Avishai Tzabary
Community@az0512124155azz-sys
A skill registry for VS Code core development, covering workbench debugging, agent host customization, performance profiling, testing, and git session operations.
Agent Skills by Avishai Tzabary
Showing 63 vetted skills indexed across 1 GitHub repositories.
launch
Launch Code OSS from sources into isolated profiles with unique debug ports for Playwright and dap-cli.
update-codex-sdk
Updates VS Code's bundled @openai/codex dependency and verifies the Codex Agent Host end to end.
github-copilot-upgrader
Upgrades the @github/copilot npm package and fixes resulting compilation and test failures.
init
Generate or update agent instruction files like AGENTS.md for AI coding agents.
agent-customization
Create and troubleshoot VS Code agent customization files including instructions, prompts, hooks, agents, and skills.
troubleshoot
Diagnose unexpected chat agent behavior by analyzing JSONL debug session logs.
project-setup-info-local
Scaffolds complete project structures for VS Code extensions, Next.js, Vite, MCP servers, and Python.
create-prompt
Create reusable .prompt.md prompt files for repeatable tasks.
project-setup-info-context7
Scaffolds complete project structures using context7 library documentation lookups.
create-skill
Creates reusable SKILL.md files that package conversational workflows into skills.
install-vscode-extension
Installs VS Code extensions by ID using the workbench.extensions.installExtension command.
create-instructions
Create .instructions.md files that codify project rules and coding conventions.
create-agent
Creates custom .agent.md agent definition files for specialized jobs.
chronicle
Analyze Copilot session history for standup reports, usage tips, and session search.
get-search-view-results
Retrieve current search results from the VS Code Search view via command.
create-hook
Create JSON hooks that enforce policies or automate agent lifecycle events.
code-oss-logs
Locate and read timestamped process logs from Code OSS dev builds.
chat-customizations-editor
Guides development and testing of the Chat Customizations management editor in Code OSS.
policy-and-managed-settings
Routes enterprise Copilot controls to runtime managed settings, VS Code policies, or extension policies.
memory-leak-audit
Audit TypeScript code for memory leaks in event listeners and disposable patterns.
component-fixtures
Create themed component fixtures for screenshot testing of VS Code UI widgets.
author-contributions
Identify files an author contributed to on a branch, tracing contributions through git renames.
symbolicate-crash-dump
Symbolicate native VS Code crash dumps into readable backtraces using electron-minidump.
azure-pipelines
Queue, monitor, and cancel Azure DevOps pipeline builds for VS Code validation.
Frequently Asked Questions About Avishai Tzabary
FAQPage SchemaWhat tasks can I accomplish with these VS Code development skills?▼
You can launch and debug Code OSS builds, run unit/integration/smoke tests, analyze heap snapshots and CPU profiles, fix CI failures, symbolicate crash dumps, author agent customization files (.agent.md, .instructions.md, SKILL.md), manage git session branches, and create or update pull requests.
Who are these skills designed for?▼
They target engineers working on the VS Code codebase itself — core workbench contributors, Copilot Chat and agent host developers, and maintainers handling Azure DevOps pipelines, accessibility compliance, theming, and performance investigations in the microsoft/vscode repository.
What are the prerequisites and dependencies for using these skills?▼
Most skills assume a local VS Code source checkout. Specific ones require the gh CLI for CI fixes, Azure CLI for flaky smoke-test diagnosis, macOS or Linux for crash dump symbolication, and @playwright/cli for UI scenario validation and screenshot capture.
How do the testing and performance skills work in practice?▼
Testing skills invoke scripts/test.sh, test-integration scripts, or npm run smoketest with grep filtering. Performance skills parse .heapsnapshot and .cpuprofile files, run chat perf benchmarks, capture renderer heap snapshots, and compare run summaries to detect memory leaks and regressions.
Can these skills manage git sessions and pull requests?▼
Yes. Dedicated skills commit changes with style-matched messages, create and update draft PRs, rebase session branches onto upstream, merge topic branches, run code reviews, act on submitted feedback, and fix failing CI checks directly from the session.