Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create a new sequentially numbered database migration with up/down SQL files
.claude/skills/ruvnet-migrate-create/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -13% | 0% |
Generate a new database migration with sequential numbering and up/down SQL file pair.
When you need to create a new database migration for schema changes such as creating tables, adding columns, creating indexes, or modifying constraints.
Glob to scan the migrations directory for existing migration files and find the highest number, then increment by 1 (zero-pad to 3 digits)<name>, choose the appropriate SQL template:create_ -> CREATE TABLE templateadd_ -> ALTER TABLE ADD COLUMN templatedrop_ -> DROP with safety checksindex -> CREATE INDEX templateNNN_<name>.up.sql with the appropriate SQL using IF NOT EXISTS for idempotencyNNN_<name>.down.sql with the reverse operation using IF EXISTSmcp__plugin_ruflo-core_ruflo__agentdb_pattern-search (ReasoningBank-routed; don't pass a namespace argument — pattern- tools ignore it).mcp__plugin_ruflo-core_ruflo__memory_store --namespace migrations to record the migration with number, name, status (pending), and file paths. The memory_* tool family routes by namespace; agentdb_hierarchical-* does NOT (it routes by tier working|episodic|semantic), so use memory_* here. See ruflo-agentdb ADR-0001 §"Namespace convention".bashnpx @claude-flow/cli@latest memory store --namespace migrations --key "migration-NNN_NAME" --value '{"number": NNN, "name": "NAME", "status": "pending"}'
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 9,685 | 6,692 | -31% | 1 | 1 | 0% | 2,195 | 867 | -61% | 0 | 0 | — |
case-02 | fail→fail | 5,879 | 3,529 | -40% | 1 | 1 | 0% | 1,289 | 787 | -39% | 0 | 0 | — |
case-03 | fail→fail | 8,528 | 3,864 | -55% | 1 | 1 | 0% | 1,832 | 715 | -61% | 0 | 0 | — |
case-04 | fail→fail | 6,353 | 5,324 | -16% | 1 | 1 | 0% | 1,459 | 965 | -34% | 0 | 0 | — |
case-05 | fail→fail | 4,298 | 4,681 | +9% | 1 | 1 | 0% | 1,089 | 1,023 | -6% | 0 | 0 | — |
case-06 | fail→fail | 7,140 | 4,632 | -35% | 1 | 1 | 0% | 1,527 | 892 | -42% | 0 | 0 | — |
case-07 | fail→fail | 3,812 | 5,528 | +45% | 1 | 1 | 0% | 804 | 950 | +18% | 0 | 0 | — |
case-08 | fail→fail | 10,661 | 4,239 | -60% | 1 | 1 | 0% | 2,244 | 660 | -71% | 0 | 0 | — |
case-09 | pass→pass | 10,015 | 2,987 | -70% | 1 | 1 | 0% | 2,161 | 1,155 | -47% | 0 | 0 | — |
case-10 | pass→fail | 6,286 | 6,128 | -3% | 1 | 1 | 0% | 1,258 | 1,874 | +49% | 0 | 0 | — |
case-11 | fail→pass | 3,738 | 1,733 | -54% | 1 | 1 | 0% | 719 | 874 | +22% | 0 | 0 | — |
case-12 | fail→fail | 7,874 | 2,481 | -68% | 1 | 1 | 0% | 1,397 | 1,104 | -21% | 0 | 0 | — |
case-13 | fail→pass | 6,866 | 2,330 | -66% | 1 | 1 | 0% | 1,326 | 1,055 | -20% | 0 | 0 | — |
case-14 | fail→pass | 8,179 | 2,349 | -71% | 1 | 1 | 0% | 1,572 | 996 | -37% | 0 | 0 | — |
case-15 | fail→pass | 10,763 | 3,899 | -64% | 1 | 1 | 0% | 2,228 | 1,314 | -41% | 0 | 0 | — |
case-16 | pass→pass | 1,708 | 1,291 | -24% | 1 | 1 | 0% | 332 | 756 | +128% | 0 | 0 | — |
case-17 | pass→pass | 5,931 | 2,270 | -62% | 1 | 1 | 0% | 1,085 | 1,019 | -6% | 0 | 0 | — |
case-18 | pass→pass | 7,535 | 1,071 | -86% | 1 | 1 | 0% | 1,389 | 674 | -51% | 0 | 0 | — |
case-19 | fail→pass | 8,575 | 3,575 | -58% | 1 | 1 | 0% | 1,569 | 1,367 | -13% | 0 | 0 | — |
case-20 | pass→pass | 7,543 | 8,718 | +16% | 1 | 1 | 0% | 1,704 | 2,427 | +42% | 0 | 0 | — |
case-21 | fail→fail | 4,564 | 9,213 | +102% | 1 | 1 | 0% | 781 | 2,201 | +182% | 0 | 0 | — |
case-22 | pass→fail | 13,545 | 4,603 | -66% | 1 | 1 | 0% | 3,055 | 809 | -74% | 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 13 counted toward the lift figure. The other 9 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 +14 percentage points is the difference between those two pass rates over the 13 comparable cases. 5 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.