launch

Launch Code OSS (VS Code from sources) into an isolated throwaway profile with unique debug ports so you can drive it with @playwright/cli AND attach a Node debugger via dap-cli in the same session. Use when working on VS Code itself and you want to interact with the running workbench, automate chat or UI flows, test UI features, take screenshots, set breakpoints in the renderer / extension host / main process, or combine UI driving with debugging.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable and well-sequenced with strong validation checkpoints, but the ~430-line body carries rationale and platform-internals padding that pushes against the token budget, and one referenced script path is not present in the bundle to verify.

Suggestions

Trim explanatory asides Claude already knows (e.g. 'Code OSS is a full Electron app and easily eats 1-4 GB', the 'Why a helper script and not just docs' preamble) to tighten conciseness without losing actionability.

Move the Windows shared-data-dir / APPLICATION_SHARED internals and the Playwright daemon socket-path mechanics into a dedicated references file, keeping SKILL.md a lean overview with one-level-deep pointers.

Verify the playwrightScripts/ directory and focus-chat-input.ts exist in the bundle, or correct the path so the in-body references resolve to real files.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but includes some explanation a competent Claude already knows (e.g. 'Code OSS is a full Electron app and easily eats 1-4 GB') and padded rationale blocks like 'Why a helper script and not just docs' and extended Playwright-session daemon internals that could be trimmed without losing actionability.	3 / 5
Actionability	Fully executable copy-paste-ready bash and PowerShell snippets cover launch, JSON capture, attach, snapshot, focus, paste, screenshots, restart, and cleanup, with specific flags, port mappings, and a concrete JSON contract.	5 / 5
Workflow Clarity	Multi-step flows are clearly sequenced with validation checkpoints: launch blocks until CDP readiness, focus-then-paste ordering with verify read-back, restart-after-source-changes, and a Troubleshooting section with feedback loops (snapshot -> diagnose -> retry) for risky driving operations.	5 / 5
Progressive Disclosure	Structure is good with clear section headers and one-level-deep references to real bundle files (scripts/launch.sh, launch.ps1, monaco-paste.sh, playwrightScripts/focus-chat-input.ts), but the body inlines substantial detail (Windows auth internals, session-daemon socket-path mechanics) that could live in separate references, and a referenced path (playwrightScripts/focus-chat-input.ts) has no corresponding directory present in the bundle.	3 / 5
	Total	16 / 20 Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concrete description that clearly states both capability and trigger conditions with low conflict risk. The only minor gap is trigger-term breadth - it favors tool names over the most colloquial phrasings a user might say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions - 'drive it with @playwright/cli', 'attach a Node debugger via dap-cli', 'set breakpoints in the renderer / extension host / main process' - with comprehensive coverage of the skill's launch+debug surface.	5 / 5
Completeness	Explicitly answers both what ('Launch Code OSS ... into an isolated throwaway profile with unique debug ports so you can drive it ... AND attach a Node debugger') and when ('Use when working on VS Code itself and you want to ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases are present ('automate chat or UI flows', 'test UI features', 'take screenshots', 'combine UI driving with debugging'), but it leans on tool names (@playwright/cli, dap-cli) over the simpler words a user might say; a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	The niche is clear and narrow - launching a Code OSS source build with CDP + DAP ports - with triggers ('working on VS Code itself') unlikely to fire for unrelated skills, so conflict risk is minimal.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: microsoft/vscode
Path: .agents/skills/launch/SKILL.md
Commit: 123cec2

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.