cursor-pack
Complete Cursor integration skill pack with 30 skills covering AI code editing, composer workflows, codebase indexing, and productivity features. Flagship+ tier vendor pack.
Installation
Open Claude Code and run this command:
/plugin install cursor-pack@claude-code-plugins-plus
Use --global to install for all projects, or --project for current project only.
What It Does
> 30 production-grade skills for Cursor IDE mastery -- real .cursor/rules, real Composer workflows, real @-symbol patterns
Complete Claude Code skill pack for Cursor, the AI-first code editor. Every skill contains real configuration examples, real keyboard shortcuts, real settings paths, and real architectural patterns drawn from Cursor's actual documentation and feature set.
Skills (30) plugin-local skills
Advanced Cursor Composer techniques: agent mode, parallel agents, complex refactoring, and multi-step orchestration.
Cursor Advanced Composer
Overview
Use Composer for bounded multi-file proposals when a human owner can inspect the plan, diff, tests, and rollback before applying changes.
Prerequisites
- A defined task, affected-file boundary, repository rules, and a clean working tree or recoverable branch.
- Required test commands and a reviewer for changes that alter architecture, security, or data flow.
Instructions
- Ask Composer for a plan and affected-file list before applying any edits.
- Constrain it to the approved scope and provide acceptance checks/non-goals.
- Inspect each diff, run focused validation, and split or reject changes that exceed scope.
- Commit only reviewed, test-backed changes; retain a revert path.
Output
- A reviewed multi-file change proposal with affected files, validation results, and rollback reference.
Error Handling
| Condition | Safe response |
|---|---|
| Composer proposes unrelated files | Reject or split the request; do not apply all. |
| Output conflicts with rules/tests | Treat project controls as authoritative and revise manually or with a narrower prompt. |
| Sensitive context is attached | Stop, remove it, and follow exposure handling. |
Examples
Ask Composer to add a feature only in src/feature/ and its existing tests, requiring a plan first. Apply no files until the plan and diff are reviewed; run the focused suite and revert the commit if acceptance fails.
Advanced patterns for Cursor Composer including agent orchestration, complex multi-file refactoring, architecture migrations, and quality-control workflows.
Agent Mode Deep Dive
In Agent mode, Composer autonomously chains tool calls: reading files, searching the codebase, running terminal commands, and writing code. It operates in a loop until the task is complete or it hits the 25-tool-call limit.
Agent Tool Capabilities
| Tool | What it does | Approval needed? |
|---|---|---|
| Read file | Reads any file in workspace | No |
| Search codebase | Semantic + text search | No |
| Write file | Creates or overwrites files | Shows diff first |
| Edit file | Modifies sections of files | Shows diff first |
| Run terminal command | Executes shell commands | Yes (click Allow) |
| List directory | Browses folder structure | No |
Controlling Agent Behavior
Give the agent constraints in your prompt:
Migrate all React class components in src/components/ to functional
components with hooMaster Cursor AI Chat with @-mentions, inline edit, and conversation patterns.
Cursor AI Chat
Overview
Use Chat to reason about a bounded question or planned change while preserving human ownership of decisions, edits, review, and validation.
Prerequisites
- Approved privacy/model settings and a workspace with sensitive paths excluded.
- A clear question, relevant non-sensitive files, and the project's test/review expectations.
Instructions
- Start a topic-scoped chat and attach only the files needed for the question.
- Ask for assumptions, tradeoffs, and a testable proposal rather than accepting generated code blindly.
- Verify suggestions against source, tests, security controls, and a human code review.
- Start a new conversation when context becomes stale or the topic changes.
Output
- A bounded explanation or proposal with assumptions, affected files, and validation steps.
Error Handling
| Condition | Safe response |
|---|---|
| Answer contradicts repository facts | Inspect the source and restate the question with the correct files. |
| Conversation loses context | Start a new scoped chat; do not compensate by attaching the entire repository. |
| Prompt includes sensitive material | Remove it and follow the exposure process before continuing. |
Examples
Ask Chat to compare SSE and WebSockets for the stated service, attaching only the API contract and architecture note. Require it to list assumptions and a rollout/rollback test plan; then review the proposal before authoring any change.
Master the Cursor AI Chat panel and inline edit for code assistance, debugging, and exploration.
Core Chat Interfaces
Chat Panel (Cmd+L / Ctrl+L)
The side-panel chat for conversational code assistance:
┌─────────────────────────────────┐
│ Chat [M] │ ← Model selector
│─────────────────────────────────│
│ Context Pills: │
│ [main.ts] [utils/] [@Web] │ ← Active context shown as pills
│─────────────────────────────────│
│ User: Explain the auth flow │
│ in @src/auth/middleware.ts │
│ │
│ AI: The middleware checks... │
│─────────────────────────────────│
│ [Type message...] [Send] │
└─────────────────────────────────┘
Key actions:
- Select code in editor, then
Cmd+Lto add selection as context Cmd+Shift+Ladds selection to existing chat without clearing- Click model name in top-right to switch models mid-conversation
Inline Edit (Cmd+K / Ctrl+K)
Surgical edits within the editor. Select code (or place cursor), press Cmd+K, type instruction:
Selected: function calculateTotal(itemsConfigure BYOK API keys for OpenAI, Anthropic, Google, Azure, and custom models in Cursor.
Cursor API Key Management
Overview
Manage any Cursor BYOK/provider credentials as individual, least-privilege secrets with approved routing, ownership, rotation, spending limits, and exposure response.
Prerequisites
- An approved provider/model route, named key owner, secrets-manager integration, and budget policy.
- Confirmation that BYOK is permitted for the intended data classification and tenant configuration.
Instructions
- Issue one scoped key per owner or approved service through the provider/secrets manager.
- Configure it through the approved UI/injection path; never commit it, paste it into rules, or share it between users.
- Set provider spending/rate controls, review usage, and rotate on schedule or suspected exposure.
- Revoke first, then investigate, when a key is lost, leaked, or no longer required.
Output
- An attributable, scoped credential with rotation, budget, and revocation evidence.
Examples
Create a personal provider key in the approved secret manager, configure it only in the local secure setting, verify a low-cost non-sensitive request, and confirm usage attribution. If it appears in logs, chat, or git, revoke it immediately and replace it; do not attempt to redact history before revocation.
Configure Bring Your Own Key (BYOK) for AI model providers in Cursor. BYOK lets you use your own API keys to bypass Cursor's monthly quota, pay per token directly, and access models not included in Cursor's subscription.
Supported Providers
| Provider | Key Format | Models Available |
|---|---|---|
| OpenAI | sk-proj-... or sk-... |
GPT-4o, GPT-4o-mini, o1, o3, GPT-5 |
| Anthropic | sk-ant-api03-... |
Claude Sonnet, Claude Opus, Claude Haiku |
AIzaSy... |
Gemini 2.5 Pro, Gemini Flash | |
| Azure OpenAI | Azure portal key | Any deployed Azure OpenAI model |
| AWS Bedrock | IAM credentials | Claude, Titan, Llama models |
| OpenAI-compatible | Varies | Ollama, LM Studio, Together AI, etc. |
Configuration Steps
OpenAI
- Go to platform.openai.com/api-keys
- Create a new API key (project-scoped recommended)
- In Cursor:
Cursor Settings>Models> checkUse own API key - Paste key in the OpenAI API Key field
- Select model from dropdown (e.g.,
gpt-4o)
Anthropic
- Go to console.anthropic.com/settings/keys
- Create a new API k
Set up and optimize Cursor codebase indexing for semantic code search and @Codebase queries.
Cursor Codebase Indexing
Overview
Configure codebase indexing so relevant source and documentation are available while sensitive, generated, oversized, and unrelated files remain excluded from AI context.
Prerequisites
- Repository ownership, expected source/documentation paths, and reviewed
.cursorignore/indexing exclusions. - A non-sensitive verification fixture and a change-review path for configuration updates.
Instructions
- Define the intended workspace scope and add exclusions before the first indexing pass.
- Verify required files can be found and excluded paths cannot be attached or discovered.
- Reindex only after a reviewed configuration/workspace change and capture a redacted result.
- Monitor index size/performance and narrow scope rather than weakening data controls.
Output
- A verified index scope with explicit included/excluded paths and an owner for maintenance.
Examples
Index src/ and docs/ for a service while excluding .env*, build output, vendor directories, and customer exports. Verify a sanitized source file is available and an excluded placeholder is not before allowing AI work on the repository.
Set up and optimize Cursor's codebase indexing system. Indexing creates embeddings of your code, enabling @Codebase semantic search and improving AI context awareness across Chat, Composer, and Agent mode.
How Indexing Works
Your Code Files
│
▼
Syntax Chunking ─── splits files into meaningful code blocks
│
▼
Embedding Generation ─── converts chunks to vector representations
│
▼
Vector Storage (Turbopuffer) ─── cloud-hosted nearest-neighbor search
│
▼
@Codebase Query ─── your question → embedding → similarity search → relevant chunks
Key Architecture Details
- Merkle tree for change detection: only modified files are re-indexed (every 10 minutes)
- No plaintext storage: code is not stored server-side; only embeddings and obfuscated metadata
- Privacy Mode compatible: with Privacy Mode on, embeddings are computed without retaining source code
- Indexing runs in the background; small projects complete in seconds, large projects (50K+ files) may take hours initially
Initial Setup
- Open your project in Cursor
- Indexing starts automatically on first open
- Check status: look at the bottom status bar for "Indexing..." indicator
- View indexed files:
Cursor Settings>Features>Codebase Indexing>View included files
Verify Indexing Status
The status bar shows:
- "Indexing...&
Troubleshoot common Cursor IDE errors: authentication, completion, indexing, API, and performance issues.
Cursor Common Errors
Overview
Diagnose Cursor startup, authentication, extension, indexing, and workspace errors with reversible, user-scoped steps before resetting local state.
Prerequisites
- A reproduction, Cursor version, affected operating system, and an approved backup location for user settings.
- Authorization to inspect local logs; redact project paths, prompts, and credentials from support evidence.
Instructions
- Reproduce the issue with extensions disabled or in a disposable profile when possible.
- Capture the smallest relevant status/log evidence and try the least-destructive documented remedy.
- Back up settings before clearing caches or resetting state, then validate recovery with a non-sensitive workspace.
- Escalate persistent issues with a redacted reproduction instead of sharing workspace data.
Output
- A classified issue, reversible remediation, and redacted verification result.
Error Handling
| Condition | Safe response |
|---|---|
| Reset would erase user settings | Create and verify a backup before proceeding. |
| Logs contain sensitive code or tokens | Redact them and use the approved secure support route. |
| Error persists after safe remediation | Stop destructive retries and escalate with the minimal reproduction. |
Examples
When Cursor will not start, launch once with extensions disabled, record the version and outcome, then re-enable extensions individually in a disposable profile. Clear only cache folders after backing up settings; do not delete the full profile to diagnose a single extension.
Diagnostic and resolution guide for the most frequent Cursor IDE issues. Organized by error category with specific symptoms, causes, and fixes.
Authentication Errors
"Sign-in failed" / OAuth Loop
Symptoms: Browser opens for auth, redirects back, Cursor still shows "Sign In".
Fix:
- Clear browser cookies for
cursor.comandauth.cursor.com - Try incognito/private window for the OAuth flow
- Check if browser is blocking popups from cursor.com
- Try a different auth method (GitHub vs Google vs email)
"License not found" / "No active subscription"
Symptoms: Signed in but AI features are disabled.
Fix:
- Verify subscription at cursor.com/settings
- Confirm the email address matches your Cursor account
- Sign out (
Cmd+Shift+P>Sign Out) then sign back in - If on a team plan, ask admin to verify your seat is assigned
Compliance and security auditing for Cursor IDE usage: SOC 2, GDPR, HIPAA assessment, evidence collection, and remediation.
Cursor Compliance Audit
Overview
Assess a Cursor deployment against approved privacy, identity, source-code, and audit controls. This is an evidence-backed configuration review, not legal certification.
Prerequisites
- A named system owner, applicable controls, and authority to inspect tenant settings.
- Read-only admin evidence, current access roster, and redaction rules for audit artifacts.
- Legal/compliance review for regulated data, customer commitments, or PHI/PCI scope.
Instructions
- Define the tenant, repositories, data classes, and control period in scope.
- Compare privacy, retention, identity, access review, and
.cursorignoresettings to the approved baseline. - Record findings with evidence, owner, severity, due date, and verification method.
- Escalate suspected sensitive-code exposure before broad configuration changes.
Compliance and security auditing framework for Cursor IDE usage. Covers SOC 2, GDPR, and HIPAA assessment with audit checklists, evidence collection, and remediation guidance.
Cursor Security Posture
Certifications and Attestations
| Certification | Status | Notes |
|---|---|---|
| SOC 2 Type II | Certified | Annual audit, report available on request |
| Penetration testing | Annual | Results shared under NDA (Enterprise) |
| Encryption at rest | AES-256 | All stored data |
| Encryption in transit | TLS 1.2+ | All API communications |
| Zero data retention | Available | Via Privacy Mode |
| GDPR compliance | Yes | EU data processing supported |
| HIPAA BAA | Not available (as of early 2026) | See HIPAA section |
Data Processing Architecture
Developer Machine
│
├─► Cursor Client ──► Cursor API (US/EU) ──► Model Provider
│ (local) (routing + auth) (OpenAI/Anthropic)
│ │
│ └─► Zero retention agreement
│
├─► Codebase Index ──► Embedding API ──► Turbopuffer (vectors)
│ (no plaintext stored)
│
└─► Local Settings (API keys, preferences)
(never transmitted)
Audit Checklist: SOC 2
CC6.1 — Logical Access Controls
[ ] SSO (SAML/OIDC) configured and enforced
[ ] MFA enabled at Identity Provider level
[ ] RBAC roles assigned: Owner, Admin, Member
[ ] Inactive users deprovisioned (SCIM or manual)
[ ] Access review completed (quarterly)
Evidence:
- SSO configuration screenshot from admin dashboard
- IdP MFA policy documentation
- User list export from Cursor admin
- SCIM sync logs (if applicable)
<Master Cursor Composer for multi-file AI editing, scaffolding, and refactoring.
Cursor Composer Workflows
Overview
Structure Composer work around explicit planning, small reviewed diffs, test evidence, and rollback rather than unattended multi-file generation.
Prerequisites
- A bounded issue, affected-file inventory, repository rules, and test commands.
- A recoverable branch and reviewer for material architectural, security, or data changes.
Instructions
- Request a plan and non-goals before any edits.
- Apply one coherent slice at a time, review the diff, and run its focused checks.
- Keep human decisions for API, security, migration, and dependency changes.
- Commit validated slices and revert/split failures rather than accepting a broad repair.
Output
- A sequence of small reviewed Composer-assisted changes with validation and rollback evidence.
Error Handling
| Condition | Safe response |
|---|---|
| Plan exceeds scope | Revise the request and reduce affected files. |
| Diff fails test or policy | Reject/revert the slice and diagnose within the stated boundary. |
| Composer needs sensitive context | Do not attach it; use sanitized interfaces or approved process. |
Examples
Ask Composer to plan a module-local refactor, accept only the first reviewed slice, run its focused test, and commit it. Stop if it proposes a dependency, migration, or unrelated repository change.
Master Cursor Composer (Cmd+I / Ctrl+I) for multi-file code generation, scaffolding, and coordinated refactoring. Composer is the primary tool for changes that span multiple files.
Composer Interface
┌─────────────────────────────────────────────────────────┐
│ Composer [Model ▾] │
│─────────────────────────────────────────────────────────│
│ Context: [src/api/] [prisma/schema.prisma] │
│─────────────────────────────────────────────────────────│
│ Create a CRUD API for products with: │
│ - Prisma model with id, name, price, category │
│ - API routes (GET list, GET by id, POST, PUT, DELETE) │
│ - Zod validation schemas │
│ - Unit tests with vitest │
│─────────────────────────────────────────────────────────│
│ ┌─ Changes ──────────────────────────────────────────┐ │
│ │ ✅ prisma/schema.prisma (+12 lines) │ │
│ │ ✅ src/api/products/route.ts (new file) │ │
│ │ ✅ src/api/products/[id]/route.ts (new file) │ │
│ │ ✅ src/schemas/product.ts (new file) │ │
│ │ ✅ tests/api/products.test.ts (new file) │ │
│ └────────────────────────────────────────────────────┘ │
│ [Apply All] [Review Changes] [Reject] │
└──────────────────────────────────Optimize context window usage in Cursor with @-mentions, context pills, and conversation strategy.
Cursor Context Management
Overview
Control what Cursor sees so each conversation has the minimum relevant, policy-permitted context required for a reliable answer or edit.
Prerequisites
- A task scope, approved privacy setting, data classification, and working ignore configuration.
- Relevant files/interfaces that can be shared without credentials, customer data, or unrelated repositories.
Instructions
- Start with the exact files, symbols, and constraints needed; avoid indiscriminate
@Codebaseuse. - Inspect context pills/attachments before submitting and remove stale or sensitive material.
- Start a new chat when topic or repository boundary changes.
- Verify generated output against the source and tests; context relevance never replaces validation.
Output
- A minimal documented context set and a scoped result that can be independently reviewed.
Error Handling
| Condition | Safe response |
|---|---|
| Context is stale or contradictory | Start a new topic-scoped chat with current files. |
| Sensitive path appears | Stop, remove it, repair exclusions, and follow exposure procedure. |
| Model misses key fact | Attach the authoritative file/interface rather than expanding the whole codebase. |
Examples
For a bug in one service, attach its handler, interface, and focused test, state the failing behavior, and ask for a minimal fix. If the conversation starts discussing a different service, open a new chat instead of piling on more context.
Optimize how Cursor AI uses context to produce accurate, relevant responses. Context is everything the model sees when generating a response -- managing it well is the single biggest lever for output quality.
Context Sources
Cursor assembles context from multiple sources before each AI request:
┌─ Always Included ─────────────────────────────────────┐
│ System prompt (Cursor internal) │
│ Active .cursor/rules/*.mdc with alwaysApply: true │
│ Current file (for Tab, Inline Edit) │
└───────────────────────────────────────────────────────┘
┌─ Conditionally Included ──────────────────────────────┐
│ Selected code (highlighted before Cmd+L/Cmd+K) │
│ @-mention targets (@Files, @Folders, @Code) │
│ Glob-matched rules (.mdc with matching globs) │
│ Conversation history (prior turns in chat) │
│ Open editor tabs (lightweight reference) │
└───────────────────────────────────────────────────────┘
┌─ On-Demand (explicit @-mention) ──────────────────────┐
│ @Codebase → semantic search across indexed files │
│ @Docs → crawled external documentation │
│ @Web → live web search resultsCreate effective custom prompts for Cursor AI using project rules, prompt engineering patterns, and reusable templates.
Cursor Custom Prompts
Overview
Create reusable prompts that encode approved engineering practice without injecting secrets, bypassing repository controls, or replacing human review.
Prerequisites
- A defined task class, source-of-truth repository rules, and a maintainer for prompt changes.
- A non-sensitive evaluation fixture and review path for any shared prompt.
Instructions
- State the scope, inputs, constraints, acceptance checks, and explicit non-goals.
- Keep prompts free of credentials, customer data, and contradictory instructions; reference reviewed rules rather than duplicating them.
- Evaluate the prompt against a fixture, inspect the diff/output, and version shared prompts through normal review.
- Retire or revise prompts that produce policy, quality, or security regressions.
Output
- A versioned, scoped reusable prompt with expected checks and a named owner.
Error Handling
| Condition | Safe response |
|---|---|
| Prompt generates over-broad changes | Narrow its file/task constraints and require a diff review. |
| Prompt conflicts with repository rules | Treat rules as authoritative and update/remove the prompt. |
| Prompt includes sensitive data | Remove it, follow exposure procedure, and replace with sanitized placeholders. |
Examples
For a test-writing prompt, specify the exact target module, existing test framework, failure behavior, and command to run. Review the generated test diff and reject it if it changes production code or hard-codes secrets.
Create effective prompts for Cursor AI. Covers prompt engineering fundamentals, reusable templates stored in project rules, and advanced techniques for consistent, high-quality code generation.
Prompt Anatomy
A well-structured Cursor prompt has four parts:
1. CONTEXT → @-mentions pointing to relevant code
2. TASK → What you want done (specific, actionable)
3. CONSTRAINTS → Rules, patterns, limitations
4. FORMAT → How the output should look
Example: All Four Parts
@src/api/users/route.ts @src/types/user.ts ← CONTEXT
Create a new API endpoint for updating user profiles. ← TASK
Constraints: ← CONSTRAINTS
- Follow the same pattern as the users route
- Use Zod for input validation
- Return 400 for invalid input, 404 for missing user
- Only allow updating: name, email, avatarUrl
Return the endpoint code and the Zod schema as ← FORMAT
separate code blocks.
Prompt Templates
Template: Feature Implementation
@[existing-similar-feature] @[relevant-types]
Implement [feature name] following the pattern in [reference file].
Requirements:Debug AI suggestion quality, context issues, and code generation problems in Cursor.
Cursor Debug Bundle
Overview
Collect a minimal, redacted reproduction for a Cursor issue involving context, rules, indexing, model behavior, or extensions. Debug material may contain proprietary code or prompts, so scope and retention matter as much as reproducibility.
Prerequisites
- A named issue owner, Cursor version, affected workspace, and approved bug-report destination.
- Permission to inspect logs and settings, plus redaction rules for code, prompts, paths, tokens, and user data.
- A minimal reproducer that does not require customer data or production credentials.
Instructions
- Start with the smallest reproducible prompt, file set, rule set, and model configuration.
- Record versions, active context, indexing state, extensions, and redacted console errors.
- Remove proprietary code, credentials, identifiers, and full prompt/output text before sharing externally.
- Test the proposed resolution in a non-sensitive workspace and document its result before closing the issue.
Diagnose and fix AI suggestion quality issues in Cursor. Covers why AI generates wrong code, how to improve context, and systematic debugging workflows.
Diagnostic Framework
When AI suggestions are wrong, the cause is almost always one of these:
┌─ Context Problems (80% of issues) ───────────────────────┐
│ 1. Missing context: AI doesn't have the relevant code │
│ 2. Wrong context: AI has stale or irrelevant files │
│ 3. Too much context: context window overflow │
│ 4. No project rules: AI doesn't know your conventions │
└──────────────────────────────────────────────────────────┘
┌─ Model Problems (15% of issues) ─────────────────────────┐
│ 5. Wrong model for the task │
│ 6. Model hallucinating APIs or patterns │
└──────────────────────────────────────────────────────────┘
┌─ Prompt Problems (5% of issues) ─────────────────────────┐
│ 7. Ambiguous or vague instructions │
│ 8. Conflicting requirements in prompt │
└──────────────────────────────────────────────────────────┘
Debugging by Symptom
AI Uses Wrong API or Library Version
Symptom: Generated code uses React.createClass, old Express syntax, or deprecated patterns.
Root cause: Model training data includes old code. No project rules specifying versions.
Fix:
# .cursor/rules/stack-versions.mdc
---
description: "Tech stack version pinning"
globs: ""
alwaysApply: true
---
# Stack Versions (ALWAYS use these)
- React 19 with Server Components (NOT class components)
- Next.js 15 App Router (NOT Pages Router)
- TypeScript 5.7 strict mode
- Prisma 6 (NOT Sequelize or TypeORM)
- Tailwind CSS 4 (NOT sIntegrate VS Code extensions with Cursor IDE: compatibility, Open VSX registry, VSIX installation, conflict resolution, and essential extensions.
Cursor Extension Integration
Overview
Add extensions only when their publisher, permissions, data flow, compatibility, and maintenance risk are understood for the target repository.
Prerequisites
- Approved extension source, publisher verification, and workspace/data classification.
- A disposable profile or test workspace and a rollback method for extension settings.
Instructions
- Review publisher, permissions, license, update history, and network/data behavior.
- Test one extension in an isolated profile with a non-sensitive workspace.
- Check conflicts with Cursor, rules, completion providers, and repository tooling.
- Approve, document, and periodically review the extension; remove it on security or compatibility failure.
Output
- A tested extension decision with owner, version, permission/data assessment, and rollback path.
Error Handling
| Condition | Safe response |
|---|---|
| Extension conflicts or degrades editor behavior | Disable/remove it in the test profile and retain diagnostics. |
| Extension requests unapproved access | Do not install; seek security review or an approved alternative. |
| Update changes permissions | Hold update until the new permissions are reviewed. |
Examples
Test a formatter extension in a disposable profile against a sample repository, verify it does not transmit code or conflict with existing formatting, and then document the approved version. Remove it rather than disabling security controls if it conflicts.
Integrate VS Code extensions with Cursor IDE. Covers the Open VSX Registry, VSIX installation for Microsoft-exclusive extensions, conflict resolution with AI features, and recommended extension stacks.
Extension Marketplace: Key Difference from VS Code
Cursor uses the Open VSX Registry instead of Microsoft's VS Code Marketplace. This is because Microsoft's marketplace terms restrict access to VS Code products only.
Impact: Most popular extensions are on Open VSX. Some Microsoft-published extensions are not.
Available on Open VSX (works directly)
| Extension | Category | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ESLint | Linting | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Prettier | Formatting | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| GitLens | Git visualization | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Docker | Container management | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Python | Python language support | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Pylance | Python analysis (community build) | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Go | Go language support | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Rust Analyzer | Rust language support | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Tailwind CSS IntelliSense | CSS utilities | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|
cursor-git-integration
View full skill →
Integrate Git workflows with Cursor IDE: AI commit messages, @Git context, diff review, and conflict resolution.
ReadWriteEditBash(cmd:*)
Cursor Git IntegrationOverviewUse Cursor's Git features as a view and drafting aid while preserving repository branch protection, reviews, signed checks, and human ownership of commits/merges. Prerequisites
Instructions
Output
Error Handling
ExamplesReview a Cursor-generated diff, stage only its intended files, run the focused suite, and push a topic branch for review. If an accidental file is staged, unstage it and recheck the diff before committing. Leverage Cursor's AI features within Git workflows: AI-generated commit messages, Source Control PanelAccess with
AI-Generated Commit MessagesClick the sparkle/AI icon next to the commit message input. Cursor reads the staged diff and generates a message: Example output:
cursor-hello-world
View full skill →
Create your first project using Cursor AI features: Tab, Chat, Composer, and Inline Edit.
ReadWriteEditBash(cmd:*)
Cursor Hello WorldOverviewPractice Tab, Chat, Inline Edit, and Composer in a disposable sample project before using them on production code. Every proposed diff remains subject to normal review, tests, security checks, and repository rules. Instructions
A hands-on 10-minute walkthrough of Cursor's four core AI features: Tab Completion, Chat, Inline Edit, and Composer. Setup
Open the project in Cursor: Exercise 1: Tab CompletionCreate
Press Tab to accept the full suggestion, or Cmd+Right Arrow to accept word-by-word. Try These Prompts for TabType a comment describing what you want, then start the function:
Tab reads your comment and generates the implementation. Exercise 2: Chat (Cmd+L)Open Chat with Ask about your code:
Generate new code:
Debug a concept:
Chat responds with explanations and code snippets. Click Apply on any code block to insert it into your editor.
cursor-indexing-issues
View full skill →
Troubleshoot Cursor codebase indexing: stuck indexing, empty search, @codebase failures, and performance issues.
ReadWriteEditBash(cmd:*)
Cursor Indexing IssuesOverviewDiagnose missing, stale, slow, or over-broad codebase indexing while keeping sensitive and generated files excluded from AI context. Prerequisites
Instructions
Output
Error Handling
ExamplesWhen Diagnose and fix codebase indexing problems. Covers stuck indexing, empty search results, stale results, and performance optimization for large codebases. Quick Diagnosis
Fix: Stuck IndexingStep 1: Reduce ScopeCreate or update
cursor-install-auth
View full skill →
Install Cursor IDE and configure authentication across macOS, Linux, and Windows.
ReadWriteEditBash(cmd:*)
Cursor Install & AuthOverviewInstall Cursor, authenticate through the approved identity flow, and establish privacy settings before opening sensitive repositories. Do not treat local profiles or settings files as a secrets store. Instructions
Install Cursor IDE and authenticate your account. Covers all platforms, plan activation, and VS Code migration. InstallationmacOS
After install, drag Cursor.app to Applications. First launch may require: System Settings > Privacy & Security > Allow. Linux
Add to PATH for terminal launching:
WindowsDownload installer from cursor.com/download. Run the AuthenticationFirst Launch Sign-In
Plan ActivationAfter sign-in, your plan is automatically active:
|