Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to create, optimize, or audit migration guides for users switching from competitors. Also use when the user mentions "migration guide," "migrate from X," "switch to [product]," "import from X," or "data migration." For rebrand and redirects, use rebranding-strategy.
.claude/skills/kostja94-migration-page-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 60% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 46% | 0% |
| case-08 | ✓→✗ | ▼ Worse | 19% | 0% |
| case-14 | ✓→✗ | ▼ Worse | 2% | 0% |
Guides migration pages that help users switch from a competitor to your product. Reduces friction for switchers; often linked from alternatives pages. Common for SaaS, tools, and productivity apps.
When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read it for product, migration capabilities, and source platforms.
Identify:
| Section | Purpose | |---------|---------| | Headline | "Migrate from Competitor] to Product] in Minutes" | | Why switch | Brief; link to alternatives for full comparison | | What transfers | Data, structure, attachments; what's supported | | Steps | Numbered guide; screenshots or video | | Troubleshooting | Common issues, support link | | CTA | Start migration, try free, contact support |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 5,433 | 4,608 | -15% | 1 | 1 | 0% | 976 | 1,389 | +42% | 0 | 0 | — |
case-02 | fail→fail | 9,200 | 6,484 | -30% | 1 | 1 | 0% | 1,423 | 1,626 | +14% | 0 | 0 | — |
case-03 | pass→pass | 8,067 | 8,498 | +5% | 1 | 1 | 0% | 1,396 | 1,978 | +42% | 0 | 0 | — |
case-04 | fail→fail | 54,686 | 6,699 | -88% | 1 | 1 | 0% | 2,090 | 1,680 | -20% | 0 | 0 | — |
case-05 | fail→fail | 12,606 | 10,776 | -15% | 1 | 1 | 0% | 2,177 | 2,287 | +5% | 0 | 0 | — |
case-06 | pass→pass | 16,727 | 18,020 | +8% | 1 | 1 | 0% | 2,497 | 3,028 | +21% | 0 | 0 | — |
case-19 | pass→pass | 17,775 | 16,291 | -8% | 1 | 1 | 0% | 2,704 | 3,220 | +19% | 0 | 0 | — |
case-07 | fail→pass | 11,226 | 6,936 | -38% | 1 | 1 | 0% | 1,915 | 1,734 | -9% | 0 | 0 | — |
case-08 | pass→fail | 10,437 | 8,729 | -16% | 1 | 1 | 0% | 1,963 | 2,332 | +19% | 0 | 0 | — |
case-09 | fail→fail | 16,038 | 12,777 | -20% | 1 | 1 | 0% | 2,632 | 2,671 | +1% | 0 | 0 | — |
case-10 | fail→fail | 14,667 | 12,961 | -12% | 1 | 1 | 0% | 2,417 | 3,078 | +27% | 0 | 0 | — |
case-11 | fail→pass | 3,669 | 2,281 | -38% | 1 | 1 | 0% | 595 | 951 | +60% | 0 | 0 | — |
case-12 | pass→pass | 8,098 | 6,849 | -15% | 1 | 1 | 0% | 1,228 | 1,659 | +35% | 0 | 0 | — |
case-13 | fail→fail | 16,365 | 11,950 | -27% | 1 | 1 | 0% | 2,553 | 2,482 | -3% | 0 | 0 | — |
case-14 | pass→fail | 15,654 | 12,341 | -21% | 1 | 1 | 0% | 2,795 | 2,839 | +2% | 0 | 0 | — |
case-15 | pass→pass | 12,003 | 10,970 | -9% | 1 | 1 | 0% | 2,058 | 2,336 | +14% | 0 | 0 | — |
case-16 | pass→pass | 17,127 | 10,584 | -38% | 1 | 1 | 0% | 2,997 | 2,490 | -17% | 0 | 0 | — |
case-17 | pass→fail | 14,300 | 11,774 | -18% | 1 | 1 | 0% | 2,471 | 2,661 | +8% | 0 | 0 | — |
case-18 | fail→pass | 7,896 | 7,047 | -11% | 1 | 1 | 0% | 1,252 | 1,830 | +46% | 0 | 0 | — |
case-20 | pass→pass | 15,814 | 13,597 | -14% | 1 | 1 | 0% | 2,340 | 2,132 | -9% | 0 | 0 | — |
case-21 | pass→pass | 8,795 | 9,001 | +2% | 1 | 1 | 0% | 1,695 | 2,227 | +31% | 0 | 0 | — |
case-22 | pass→pass | 9,274 | 7,982 | -14% | 1 | 1 | 0% | 1,550 | 1,881 | +21% | 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. The headline lift of -20 percentage points is the difference between those two pass rates over the 22 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.