Dev & Engineering ✓ Microsoft · Official vscodechat-customizationsplaywrightcomponent-testingmcp-server-managementtypescript

VS Code Chat Customizations Editor Skill

Guides developers through safe changes and testing for VS Code’s chat customization management UI.

FollowSkills review · FSRS-2.0
Use with care
52/ 100 5-point scale 2.6 / 5
1 2 3 4 5 6
1Trust15 / 25 · 3.0/5

The skill is scoped to Chat Customizations editor code paths and declares a limited Bash/npx Playwright tool pattern, showing some least-privilege awareness. It does not define user confirmation, sensitive-data flows, external-network behavior, rollback, or operational safety boundaries, so 10 points are deducted.

2Reliability8 / 20 · 2.0/5

It provides key folders, interface synchronization chains, test commands, fixture data requirements, and concrete layout diagnostics, making the happy path fairly clear. However, the referenced spec, sessions skill, component-fixtures skill, and launch skill are not included, and static review cannot verify runnable commands or failure feedback; 8 is appropriate under the static cap.

3Adaptability10 / 15 · 3.3/5

The intended audience is clear: maintainers working on the Chat Customizations editor, including Local, CLI, Claude harnesses and multiple customization types. Non-fit cases, trigger boundaries, input/output contracts, and Chinese-language support are not specified, so adaptability is limited.

4Convention9 / 15 · 3.0/5

The document is well organized and includes metadata, repository navigation, interfaces, tests, fixtures, CI, debugging guidance, and known fixture/product gaps. It lacks explicit versioning, changelog, named maintenance responsibility, and an independent update path, with several assumptions delegated to external skills.

5Effectiveness6 / 15 · 2.0/5

For narrowly defined VS Code maintenance tasks, the guidance is actionable, especially for interface synchronization, fixture construction, and layout diagnosis. It produces no directly usable deliverable and provides no statically verifiable representative result or alternative-cost comparison, so 6 is awarded under the static cap.

6Verifiability4 / 10 · 2.0/5

The repository materials include CI workflows, test commands, and fixture conventions, making some claims auditable. They do not clearly cover every key path of this skill, and no reproduction was executed in this review, so 4 is appropriate under the static cap.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 5b3e1be7be9e
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • This assessment is based only on static file review; tests, Playwright, compilation, and live-product debugging were not executed.
  • The skill depends on unavailable AI_CUSTOMIZATIONS.md, sessions, component-fixtures, and launch skills, so parts of the guidance cannot be independently reproduced from the supplied evidence.
  • The tool pattern declared in metadata does not fully match the component-screenshot MCP references and other external skill references in the body; actual permissions should be confirmed.
  • No malware, credential theft, covert exfiltration, or other explicit red-line risk was identified; Chinese-language support and mainland-China network reachability are not evidenced.
See the full review method →

What does this skill do, and when should you use it?

This skill targets development of the Chat Customizations editor in the VS Code repository, covering management UI for agents, skills, instructions, hooks, prompts, MCP servers, and plugins. It explains how to follow harness descriptors, storage-source filters, and cross-layer extension API synchronization rules. It also covers component fixtures, screenshot regression checks, layout diagnostics, and live Code OSS debugging. Its scope is limited to the editor described by `.github/skills/chat-customizations-editor/SKILL.md`; it does not describe the capabilities of the repository’s other skills.

It instructs developers to read src/vs/sessions/AI_CUSTOMIZATIONS.md before changes and update it afterward; locate chat common interfaces, the management editor, sessions-window overrides, and sessions tree code; keep changes to the proposed customization provider API synchronized across the extension API, IPC DTO, ExtHost, MainThread, and internal interface layers; populate component fixtures with data for each customization type; use npx @playwright/cli to connect to Code OSS, open the customization editor, switch sections, and inspect DOM layout; and run the specified unit test, client type-check, and layer-validation commands.

  1. A VS Code developer needs to add or modify management UI for agents, skills, prompts, MCP servers, or plugins.
  2. A developer changes harness descriptors, button overrides, or storage-source filtering and must verify both core and sessions registrations.
  3. An extension API contributor adds fields to `chatSessionCustomizationProvider` and needs to propagate them through the complete API and IPC mapping chain.
  4. A test developer maintains component screenshot fixtures and needs coverage for tabs, harnesses, or narrow layouts.
  5. A developer investigates list-height, reflow, or real-data layout problems that do not reproduce in mocked component fixtures.

What are this skill's strengths and limitations?

Pros
  • Provides concrete guidance for the editor’s folders, interfaces, API synchronization chain, and test fixtures.
  • Covers component screenshots, CI regression gates, live-product debugging, and common layout failure modes.
  • Explicitly requires consistency between core and sessions registrations and defines the five layers affected by extension API field changes.
  • Distributed with the MIT-licensed Code - OSS repository.
Limitations
  • Its scope is tightly limited to the Chat Customizations editor in the VS Code source tree rather than general chat customization development.
  • It depends on VS Code internal paths, interfaces, and mocked test services, so it is not designed for use outside this repository.
  • The source does not provide standalone installation steps, version requirements, or cross-platform validation evidence.
  • It requires shell and filesystem access plus `@playwright/cli`; some screenshot workflows also depend on the repository’s MCP component-screenshot tool.

How do you install this skill?

This skill is one of 61 skills in the microsoft/vscode repository and is located at .github/skills/chat-customizations-editor/SKILL.md. The source provides the repository URL, https://github.com/microsoft/vscode, but no standalone installation command or dedicated destination directory; place the file where the Agent Skills client can discover it. The repository as a whole is distributed under the MIT license.

How do you use this skill?

In a VS Code checkout, give a task such as: “Modify the Chat Customizations editor’s MCP Servers tab and add screenshot-fixture coverage.” Read src/vs/sessions/AI_CUSTOMIZATIONS.md first, make the changes using the documented folders and interfaces, and update the specification afterward. For UI verification, use the component fixtures or connect to a running Code OSS instance with npx @playwright/cli. The source lists ./scripts/test.sh --grep "applyStorageSourceFilter|customizationCounts", npm run typecheck-client, and npm run valid-layers-check; these assume an appropriate VS Code source-development environment.

FAQ

Is this for VS Code end users or VS Code source contributors?
It is for developers and test developers modifying the Chat Customizations editor in the VS Code source tree, not an end-user guide to operating the feature.
Can it be installed and run independently?
The source gives no standalone installation command or executable. The instructions depend on internal directories, services, and fixtures in `microsoft/vscode`, so it is intended for that repository’s development environment.
What is easiest to miss when changing the extension API?
A new `IExternalCustomizationItem` field must be synchronized across the proposed extension API, IPC DTO, ExtHost mapping, MainThread mapping, and internal interface.
Will every layout issue reproduce in component fixtures?
No. The source states that live-product reflow timing, narrow window sizes, and real data counts may not reproduce in fixed-size fixtures with mock data. Those issues should be investigated in running Code OSS.

More skills from this repository

All from microsoft/vscode

Dev & Engineering ✓ Microsoft · Official

VS Code Performance Investigation Workflow

Automate repeatable VS Code scenarios and collect performance and memory evidence.

Dev & Engineering ✓ Microsoft · Official

VS Code Configuration Policy Maintainer

Standardize VS Code policy registration, export, and validation.

Dev & Engineering ✓ Microsoft · Official

VS Code Integrated Browser Architecture

A practical architecture guide for safely changing VS Code's cross-process integrated browser.

Dev & Engineering ✓ Microsoft · Official

Code OSS Launch & Debug

Launch a built-from-source VS Code with isolated profiles, Playwright control, and multi-process debugging ports.

Dev & Engineering ✓ Microsoft · Official

Run Command Builder

Configure and update commands shown in a VS Code Agent Session's Run button.

Dev & Engineering ✓ Microsoft · Official

VS Code Insiders UI Automation

Automate VS Code Insiders and Copilot Chat through Playwright and CDP.

Dev & Engineering ✓ Microsoft · Official

Context7 Project Bootstrapper

Build a complete VS Code project scaffold using current library documentation.

Dev & Engineering ✓ Microsoft · Official

VS Code Chat Performance Lab

Benchmark chat rendering and detect memory growth across VS Code builds.

Dev & Engineering ✓ Microsoft · Official

VS Code Unit Test Runner

Run VS Code repository unit tests by file, test name, or compiled-output glob.

Dev & Engineering ✓ Microsoft · Official

VS Code Smoke Test Assistant

Run, filter, and debug VS Code end-to-end smoke tests.

Dev & Engineering ✓ Microsoft · Official

VS Code Integration Test Runner

Run and filter VS Code repository integration tests with the correct platform scripts.

Dev & Engineering ✓ Microsoft · Official

Memory Leak Audit

Systematically find and fix listener, lifecycle, and disposable leaks in VS Code code.

Dev & Engineering ✓ Microsoft · Official

Copilot Chat Troubleshooter

Explain unexpected agent behavior, latency, and tool failures from Copilot Chat debug logs.

Dev & Engineering ✓ Microsoft · Official

VS Code Smoke Test Failure Diagnosis

Diagnose and validate intermittent VS Code Electron smoke-test failures in Azure DevOps.

Dev & Engineering ✓ Microsoft · Official

GitHub Copilot SDK Upgrade Assistant

Upgrade and validate @github/copilot in the VS Code Copilot Chat project.

Dev & Engineering ✓ Microsoft · Official

Tool Rename Compatibility Check

Protect existing prompts and tool configurations when built-in tools are renamed.

Design & Frontend ✓ Microsoft · Official

VS Code Design Philosophy

Turn vague UI discomfort into concrete fixes using shared values, principles, and design moves.

Dev & Engineering ✓ Microsoft · Official

VS Code Agent Customization Assistant

Create, repair, and troubleshoot VS Code Agent customization files and their loading behavior.

Dev & Engineering ✓ Microsoft · Official

VS Code Crash Dump Symbolicator

Turn native VS Code crash dumps into readable backtraces with method names.

Dev & Engineering ✓ Microsoft · Official

Copilot Session Troubleshooter

Explain unexpected Copilot CLI behavior from session-log evidence.

Related skills