CtrlK
BlogDocsLog inGet started
Tessl Logo

launch

Launch and automate VS Code Insiders with the Copilot Chat extension using @playwright/cli via Chrome DevTools Protocol. Use when you need to interact with the VS Code UI, automate the chat panel, test the extension UI, or take screenshots. Triggers include 'automate VS Code', 'interact with chat', 'test the UI', 'take a screenshot', 'launch with debugging'.

68

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 workflow-sound: executable commands, validation checkpoints, recovery loops, and hard-won Monaco/CDP knowledge throughout. The weaknesses are duplication (the launch block appears twice) and a monolithic structure with no reference files despite being 320+ lines.

Suggestions

Consolidate the duplicated launch sequence: the 'Core Workflow' and 'Launching VS Code Extensions for Debugging' sections repeat nearly identical code blocks — keep one canonical launch section and reference it from the other.

Split the detailed Monaco Editor interaction matrix and the Troubleshooting section into reference files (e.g., references/monaco.md, references/troubleshooting.md) so SKILL.md stays a lean overview, and drop the kill-command duplication between Restart and Cleanup.

Remove or quarantine time-sensitive details (the '58 proposed APIs' count and 'vscode ^1.110.0-20260223' version pin) into a clearly labeled compatibility/deprecated note so they don't age the whole document.

DimensionReasoningScore

Conciseness

The full launch sequence (compile → code-insiders with --extensionDevelopmentPath/--remote-debugging-port/--user-data-dir → retry-attach → tab-list/snapshot) appears nearly verbatim twice ("Core Workflow" and "Launching VS Code Extensions for Debugging"), and the kill command repeats across "Restart Workflow" and "Cleanup". Version pins ("58 proposed APIs", "vscode ^1.110.0-20260223") are time-sensitive details outside any deprecated section. Not a 2 — the bulk is non-obvious operational knowledge Claude does not already know, not padding.

3 / 5

Actionability

Every section gives copy-paste-ready commands: the attach retry loop, `fill e51 "Hello from George!"`, polling until "Stop generating" disappears, a what-works/what-fails table for Monaco, a JS mouse-event fallback snippet, and OS-specific variants. Fully executable with the common cases covered.

5 / 5

Workflow Clarity

A six-step numbered core workflow with explicit checkpoints: attach-retry loop, "Verify you're connected to the right target (not about:blank)", poll for generation completion, re-snapshot after state changes, a restart-after-code-changes loop, and troubleshooting with recovery actions (wrong tab → close + reattach; stale ref → re-snapshot). Feedback loops are present throughout.

5 / 5

Progressive Disclosure

No bundle files exist; a 320-line SKILL.md inlines everything, including a full Monaco interaction matrix and troubleshooting that would fit naturally in reference files. Sections are well-organized with clear headers, but content that should be separate is inline. Not a 2 — navigation via headers is easy and structure is solid; not a 4/5 — the skill is far over the size where well-organized sections alone suffice, and nothing is split out.

3 / 5

Total

16

/

20

Passed

Description

91%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 description: concrete, tool-specific capabilities with an explicit Use-when clause and an enumerated trigger list. The only deductions are the second-person voice in the Use-when clause and a few generic trigger phrases that could fire for generic web-automation skills.

DimensionReasoningScore

Specificity

"Launch and automate VS Code Insiders with the Copilot Chat extension using @playwright/cli via Chrome DevTools Protocol" plus "interact with the VS Code UI, automate the chat panel, test the extension UI, or take screenshots" lists multiple concrete, tool-anchored actions (a 5), but the second-person "Use when you need to..." clause triggers the rubric's voice penalty, reducing it by 1. Not a 3 — coverage is comprehensive, not just 1-2 actions.

4 / 5

Completeness

Explicitly answers both what ("Launch and automate VS Code Insiders with the Copilot Chat extension using @playwright/cli via Chrome DevTools Protocol") and when (a "Use when..." clause plus an enumerated trigger list). Not a 4 — the when-guidance is fully explicit with concrete trigger phrases, not merely present.

5 / 5

Trigger Term Quality

"Triggers include 'automate VS Code', 'interact with chat', 'test the UI', 'take a screenshot', 'launch with debugging'" gives natural phrases a user would actually say, reinforced by the Use-when clause. Matches the comprehensive-synonyms anchor; no natural variant is obviously missing.

5 / 5

Distinctiveness Conflict Risk

The niche is clear (VS Code Insiders + Copilot Chat + CDP attach), but generic triggers like "take a screenshot" and "test the UI" overlap with generic web/Playwright automation skills — minor overlap risk with closely related skills. Not a 5 because several triggers are not VS Code-specific; not a 3 because the domain is far from generic.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
posit-dev/positron
Reviewed

Table of Contents

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.