Browse agent skills

A

Agent Customization

microsoft

Streamline your VS Code agent customization process.

Chat Performance Testing

microsoft

Benchmark and validate chat UI performance in VS Code.

Accessibility

microsoft

Enhance VS Code UI with essential accessibility features.

Component Fixtures

microsoft

Streamline UI component testing with isolated fixtures.

Diagnosing Flaky Smoke Tests

microsoft

Streamline troubleshooting for VS Code smoke tests.

Chat Customizations Editor

microsoft

Manage AI customization items efficiently.

T

Tool Rename Deprecation

microsoft

Maintain backward compatibility during tool renaming.

VS Code Dev Workbench

microsoft

Run the VS Code web workbench locally for development.

P

Project Setup Info Local

microsoft

Streamline your VS Code project initialization process.

Code OSS Logs

microsoft

Access and analyze logs from Code OSS development builds.

Agent Host E2E Tests

microsoft

Streamline testing for agent host functionality.

Error Fixing Guidelines

microsoft

A structured approach to resolving telemetry errors in VS Code.

Sessions Management

microsoft

Essential guidelines for agents window development.

Unit Tests

microsoft

Efficiently run and manage unit tests in VS Code.

G

Generate Run Commands

microsoft

Automate task setup for your development environment.

VS Code Extension Release

cline

Streamline your VS Code extension publishing process.

I

Install VS Code Extension

microsoft

Effortlessly add extensions to your VS Code setup.

Chat Customization Generator

microsoft

Streamline AI agent customization for your codebase.

I

Integration Tests

microsoft

Run integration tests for the VS Code repository efficiently.

Symbolicate a native VS Code crash dump (.dmp) using electron-minidump. Use when given a crash dump file, asked to symbolicate a crash, resolve missing method names in a native crash backtrace, or attach Electron/Insiders/Stable symbol files. VS Code team members only; requires macOS or Linux.

Fix a microsoft/vscode issue that the VS Code Sweeper reviewed as agent-fixable. Fetches the review's fix spec from the sweeper's public state repo, implements the narrow fix in the current vscode checkout, and — after showing the diff — opens a draft PR. Use when asked to fix a vscode issue with the sweeper-fix skill, a vscodesweeper record, or a sweeper fix spec.

Use when running VS Code smoke tests or working on smoke-test CI steps. Covers npm run smoketest / smoketest-no-compile, grep filtering tests, and a temporary repeat-loop technique for tracking down flaky smoke tests in CI.

Use whenever adding, modifying, or reviewing any Copilot, agent, LLM, AI, tool, permission, sandbox, MCP, model, telemetry, feature-gate, setting, configuration, or enterprise control—especially anything an organization or administrator may need to manage. Start here to decide whether it belongs in runtime managed settings, a typed SDK contract, VS Code configuration policy, extension policy, or a split implementation. Run on every new Copilot/agent/LLM control and ANY change that adds a `policy:` field.

Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under `src/vs/platform/browserView` and `src/vs/workbench/contrib/browserView`.