Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use this skill when unskipping a test that was previously skipped.
.claude/skills/chromedevtools-fixing-skipped-tests/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -59% | 0% |
This skill outlines the workflow for fixing skipped tests in the DevTools codebase, typically given a Chromium bug link (e.g., crbug.com/1234567).
crbug.com/<bugid>. Extract the <bugid> from the link.fixed-<bugid>.devtools-version-control skill to create and switch branches appropriately.test/TestExpectations file for the <bugid> to find skipped tests..skip in the code, but rather by having a [ Skip ] expectation in test/TestExpectations.[ Skip ] expectation for one of the tests associated with the bug in test/TestExpectations (or change it to [ Pass Failure ] if you are investigating flakiness).npm run test path/to/foo.test.ts:test_name) using the guidelines from the devtools-verification skill. If you are dealing with flaky tests, you can use the --repeat=x flag (e.g. npm run test -- --repeat=20 path/to/foo.test.ts:test_name) to run the test multiple times to reproduce the flakiness. This flag works for both E2E and unit tests.[crbug.com/<bugid>] prefix from the test name string in the code if it is present.// TODO(crbug...): Flaky).test/TestExpectations, and verifying until all are passing.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→pass | 12,929 | 7,641 | -41% | 1 | 1 | 0% | 2,400 | 2,002 | -17% | 0 | 0 | — |
case-01 | fail→pass | 13,849 | 6,827 | -51% | 1 | 1 | 0% | 2,622 | 1,972 | -25% | 0 | 0 | — |
case-02 | fail→pass | 14,848 | 5,283 | -64% | 1 | 1 | 0% | 2,692 | 1,688 | -37% | 0 | 0 | — |
case-03 | fail→pass | 11,137 | 5,390 | -52% | 1 | 1 | 0% | 2,150 | 1,707 | -21% | 0 | 0 | — |
case-05 | pass→pass | 8,470 | 4,525 | -47% | 1 | 1 | 0% | 1,672 | 1,369 | -18% | 0 | 0 | — |
case-06 | pass→pass | 9,079 | 4,303 | -53% | 1 | 1 | 0% | 1,785 | 1,472 | -18% | 0 | 0 | — |
case-07 | fail→pass | 4,731 | 1,539 | -67% | 1 | 1 | 0% | 815 | 825 | +1% | 0 | 0 | — |
case-08 | fail→pass | 12,775 | 1,963 | -85% | 1 | 1 | 0% | 2,362 | 960 | -59% | 0 | 0 | — |
case-09 | fail→fail | 6,201 | 2,669 | -57% | 1 | 1 | 0% | 1,182 | 1,061 | -10% | 0 | 0 | — |
case-10 | pass→pass | 8,406 | 2,191 | -74% | 1 | 1 | 0% | 1,558 | 963 | -38% | 0 | 0 | — |
case-11 | pass→pass | 12,907 | 1,444 | -89% | 1 | 1 | 0% | 2,340 | 840 | -64% | 0 | 0 | — |
case-12 | pass→pass | 3,243 | 2,060 | -36% | 1 | 1 | 0% | 537 | 947 | +76% | 0 | 0 | — |
case-13 | pass→pass | 2,592 | 1,850 | -29% | 1 | 1 | 0% | 527 | 939 | +78% | 0 | 0 | — |
case-23 | pass→pass | 7,793 | 2,216 | -72% | 1 | 1 | 0% | 1,405 | 1,047 | -25% | 0 | 0 | — |
case-14 | fail→pass | 10,434 | 3,942 | -62% | 1 | 1 | 0% | 1,732 | 1,354 | -22% | 0 | 0 | — |
case-15 | fail→pass | 11,126 | 4,185 | -62% | 1 | 1 | 0% | 1,989 | 1,392 | -30% | 0 | 0 | — |
case-16 | pass→pass | 11,681 | 1,995 | -83% | 1 | 1 | 0% | 2,290 | 1,006 | -56% | 0 | 0 | — |
case-17 | pass→pass | 9,466 | 1,698 | -82% | 1 | 1 | 0% | 1,702 | 939 | -45% | 0 | 0 | — |
case-18 | pass→pass | 5,571 | 1,473 | -74% | 1 | 1 | 0% | 945 | 865 | -8% | 0 | 0 | — |
case-19 | fail→pass | 9,503 | 1,665 | -82% | 1 | 1 | 0% | 1,789 | 868 | -51% | 0 | 0 | — |
case-20 | fail→pass | 11,609 | 1,198 | -90% | 1 | 1 | 0% | 2,234 | 773 | -65% | 0 | 0 | — |
case-21 | fail→pass | 8,792 | 2,478 | -72% | 1 | 1 | 0% | 1,748 | 1,112 | -36% | 0 | 0 | — |
case-22 | pass→pass | 11,497 | 2,498 | -78% | 1 | 1 | 0% | 2,073 | 985 | -52% | 0 | 0 | — |
case-24 | pass→pass | 5,392 | 1,702 | -68% | 1 | 1 | 0% | 998 | 934 | -6% | 0 | 0 | — |
case-25 | pass→pass | 2,881 | 2,234 | -22% | 1 | 1 | 0% | 457 | 980 | +114% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 25 cases were attempted. The headline lift of +40 percentage points is the difference between those two pass rates over the 25 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.