$ loading_
Configure and manage agents, skills, prompts, and integrations in the editor.
The material indicates a prompt/documentation-style skill from an open-source repository, with no required secrets, no declared remote endpoints, and no evidence of independent code execution or data exfiltration. Based on the provided facts, overall risk is low, with only minor caution around limited maintenance metadata despite positive open-source auditability.
The material explicitly states that no keys or environment variables are required; no login credentials, API tokens, or other sensitive authentication data are requested, so credential exposure or abuse risk is low.
No remote endpoints are declared, and the system classifies it as prompt-only; there is no described behavior of sending user data to external services, so network egress risk is low.
The description shows a skill intended to guide work on the Chat Customizations Editor, mainly containing folder, interface, and testing guidance; there is no evidence that it independently starts processes, runs scripts, or invokes system capabilities.
The material is documentation/prompt-like; although it mentions workspace, user, extension, and plugin storage concepts, it does not show that the skill itself has direct read/write access to such data or requests excessive privileges.
The source points to the open-source microsoft/vscode repository on GitHub, making the code auditable, which is a strong risk-reducing factor; while community star and maintenance metadata for this specific item are limited, there are no red flags such as closed source, unknown origin, or suspicious distribution.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "chat-customizations-editor" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/vscode/main/.github/skills/chat-customizations-editor/SKILL.md 2. Save it as ~/.claude/skills/chat-customizations-editor/SKILL.md 3. Reload skills and tell me it's ready
Guide me through creating a new customer support agent in the Chat Customizations editor, including base instructions, system prompts, and recommended skills and plugin settings.
A step-by-step agent setup plan with recommended fields, content, and structure.
Review the prompts and hooks in my Chat Customizations editor, identify inconsistent naming, overlapping responsibilities, and optimization opportunities, then suggest a cleanup plan.
A configuration review with issue lists, naming recommendations, and a restructuring plan.
Explain how to connect an MCP server in the Chat Customizations editor, and list the required configuration checks, permission risks, and testing steps.
An MCP server integration guide with configuration points, risk notes, and a validation checklist.
Split-view management pane for AI customization items across workspace, user, extension, and plugin storage. Supports harness-based filtering (Local, Copilot CLI, Claude).
src/vs/sessions/AI_CUSTOMIZATIONS.md — always read before making changes, always update after.
| Folder | What |
|---|---|
src/vs/workbench/contrib/chat/common/ | ICustomizationHarnessService, ISectionOverride, IStorageSourceFilter — shared interfaces and filter helpers |
src/vs/workbench/contrib/chat/browser/aiCustomization/ | Management editor, list widgets (prompts, MCP, plugins), harness service registration |
src/vs/sessions/contrib/chat/browser/ | Sessions-window overrides (harness service, workspace service) |
src/vs/sessions/contrib/sessions/browser/ | Sessions tree view counts and toolbar |
When changing harness descriptor interfaces or factory functions, verify both core and sessions registrations compile.
IHarnessDescriptor — drives all UI behavior declaratively (hidden sections, button overrides, file filters, agent gating). See spec for full field reference.ISectionOverride — per-section button customization (command invocation, root file creation, type labels, file extensions).IStorageSourceFilter — controls which storage sources and user roots are visible per harness/type.IExternalCustomizationItemProvider / IExternalCustomizationItem — internal interfaces (in customizationHarnessService.ts) for extension-contributed providers that supply items directly. These mirror the proposed extension API types.Principle: the UI widgets read everything from the descriptor — no harness-specific conditionals in widget code.
chatSessionCustomizationProvider)The proposed API in src/vscode-dts/vscode.proposed.chatSessionCustomizationProvider.d.ts lets extensions register customization providers. Changes to IExternalCustomizationItem or IExternalCustomizationItemProvider must be kept in sync across the full chain:
| Layer | File | Type |
|---|---|---|
| Extension API | vscode.proposed.chatSessionCustomizationProvider.d.ts | ChatSessionCustomizationItem |
| IPC DTO | extHost.protocol.ts | IChatSessionCustomizationItemDto |
| ExtHost mapping | extHostChatAgents2.ts | $provideChatSessionCustomizations() |
| MainThread mapping | mainThreadChatAgents2.ts | provideChatSessionCustomizations callback |
| Internal interface | customizationHarnessService.ts | IExternalCustomizationItem |
When adding fields to IExternalCustomizationItem, update all five layers. The proposed API .d.ts is additive-only (new optional fields are backward-compatible and do not require a version bump).
Component explorer fixtures (see component-fixtures skill): aiCustomizationListWidget.fixture.ts, aiCustomizationManagementEditor.fixture.ts under src/vs/workbench/test/browser/componentFixtures/.
The management editor fixture supports a selectedSection option to render any tab. Each tab has Dark/Light variants auto-generated by defineThemedFixtureGroup.
Available fixture IDs (use with mcp_component-exp_screenshot):
| Fixture ID pattern | Tab shown |
|---|---|
chat/aiCustomizations/aiCustomizationManagementEditor/AgentsTab/{Dark,Light} | Agents |
chat/aiCustomizations/aiCustomizationManagementEditor/SkillsTab/{Dark,Light} | Skills |
chat/aiCustomizations/aiCustomizationManagementEditor/InstructionsTab/{Dark,Light} | Instructions |
chat/aiCustomizations/aiCustomizationManagementEditor/HooksTab/{Dark,Light} | Hooks |
chat/aiCustomizations/aiCustomizationManagementEditor/PromptsTab/{Dark,Light} | Prompts |
chat/aiCustomizations/aiCustomizationManagementEditor/McpServersTab/{Dark,Light} | MCP Servers |
…
Launch VS Code OSS in isolation for automation and multi-process debugging.
Generate or update session run commands for faster project startup and testing.
Investigate failed PR checks and iteratively fix CI issues faster.
Run chat performance benchmarks and memory leak checks for VS Code builds.
Run vscode.dev locally to test the VS Code workbench and Agents window.
Set up complete project scaffolds and development environments in VS Code.
Generate or update chat customization files for AI coding agents.
Manage CustomGPT agents, conversations, and content through MCP using natural language.
Customize Claude Code plugins for organization-specific tools, connectors, and workflows.
Create custom VS Code chat modes and prompts for specialized development workflows.
Integrate skills, MCP servers, and agent configs to strengthen coding agents.
Discover, install, and manage curated skills for any MCP-compatible agent.