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

89%

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

86%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.

The body is highly actionable with executable examples and well-structured progressive disclosure into real bundle files, and it documents genuinely non-obvious traps. It is somewhat verbose in a few repeated or over-justified sections, and its validation steps are advisory rather than a strict checklist.

Suggestions

Tighten the 'Parallel multi-instance pattern' section: the agent A and agent B blocks repeat the full launch+attach sequence — show the shared pattern once and note that each agent only varies PW_SESSION.

Compress the 'Why a helper script and not just docs' rationale to the three numbered traps; the framing about miscopied heredocs can be one line.

Make verification explicit in the core workflow (e.g. a numbered 'attach -> snapshot -> confirm target -> interact -> re-snapshot after changes -> verify input state before sending') so checkpoints read as a checklist rather than prose.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no elementary padding), but the ~339-line body has sections that could be tightened, e.g. the parallel multi-instance pattern repeats the launch+attach sequence and the 'why a helper script' rationale is verbose.	4 / 5
Actionability	Fully executable copy-paste-ready bash for launch, jq parsing, attach/snapshot, the monaco-paste helper with all flag variants, screenshots, restart, and cleanup, plus a port-to-use table covering the common cases.	5 / 5
Workflow Clarity	Clear sequenced workflows (launch -> parse JSON -> attach -> snapshot -> interact) with verification guidance and troubleshooting feedback loops, but the validation checkpoints are advisory prose rather than the explicit validate->fix->retry checklist of the anchor-5 example.	4 / 5
Progressive Disclosure	SKILL.md is an overview that delegates real mechanics to confirmed one-level-deep bundle files (scripts/launch.sh, scripts/monaco-paste.sh) and to the dap-cli skill, with clear relative-path references and per-helper usage guidance.	5 / 5
	Total	18 / 20 Passed

Description

92%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.

The description is specific, actionable, and clearly delineates both the capability and the triggering contexts, with strong natural-language triggers and minimal conflict risk. Its only minor weakness is relying on a couple of tool names that users may not say verbatim.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — drive via @playwright/cli, attach dap-cli debugger, automate chat/UI flows, take screenshots, set breakpoints across renderer/extension host/main process — covering the skill comprehensively.	5 / 5
Completeness	Explicitly answers both 'what' (launch Code OSS into an isolated throwaway profile with unique debug ports for UI driving + debugging) and 'when' ('Use when working on VS Code itself and you want to...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural trigger phrases ('working on VS Code itself', 'automate chat or UI flows', 'take screenshots', 'set breakpoints') but leans on tool names a user may not voice verbatim and misses a few synonyms.	4 / 5
Distinctiveness Conflict Risk	A very narrow niche (VS Code internals dev, launching Code OSS from sources with CDP + per-process debug ports) with triggers unlikely to fire for any other skill.	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: posit-dev/positron
Path: .agents/skills/launch/SKILL.md
Commit: 9bb0f27

Reviewed: about 21 hours 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.