CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

validate-ui-scenario

Use when reproducing a UI bug or verifying a fix by driving a real VS Code window end to end and capturing evidence. Writes a scenario file, runs it against a dev build or installed Insiders, and produces a captioned video, per-step screenshots, a Playwright trace, and an HTML report to attach to an issue or pull request.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

An excellent, highly actionable skill body: executable commands, a complete worked example, explicit validation checkpoints, and honest guidance on skipped steps and degraded evidence. Its only limitations are minor tightening opportunities and a monolithic single-file structure that could offload the long example to a reference file.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — it explains only harness-specific facts (the .cjs extension requirement, virtualized settings trees, ffmpeg discovery) that Claude could not know. Minor instances could be trimmed (e.g., some prose around target flags and the ffmpeg section), fitting 'efficient; minor instances of over-explanation'.

4 / 5

Actionability

Everything is executable: exact commands ('pnpm -C test/scenario run compile', 'node test/scenario/out/runScenario.js <scenario.cjs>'), a complete copy-paste-ready scenario file, field/flag reference tables, exit-code semantics, and per-platform ffmpeg install commands. The worked example covers the common case end to end.

5 / 5

Workflow Clarity

A clear Prepare → Write the scenario → Run it → Report back sequence with explicit validation checkpoints: the ffmpeg pre-flight check, exit-code meanings, skip/needs classification, re-render recovery ('node test/scenario/out/renderEvidenceChapters.js <run-dir>'), and a report-back checklist that surfaces degraded evidence. The example reinforces the full loop, including how a failing run is a successful reproduction.

5 / 5

Progressive Disclosure

No bundle files exist, so all content lives in a single ~190-line SKILL.md. Section structure is clear and content is well-placed, but the full worked scenario example and the field reference table could arguably live in a separate reference file, and the under-50-line simple-skill exception does not apply. This fits 'good structure; minor organization gaps' rather than the reference-split top anchor.

4 / 5

Total

18

/

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 description with an explicit trigger clause, third-person voice, and a comprehensive, concrete inventory of actions and output artifacts. The only weaknesses are a few missing natural trigger synonyms and minor overlap risk against closely related testing/exploration skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Writes a scenario file, runs it against a dev build or installed Insiders, and produces a captioned video, per-step screenshots, a Playwright trace, and an HTML report' — with comprehensive coverage of both inputs and outputs. It exceeds the 'several specific actions; minor gaps' anchor because the action set and artifact list leave no meaningful gaps.

5 / 5

Completeness

It explicitly answers 'when' with a concrete 'Use when reproducing a UI bug or verifying a fix by driving a real VS Code window end to end and capturing evidence' clause, and 'what' with the scenario/run/artifact actions. Both halves are explicit with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Natural phrases like 'reproducing a UI bug', 'verifying a fix', 'VS Code', 'video', and 'issue or pull request' match what users would actually say. A few natural variants are missing (e.g., 'record a video', 'regression', 'e2e'), so it falls just short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The niche is clear — end-to-end VS Code UI validation producing evidence artifacts — and unlikely to trigger for unrelated skills. However, 'verifying a fix' and 'driving a real VS Code window' have minor overlap with closely related skills (smoke tests, interactive launching) that the description alone does not disambiguate, fitting the 'mostly distinct; minor overlap risk' anchor.

4 / 5

Total

18

/

20

Passed

Validation

100%

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

.github/skills/validate-ui-scenario/SKILL.md

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.