**WORKFLOW SKILL** - Execute the end-to-end WingtipToys migration benchmark: clear samples\AfterWingtipToys, run the migration-toolkit against samples\WingtipToys, repair the generated app until Playwright acceptance tests pass, and write a numbered run report with embedded screenshots under dev-docs\migration-tests\wingtiptoys. WHEN: "run Wingtip migration", "test WingtipToys migration", "Wingtip benchmark", "migrate WingtipToys", "rerun Wingtip migration". INVOKES: migration-toolkit (scripts +
SkillScore86Maintained
Automatic
◆QA & Test Engineering pack
Last verified 8/19/2026
What it changes
Passed 16 of 19 test cases with the skill, and 3 of 19 without it.
Without skill18%
With skill86%
Checks it passed that the model alone missed
Stops timing after writing the test run report
Starts wall-clock timing before clearing the output folder
Identifies ./REPORT-TEMPLATE.md as the source report template
and 17 more in the full report
15 fixed4 passed either way3 still failing0 broke
Pass-rate lift
+68 pp
Tokens
+94%
Agent turns
0%
Response time
-55%
Model gemini-3.6-flashMeasured 8/19/2026v119 of 22 cases passed with skill · 19 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 15
Prompt
What dotnet command validates Phase 3 compilation of the migrated Blazor application?
case-15 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md245 linessingle file
WingtipToys Migration Test
End-to-end migration benchmark for the canonical WingtipToys Web Forms sample. This workflow uses the repository's migration toolkit as the public entry point, preserves the migrated application shape in samples\AfterWingtipToys\, and considers the run successful only when the existing Playwright acceptance tests pass.
Benchmark Integrity Rules
This workflow is a benchmark, so every run must start from scratch.
Required behavior
Start with the raw Web Forms source in samples\WingtipToys\.
Clear samples\AfterWingtipToys\ before each run.
Run migration-toolkit\scripts\bwfc-migrate.ps1 to produce the output for this run.
Repair only the fresh output produced during the current run.
Forbidden behavior
Do not restore or copy previously migrated content into samples\AfterWingtipToys\.
Do not use git history as migration input or repair content:
no git restore
no git checkout
no git show to pull old file contents into the run
no copying files from prior commits, branches, tags, or stashes
Do not reuse prior benchmark outputs from:
samples\AfterWingtipToys\
dev-docs\migration-tests\wingtiptoys\run*
session artifacts, temp folders, or prior migration snapshots
Do not treat an earlier repaired sample as the answer. The point of the run is to measure what the toolkit plus current repair work can achieve from scratch.
If a run uses prior migrated content or git-sourced repairs, the benchmark is invalid and must be restarted from a freshly cleared output folder.