Install any skill in seconds. Free to start, no credit card required.
Get Started Free →GUI desktop app only. Repo-specific bug reproduction guidance for Warp. Specializes the core reproduce-bug-report skill for logged-out Warp UI repros, exact reporter-version installs, and login-free onboarding.
.claude/skills/warpdotdev-gui-reproduce-bug-report-local/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -61% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -56% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 14% | 0% |
warpScope — GUI desktop app only. This skill applies to Warp's GUI desktop front-end (the app/ crate on the WarpUI pixel/GPU framework). It does not apply to the headless TUI front-end (crates/warp_tui; cell-grid TuiElement library under crates/warpui_core/src/elements/tui), which has its own components, tests, and change-verification workflow. For TUI work, see the tui-ui-guidelines, tui-testing, and tui-verify-change skills instead.
This skill specializes the core reproduce-bug-report skill (named in the specializes frontmatter field) and is not functional on its own. Before applying its guidance, confirm the parent skill is installed and resolvable at .agents/skills/reproduce-bug-report/SKILL.md. If it is missing, install it first by copying the skill directory from the source declared in the specializes_source frontmatter field (warpdotdev/common-skills:.agents/skills/reproduce-bug-report). Then continue with the guidance below.
This file is a companion to the core reproduce-bug-report skill. It does not redefine the shared Oz computer-use orchestration, artifact handling, safety rules, or reporting format. It specializes scope and setup for Warp bug reports.
When applying the core skill to Warp, ensure the parent prompt and child prompts include:
unknown.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 18,394 | 8,536 | -54% | 1 | 1 | 0% | 2,823 | 1,575 | -44% | 0 | 0 | — |
case-02 | fail→fail | 5,713 | 8,182 | +43% | 1 | 1 | 0% | 172 | 1,387 | +706% | 0 | 0 | — |
case-03 | fail→fail | 6,090 | 7,661 | +26% | 1 | 1 | 0% | 306 | 1,485 | +385% | 0 | 0 | — |
case-04 | fail→pass | 29,624 | 6,969 | -76% | 1 | 1 | 0% | 5,434 | 2,131 | -61% | 0 | 0 | — |
case-05 | fail→pass | 11,526 | 5,514 | -52% | 1 | 1 | 0% | 2,011 | 1,901 | -5% | 0 | 0 | — |
case-06 | fail→pass | 15,917 | 4,856 | -69% | 1 | 1 | 0% | 2,132 | 1,798 | -16% | 0 | 0 | — |
case-07 | fail→pass | 58,260 | 3,118 | -95% | 1 | 1 | 0% | 3,456 | 1,508 | -56% | 0 | 0 | — |
case-08 | pass→pass | 12,283 | 10,003 | -19% | 1 | 1 | 0% | 1,907 | 2,604 | +37% | 0 | 0 | — |
case-09 | fail→pass | 9,516 | 5,086 | -47% | 1 | 1 | 0% | 1,511 | 1,726 | +14% | 0 | 0 | — |
case-10 | fail→pass | 16,655 | 15,118 | -9% | 1 | 1 | 0% | 2,617 | 2,543 | -3% | 0 | 0 | — |
case-11 | fail→pass | 14,437 | 5,078 | -65% | 1 | 1 | 0% | 2,158 | 1,907 | -12% | 0 | 0 | — |
case-12 | pass→pass | 21,148 | 5,182 | -75% | 1 | 1 | 0% | 1,333 | 1,645 | +23% | 0 | 0 | — |
case-13 | fail→pass | 9,750 | 2,767 | -72% | 1 | 1 | 0% | 1,297 | 1,429 | +10% | 0 | 0 | — |
case-14 | fail→pass | 10,158 | 3,907 | -62% | 1 | 1 | 0% | 1,052 | 1,652 | +57% | 0 | 0 | — |
case-15 | fail→fail | 16,763 | 4,576 | -73% | 1 | 1 | 0% | 2,624 | 1,854 | -29% | 0 | 0 | — |
case-16 | fail→pass | 12,425 | 4,239 | -66% | 1 | 1 | 0% | 1,787 | 1,804 | +1% | 0 | 0 | — |
case-17 | fail→pass | 11,949 | 3,783 | -68% | 1 | 1 | 0% | 1,529 | 1,435 | -6% | 0 | 0 | — |
case-18 | pass→fail | 16,463 | 4,663 | -72% | 1 | 1 | 0% | 2,251 | 1,804 | -20% | 0 | 0 | — |
case-19 | fail→pass | 10,117 | 3,868 | -62% | 1 | 1 | 0% | 1,432 | 1,661 | +16% | 0 | 0 | — |
case-20 | fail→pass | 7,694 | 4,207 | -45% | 1 | 1 | 0% | 1,015 | 1,722 | +70% | 0 | 0 | — |
case-21 | fail→pass | 9,488 | 5,531 | -42% | 1 | 1 | 0% | 1,325 | 1,595 | +20% | 0 | 0 | — |
case-22 | pass→pass | 17,340 | 9,782 | -44% | 1 | 1 | 0% | 2,327 | 2,654 | +14% | 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. 22 cases were attempted, and 18 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +59 percentage points is the difference between those two pass rates over the 18 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
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.