  7. Document API usage

Multi-File Refactoring

Prompt: "Set up Windsurf Cascade for: renaming components across files, updating import paths, refactoring prop types, and running type checks. Configure to preview changes before applying."

Claude will:

  1. Configure Cascade settings
  2. Enable preview mode
  3. Set up diff viewing
  4. Add rollback capability
  5. Configure type checking
  6. Set up batch operations
  7. Add safety confirmations

Tips for Best Results

  1. Use .cursorrules: Create project-specific rules file with tech stack, conventions, and patterns. AI reads this for context.

  2. Composer for Large Changes: Use Cmd+I (Cursor) or Cascade (Windsurf) for multi-file edits. More powerful than inline chat.

  3. @ Mentions for Context: Use @filename, @folder, @docs to give AI specific context. Reduces hallucinations.

  4. Agent Mode Guardrails: Set file permissions and review changes. Don't let agent edit critical files unsupervised.

  5. Model Selection: Claude Sonnet for code quality, GPT-4 for speed. Switch based on task complexity.

  6. Token Optimization: Use codebase indexing wisely. Exclude node_modules, dist, .next from context.

Common Workflows

React Component Refactoring

"Configure Cursor for React refactoring workflow:
1. Set up .cursorrules with React 19 patterns
2. Enable TypeScript strict mode validation
3. Configure agent mode for component splits
4. Add rules for shadcn/ui usage
5. Set up automatic prop-types to TS conversion
6. Configure test generation with Vitest
7. Enable preview for all agent changes
8. Add rollback shortcuts"

API Route Generation

"Set up Windsurf for API development:
1. Create .cursorrules for FastAPI/Next.js API routes
2. Configure agent to generate OpenAPI docs
3. Set up automatic validation with Zod
4. Add error handling templates
5. Configure test generation
6. Set up database query optimization
7. Enable security scanning
8. Add rate limiting patterns"

Legacy Code Migration

"Configure Cursor for migrating JS to TS:
1. Set up .cursorrules for TypeScript migration
2. Configure agent for file-by-file conversion
3. Add type inference rules
4. Set up any type replacement
5. Configure import path updates
6. Enable type checking after each file
7. Add rollback on type errors
8. Generate migration report"

Test Coverage Improvement

"Set up Windsurf for test generation:
1. Configure agent for unit test creation
2. Add .cursorrules for testing patterns
3. Set up coverage threshold checks
4. Configure mock generation
5. Add integration test templates
6. Set up snapshot testing rules
7. Enable test runner integration
8. Generate coverage reports"

Troubleshooting

Issue: "AI suggestions are slow or timing out" Solution: Reduce context size by excluding large folders in settings. Use @filename for specific context instead of full codebase. Check API rate limits. Switch to faster model (GPT-3.5) for simple edits. Clear index and rebuild.

Issue: "Agent mode making unwanted changes" Solution: Add .cursorrules with explicit guidelines. Set file permissions to read-only for critical files. Enable preview mode to review all changes. Use 'explain' prompts before 'do' prompts. Add 'do not modify' comments in code.

Issue: "API costs higher than expected" Solution: Exclude unnecessary folders from indexing. Use caching (Cursor's @codebase). Switch to smaller models for simple tasks. Disable auto-complete for comments. Review token usage in settings. Use local models for basic completion.

Issue: "Keybindings conflicting with other extensions" Solution: Check keybindings.json for conflicts. Reassign Cursor/Windsurf shortcuts. Disable conflicting extensions. Use Cmd+K+S (Cursor) to view all shortcuts. Export keybindings and version control them.

Issue: "AI not using project context correctly" Solution: Create detailed .cursorrules file. Use @docs to reference documentation. Add README with architecture overview. Use @folder for package-specific context. Verify codebase indexing is complete. Rebuild index if stale.

Learn More

Features

  • AI-powered multi-file editing with agent modes
  • Inline code completion with context awareness
  • Chat interface for code explanations and refactoring
  • Composer/Cascade for large-scale code changes
  • Custom rules files (.cursorrules, .windsurfrules) for project-specific guidance
  • Context-aware codebase indexing and retrieval
  • Multi-file refactoring with preview and rollback
  • Performance optimization and resource management with workspace indexing configuration, memory usage tuning, and extension management for optimal IDE responsiveness

Use Cases

  • Configuring AI IDE for specific tech stacks
  • Setting up multi-file refactoring workflows
  • Optimizing token usage and API costs
  • Legacy code migration and modernization
  • Automated test generation and coverage improvement
  • Code review and security scanning workflows

Source citations

Add this badge to your README

Show that Cursor Windsurf AI Code Editor Skill - Claude Code Skills is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/skills/cursor-windsurf-ai-ide-setup.svg)](https://heyclau.de/entry/skills/cursor-windsurf-ai-ide-setup)

How it compares

Cursor Windsurf AI Code Editor Skill - Claude Code Skills side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

3 trust signals differ across this comparison (Package trust, Source provenance, Submitter).

Next steps differ across entries — use the actions in the table below to copy install commands and source links per resource.

Field

Configure and optimize Cursor and Windsurf AI code editors for maximum productivity. Set up agent mode, composer features, keybindings, and AI-powered refactoring workflows. Customize with .cursorrules and .windsurfrules for project-specific guidance.

Open dossier

Create portable Agent Skills, generate platform adapters, validate package metadata, and prepare PR-first HeyClaude submissions.

Open dossier

Master collaborative AI-assisted development with Windsurf IDE's Cascade AI, multi-file context awareness, and Flow patterns for team workflows.

Open dossier

Expert Claude Code terminal ergonomics capability pack for auditing multiline input, Option/Meta shortcuts, tmux passthrough, notifications, fullscreen rendering, themes, status lines, Vim mode, and custom keybindings before a user blames Claude for terminal behavior.

Open dossier
Next stepsDiffers
Trust
Review statusReviewedMaintainer reviewedReviewedMaintainer reviewedReviewedMaintainer reviewedReviewedMaintainer reviewed
Package trustDiffersPackage verified2025-10-23Package verified2026-06-02Package verified2025-10-16Package not verified
Source provenanceDiffersSource-backedNo submission linkNo submission linkSubmission linkedSource submission
SubmitterDiffersYB0y
Install riskReview firstLow riskLow riskReview first
Notes Safety Privacy Safety Privacy Safety Privacy Safety Privacy
BrandWindsurf logoWindsurfWindsurf logoWindsurf
Categoryskillsskillsskillsskills
Sourcefirst-partyfirst-partyfirst-partysource-backed
AuthorJSONboredJSONboredJSONboredYB0y
Added2025-10-232026-04-272025-10-162026-06-10
Platforms
Claude CodeCodexWindsurfGeminiCursorCLI
Claude CodeCodexWindsurfGeminiCursorCLI
Claude CodeCodexWindsurfGeminiCursorCLI
Claude CodeCodexWindsurfGeminiCursorCLI
Source repo
Safety notesSetup downloads and unzips a package and changes IDE configuration files; review what it writes and run it in a trusted workspace.Downloads and unzips a HeyClaude-maintainer-packaged skill archive into a local folder when using the install command. Produces public skill package and submission drafts; review generated files before opening a PR or sharing them.Setup downloads and unzips a package and changes Windsurf IDE configuration; review what it writes and run it in a trusted workspace.This skill recommends terminal and Claude Code configuration changes; it must not edit dotfiles, keybindings, hooks, themes, or tmux settings without showing the proposed diff first. `/terminal-setup` writes terminal or editor keybindings and may adjust integrated-terminal settings; run it in the host terminal and record what changed before relying on it. tmux passthrough allows escape sequences to reach the outer terminal; enable it deliberately, especially on shared, remote, or security-sensitive hosts. Notification hooks can execute local commands when Claude needs attention; keep them simple, review command paths, and avoid hooks that send prompts or logs to third-party services. Fullscreen rendering, theme files, status lines, and keybinding changes should be treated as reversible local UI preferences, not fixes for model quality or project bugs.
Privacy notesCursor and Windsurf send your code and prompts to their AI backends to power completion and chat; review each editor's data-handling settings and keep API keys out of committed config.Does not require credentials and should only process public skill requirements, source URLs, and validation notes. Do not include private repository names, customer data, tokens, or unpublished operating details in generated skill packages.Windsurf (Cascade) sends your code and prompts to its AI backend to power multi-file operations; review Windsurf's data-handling settings and keep API keys and secrets out of committed config.Terminal settings, tmux files, keybinding files, status line commands, and hook snippets can expose usernames, hostnames, project paths, shell aliases, secrets in environment commands, and internal repository names. Notification commands and status line scripts may reveal task names, working directories, git branches, model names, costs, or local operational context. Remote terminal and SSH notification behavior can surface session activity on a local desktop; confirm the user is comfortable with that visibility. Public PR or issue notes should summarize symptoms and redacted settings, not paste complete dotfiles, shell history, terminal transcripts, or private hook scripts.
Prerequisites
  • Cursor IDE or Windsurf IDE
  • OpenAI API key or Anthropic API key
  • macOS/Windows/Linux
  • Cursor or Windsurf IDE installed (latest version recommended for best AI features)
  • Skill topic and target user
  • Official docs or source URLs
  • Validation commands or acceptance criteria
  • Windsurf IDE installed (download from codeium.com/windsurf)
  • Active project/codebase
  • Git repository (recommended for version control)
  • Codeium account (for Cascade AI features)
  • Claude Code installed and runnable in the terminal, editor terminal, SSH session, or tmux/screen environment being reviewed.
  • The user's operating system, terminal emulator, shell, Claude Code version, and whether Claude Code is running locally, remotely, or inside tmux.
  • Permission to inspect redacted terminal settings, `~/.claude/settings.json`, `~/.claude/keybindings.json`, `~/.tmux.conf`, and notification hook snippets when relevant.
  • A concrete ergonomics symptom, such as Shift+Enter submitting, missing alerts, scrollback jumping, unreadable colors, Vim mode confusion, or shortcut conflicts.
Install
curl -L https://heyclau.de/downloads/skills/cursor-windsurf-ai-ide-setup.zip -o cursor-windsurf-ai-ide-setup.zip && unzip -o cursor-windsurf-ai-ide-setup.zip -d ./cursor-windsurf-ai-ide-setup
curl -L https://heyclau.de/downloads/skills/heyclaude-skill-submission-factory.zip -o heyclaude-skill-submission-factory.zip && unzip -o heyclaude-skill-submission-factory.zip -d ./heyclaude-skill-submission-factory
curl -L https://heyclau.de/downloads/skills/windsurf-collaborative-development.zip -o windsurf-collaborative-development.zip && unzip -o windsurf-collaborative-development.zip -d ./windsurf-collaborative-development
Config
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Related guides

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.