BD 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.
This skill automates UI bug reproduction in VS Code: writes a scenario, runs it against a dev build or Insiders, captures video with captions, per-step screenshots, a Playwright trace, and an HTML report. Handles the repetitive click-screenshot-click cycle.
Scores show quality at 84%, process at 45%. No critical issues, but the process score gap hints at friction—likely environment setup or launch requires manual steps. Single file, no scripts. Supports nine platforms including Claude, Cursor, DeepSeek. Security score maxed out.
Install if you need to quickly document bugs for issues or PRs. Caveat: the process score suggests rough edges in execution—check docs before first run.
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…
As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 45/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 100Steps. 18 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2895 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (5 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 323: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.