Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Uses 1M context window to ingest an entire codebase and output a file-by-file migration plan. Supports JS to TS, React class to hooks, framework migrations, and more. Generates migration-plan.md with file inventory, dependency graph, migration order, file-by-file changes, estimated effort, and risk assessment.
.claude/skills/onewave-ai-full-codebase-migrator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 695% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -39% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 8% | 0% |
Leverage the full 1M token context window to ingest an entire codebase, understand its architecture end-to-end, and produce a comprehensive, file-by-file migration plan that a team can execute sequentially without conflicts.
references/migration-types.md -- supported migration types; when to use and when not to use this skill.references/ingestion.md -- architecture, glob patterns, metadata collection, read order, context budgeting, and dependency graph construction (Steps 0-2).references/workflow-detail.md -- per-file assessment, migration order, risk scoring, and effort estimation templates (Steps 3-6).references/output-template.md -- migration-plan.md and migration-plan.json templates, edge cases, and the final quality checklist (Steps 7-8).references/migration-types.md for supported types and fit.references/ingestion.md.references/ingestion.md.references/workflow-detail.md.references/workflow-detail.md.references/workflow-detail.md.references/workflow-detail.md and the effort calibration table in references/migration-types.md.references/output-template.md.Codebases too large for context, monorepos, partially migrated codebases, and codebases without tests each need adjusted handling. See references/output-template.md.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 35,150 | 15,366 | -56% | 1 | 1 | 0% | 6,222 | 1,014 | -84% | 0 | 0 | — |
case-02 | fail→fail | 35,993 | 8,083 | -78% | 1 | 1 | 0% | 6,213 | 1,197 | -81% | 0 | 0 | — |
case-03 | fail→fail | 21,327 | 4,627 | -78% | 1 | 1 | 0% | 3,728 | 1,044 | -72% | 0 | 0 | — |
case-04 | fail→pass | 2,296 | 14,522 | +532% | 1 | 1 | 0% | 427 | 3,394 | +695% | 0 | 0 | — |
case-05 | pass→pass | 10,797 | 7,451 | -31% | 1 | 1 | 0% | 2,003 | 1,903 | -5% | 0 | 0 | — |
case-06 | pass→pass | 8,882 | 32,103 | +261% | 1 | 1 | 0% | 1,480 | 6,097 | +312% | 0 | 0 | — |
case-07 | fail→pass | 16,307 | 12,254 | -25% | 1 | 1 | 0% | 2,563 | 2,555 | -0% | 0 | 0 | — |
case-08 | pass→pass | 15,616 | 14,149 | -9% | 1 | 1 | 0% | 2,279 | 3,100 | +36% | 0 | 0 | — |
case-09 | fail→pass | 12,792 | 9,488 | -26% | 1 | 1 | 0% | 1,949 | 2,188 | +12% | 0 | 0 | — |
case-10 | fail→pass | 17,004 | 6,362 | -63% | 1 | 1 | 0% | 2,665 | 1,629 | -39% | 0 | 0 | — |
case-11 | fail→fail | 14,701 | 5,849 | -60% | 1 | 1 | 0% | 2,137 | 1,602 | -25% | 0 | 0 | — |
case-12 | pass→pass | 11,172 | 7,937 | -29% | 1 | 1 | 0% | 1,679 | 1,786 | +6% | 0 | 0 | — |
case-13 | pass→pass | 14,376 | 7,949 | -45% | 1 | 1 | 0% | 2,390 | 1,931 | -19% | 0 | 0 | — |
case-18 | fail→pass | 14,646 | 11,735 | -20% | 1 | 1 | 0% | 2,480 | 2,689 | +8% | 0 | 0 | — |
case-14 | pass→pass | 15,626 | 16,204 | +4% | 1 | 1 | 0% | 2,208 | 2,908 | +32% | 0 | 0 | — |
case-15 | pass→pass | 11,577 | 8,334 | -28% | 1 | 1 | 0% | 1,529 | 1,705 | +12% | 0 | 0 | — |
case-16 | pass→pass | 16,829 | 13,326 | -21% | 1 | 1 | 0% | 2,661 | 2,475 | -7% | 0 | 0 | — |
case-17 | pass→pass | 14,718 | 14,121 | -4% | 1 | 1 | 0% | 2,677 | 2,983 | +11% | 0 | 0 | — |
case-19 | pass→pass | 9,550 | 3,566 | -63% | 1 | 1 | 0% | 1,640 | 1,299 | -21% | 0 | 0 | — |
case-20 | pass→pass | 12,022 | 5,967 | -50% | 1 | 1 | 0% | 2,148 | 1,709 | -20% | 0 | 0 | — |
case-21 | pass→pass | 9,091 | 2,614 | -71% | 1 | 1 | 0% | 1,509 | 1,101 | -27% | 0 | 0 | — |
case-22 | pass→pass | 15,996 | 13,452 | -16% | 1 | 1 | 0% | 2,409 | 2,816 | +17% | 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 20 counted toward the lift figure. The other 2 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 +23 percentage points is the difference between those two pass rates over the 20 comparable cases. 2 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.