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

88%

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%

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

The body is highly actionable and clearly sequenced with strong validation checkpoints, but it is monolithic (~310 lines with no external references) and repeats the launch/attach block three times, hurting token efficiency and progressive disclosure.

Suggestions

Extract the repeated launch/attach and restart command blocks into a single canonical sequence and reference it, instead of duplicating the code in three sections.

Split the Monaco editor compatibility matrix and troubleshooting recipes into a references file (e.g. MONACO.md, TROUBLESHOOTING.md) so SKILL.md stays a concise overview with one-level-deep links.

Move the persistent user-data-dir / auth rationale to one authoritative callout rather than restating it across Prerequisites, Launching, and Restarting.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and command-focused, but it repeats the launch block and attach retry loop verbatim in three places ('Core Workflow', 'Launching VS Code Extensions for Debugging', and 'Restarting') and restates the persistent user-data-dir rationale multiple times, which could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands throughout — launch flags, attach retry loops, fill/type/press workflows, JS eval fallbacks — with concrete refs and a worked chat-input example.	3 / 3
Workflow Clarity	Sequences multi-step processes explicitly (Build → Launch → Attach → Snapshot → Interact → Re-snapshot; Restart Workflow) with validation checkpoints (tab-list verification, 'Stop generating' polling loop, text-verification eval, re-snapshot after state changes).	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets all absent) and the SKILL.md is a single ~310-line monolith with all detail inline rather than split into one-level-deep reference files; organization is sectioned but content that could be externalized (e.g., the Monaco compatibility matrix) is not.	2 / 3
	Total	10 / 12 Passed

Description

100%

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

The description is strong: it names concrete actions, the specific tooling and target, and provides an explicit 'Use when...' trigger clause. It is concise, third-person, and clearly differentiated.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Launch and automate', 'interact with the VS Code UI, automate the chat panel, test the extension UI, or take screenshots' — naming the specific tool (CDP, @playwright/cli) and target surface.	3 / 3
Completeness	Clearly answers both 'what' (launch and automate VS Code Insiders with Copilot Chat via CDP) and 'when' (an explicit 'Use when...Triggers include...' clause), matching the level-3 anchor.	3 / 3
Trigger Term Quality	Includes explicit, natural triggers users would say — 'automate VS Code', 'interact with chat', 'test the UI', 'take a screenshot', 'launch with debugging' — with good coverage of phrasings.	3 / 3
Distinctiveness Conflict Risk	The narrow niche (VS Code Insiders + Copilot Chat + CDP via @playwright/cli) and specific triggers make it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: posit-dev/positron
Path: .agents/skills/launch/SKILL.md
Commit: b87c504

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.