windsurf-performance-tuning
Optimize Windsurf API performance with caching, batching, and connection pooling. Use when experiencing slow API responses, implementing caching strategies, or optimizing request throughput for Windsurf integrations. Trigger with phrases like "windsurf performance", "optimize windsurf", "windsurf latency", "windsurf caching", "windsurf slow", "windsurf batch".
Install
mkdir -p .claude/skills/windsurf-performance-tuning && curl -L -o skill.zip "https://mcp.directory/api/skills/download/8498" && unzip -o skill.zip -d .claude/skills/windsurf-performance-tuning && rm skill.zipInstalls to .claude/skills/windsurf-performance-tuning
About this skill
Windsurf Performance Tuning
Overview
Optimize Windsurf's indexing engine, Cascade context building, Supercomplete latency, and overall IDE responsiveness. Most performance issues stem from indexing too many files or missing exclusion patterns.
Prerequisites
- Windsurf IDE installed
- Understanding of workspace indexing
- Access to Windsurf settings
Instructions
Step 1: Optimize Workspace Indexing
The indexing engine is the #1 performance factor. Exclude everything that isn't source code:
# .codeiumignore — aggressive exclusion for large codebases
# Build artifacts
node_modules/
dist/
build/
.next/
.nuxt/
.output/
.svelte-kit/
coverage/
.cache/
# Package manager
pnpm-lock.yaml
package-lock.json
yarn.lock
# Generated code
*.min.js
*.min.css
*.bundle.js
*.chunk.js
**/*.map
generated/
__generated__/
# Binary and media files
*.png
*.jpg
*.gif
*.svg
*.ico
*.mp4
*.woff
*.woff2
*.ttf
*.eot
# Data files
*.sqlite
*.db
*.sql.gz
*.csv
# Python
__pycache__/
*.pyc
.venv/
venv/
.tox/
*.egg-info/
# Go
vendor/
# Rust
target/
Step 2: Open Focused Workspaces
# DON'T: Open entire monorepo root
windsurf ~/monorepo/ # Indexes ALL packages = slow
# DO: Open specific service directories
windsurf ~/monorepo/apps/web/ # Only indexes web app
windsurf ~/monorepo/packages/api/ # Only indexes API
# Each Windsurf window gets its own focused AI context
# Cascade performs better with fewer, relevant files
Step 3: Tune IDE Settings
// settings.json — performance-focused configuration
{
// Indexing limits
"codeium.indexing.maxFileSize": 524288,
// Reduce extension overhead
"extensions.autoUpdate": false,
"extensions.autoCheckUpdates": false,
// Editor performance
"editor.minimap.enabled": false,
"editor.renderWhitespace": "none",
"editor.bracketPairColorization.enabled": false,
// File watcher optimization
"files.watcherExclude": {
"**/node_modules/**": true,
"**/dist/**": true,
"**/.git/objects/**": true,
"**/build/**": true
},
// Search exclusions
"search.exclude": {
"**/node_modules": true,
"**/dist": true,
"**/coverage": true,
"**/*.min.js": true
}
}
Step 4: Optimize Cascade Usage
## Cascade Performance Tips
1. Start fresh sessions for new tasks
- Long conversations accumulate context, slowing responses
- Click + in Cascade panel to start new conversation
2. Use @ mentions instead of describing files
- BAD: "Look at the auth service file"
- GOOD: "@src/services/auth.ts fix the token refresh logic"
3. Scope prompts narrowly
- BAD: "Refactor the authentication system"
- GOOD: "Extract JWT validation from src/middleware/auth.ts into src/services/jwt.ts"
4. Use Chat mode for questions, Write mode for edits
- Chat mode is lighter — doesn't build full edit context
- Switch modes based on intent
5. Choose the right model for the task
- SWE-1 Lite: fast, lightweight questions (no credits)
- SWE-1: standard coding tasks
- SWE-1.5 / Claude: complex multi-file tasks (worth the wait)
Step 5: Memory Management
## Reduce Memory Usage
1. Close unused editor tabs
- Each open file adds to memory footprint
- Cmd/Ctrl+K Cmd/Ctrl+U: close unused tabs
2. Limit extensions
- Each extension consumes memory
- Disable extensions you don't actively use
- Check: Extensions > "@enabled" to review
3. Disable unused Supercomplete languages
- Settings > codeium.autocomplete.languages
- Disable for languages you don't write
4. Monitor process memory
- Help > Open Process Explorer
- Look for extensions consuming >200MB
Step 6: Benchmark Your Setup
#!/bin/bash
set -euo pipefail
echo "=== Windsurf Performance Check ==="
# Workspace size
FILE_COUNT=$(find . -type f -not -path '*/node_modules/*' -not -path '*/.git/*' | wc -l)
echo "Indexed files: ~$FILE_COUNT"
# Config status
echo "Has .codeiumignore: $([ -f .codeiumignore ] && echo 'YES' || echo 'NO (SLOW!)')"
IGNORE_LINES=$(wc -l < .codeiumignore 2>/dev/null || echo 0)
echo "Ignore patterns: $IGNORE_LINES"
# Recommendations
if [ "$FILE_COUNT" -gt 5000 ]; then
echo "WARNING: >5000 files. Add more patterns to .codeiumignore"
fi
if [ "$IGNORE_LINES" -lt 5 ]; then
echo "WARNING: Few ignore patterns. Add build artifacts, binaries, lock files"
fi
Error Handling
| Issue | Cause | Solution |
|---|---|---|
| Indexing never completes | Too many files | Add .codeiumignore, open subdirectory |
| Cascade timeout | Complex prompt + large context | Narrow scope, start fresh session |
| High memory usage | Too many extensions/tabs | Close tabs, disable unused extensions |
| Supercomplete lag | Large file open | Split large files, add to maxFileSize limit |
| IDE freezes | Extension conflict | Safe Mode: windsurf --disable-extensions |
Examples
Quick Performance Fix
# Create minimal .codeiumignore if missing
[ -f .codeiumignore ] || cat > .codeiumignore << 'EOF'
node_modules/
dist/
build/
.next/
coverage/
*.min.js
*.map
EOF
Reset Indexing
Command Palette (Cmd/Ctrl+Shift+P):
"Codeium: Reset Indexing"
Resources
Next Steps
For cost optimization, see windsurf-cost-tuning.
More by jeremylongshore
View all skills by jeremylongshore →You might also like
flutter-development
aj-geddes
Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.
drawio-diagrams-enhanced
jgtolentino
Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.
ui-ux-pro-max
nextlevelbuilder
"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."
godot
bfollington
This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.
nano-banana-pro
garg-aayush
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
pdf-to-markdown
aliceisjustplaying
Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.
Related MCP Servers
Browse all serversOptimize Facebook ad campaigns with AI-driven insights, creative analysis, and campaign control in Meta Ads Manager for
Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API
Chinese Trends Hub gives you real-time trending topics from major Chinese platforms like Weibo, Zhihu, Douyin, and more,
Use Google Lighthouse to check web page performance and optimize website speed. Try our landing page optimizer for bette
Process Excel files efficiently: read sheet names, extract data, and cache workbooks for large files using tools like pd
GitHub Repos Manager integrates with GitHub's REST API to streamline repo management, issues, pull requests, file ops, s
Stay ahead of the MCP ecosystem
Get weekly updates on new skills and servers.