Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Database management, forms, reports, and data operations with LibreOffice Base.
.claude/skills/lingxling-base/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 60% | 0% |
LibreOffice Base skill for creating, managing, and automating database workflows using the native ODB (OpenDocument Database) format.
Use this skill when:
bashsoffice --base
pythonimport uno def create_database(): local_ctx = uno.getComponentContext() resolver = local_ctx.ServiceManager.createInstanceWithContext( "com.sun.star.bridge.UnoUrlResolver", local_ctx ) ctx = resolver.resolve( "uno:socket,host=localhost,port=8100;urp;StarOffice.ComponentContext" ) smgr = ctx.ServiceManager doc = smgr.createInstanceWithContext("com.sun.star.sdb.DatabaseDocument", ctx) doc.storeToURL("file:///path/to/database.odb", ()) doc.close(True)
pythonimport uno def connect_to_mysql(host, port, database, user, password): local_ctx = uno.getComponentContext() resolver = local_ctx.ServiceManager.createInstanceWithContext( "com.sun.star.bridge.UnoUrlResolver", local_ctx ) ctx = resolver.resolve( "uno:socket,host=localhost,port=8100;urp;StarOffice.ComponentContext" ) smgr = ctx.ServiceManager doc = smgr.createInstanceWithContext("com.sun.star.sdb.DatabaseDocument", ctx) datasource = doc.getDataSource() datasource.URL = f"sdbc:mysql:jdbc:mysql://{host}:{port}/{database}" datasource.Properties["UserName"] = user datasource.Properties["Password"] = password doc.storeToURL("file:///path/to/connected.odb", ()) return doc
# MySQL
sdbc:mysql:jdbc:mysql://localhost:3306/database
# PostgreSQL
sdbc:postgresql://localhost:5432/database
# SQLite
sdbc:sqlite:file:///path/to/database.db
# ODBC
sdbc:odbc:DSN_NAMEbashsoffice --headless soffice --base # Base
bashpip install pyodbc # ODBC connectivity pip install sqlalchemy # SQL toolkit
bashkillall soffice.bin soffice --headless --accept="socket,host=localhost,port=8100;urp;"
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 20,478 | 19,044 | -7% | 1 | 1 | 0% | 3,892 | 4,011 | +3% | 0 | 0 | — |
case-02 | fail→pass | 8,177 | 5,139 | -37% | 1 | 1 | 0% | 1,558 | 2,085 | +34% | 0 | 0 | — |
case-03 | fail→pass | 19,725 | 15,799 | -20% | 1 | 1 | 0% | 2,989 | 3,633 | +22% | 0 | 0 | — |
case-04 | fail→fail | 16,193 | 9,421 | -42% | 1 | 1 | 0% | 2,408 | 2,924 | +21% | 0 | 0 | — |
case-21 | pass→pass | 12,841 | 10,088 | -21% | 1 | 1 | 0% | 1,848 | 2,876 | +56% | 0 | 0 | — |
case-05 | fail→pass | 12,736 | 9,549 | -25% | 1 | 1 | 0% | 2,238 | 2,519 | +13% | 0 | 0 | — |
case-06 | pass→pass | 9,000 | 5,362 | -40% | 1 | 1 | 0% | 1,483 | 1,968 | +33% | 0 | 0 | — |
case-07 | pass→pass | 13,306 | 10,955 | -18% | 1 | 1 | 0% | 1,941 | 2,690 | +39% | 0 | 0 | — |
case-08 | pass→pass | 6,176 | 4,474 | -28% | 1 | 1 | 0% | 1,019 | 1,684 | +65% | 0 | 0 | — |
case-09 | pass→pass | 6,290 | 5,728 | -9% | 1 | 1 | 0% | 808 | 1,835 | +127% | 0 | 0 | — |
case-10 | pass→pass | 10,883 | 4,790 | -56% | 1 | 1 | 0% | 1,673 | 1,772 | +6% | 0 | 0 | — |
case-11 | pass→pass | 12,090 | 3,731 | -69% | 1 | 1 | 0% | 1,947 | 1,648 | -15% | 0 | 0 | — |
case-12 | pass→pass | 5,495 | 2,877 | -48% | 1 | 1 | 0% | 738 | 1,590 | +115% | 0 | 0 | — |
case-13 | fail→pass | 10,362 | 11,983 | +16% | 1 | 1 | 0% | 1,903 | 3,037 | +60% | 0 | 0 | — |
case-14 | pass→pass | 8,788 | 5,385 | -39% | 1 | 1 | 0% | 1,344 | 1,952 | +45% | 0 | 0 | — |
case-15 | pass→pass | 11,697 | 9,989 | -15% | 1 | 1 | 0% | 1,562 | 2,432 | +56% | 0 | 0 | — |
case-16 | pass→pass | 13,770 | 10,951 | -20% | 1 | 1 | 0% | 2,278 | 3,022 | +33% | 0 | 0 | — |
case-17 | pass→pass | 17,958 | 12,044 | -33% | 1 | 1 | 0% | 2,467 | 3,055 | +24% | 0 | 0 | — |
case-18 | fail→pass | 16,490 | 15,936 | -3% | 1 | 1 | 0% | 2,665 | 3,751 | +41% | 0 | 0 | — |
case-19 | pass→pass | 9,192 | 7,709 | -16% | 1 | 1 | 0% | 1,437 | 2,466 | +72% | 0 | 0 | — |
case-20 | pass→pass | 6,499 | 5,606 | -14% | 1 | 1 | 0% | 1,124 | 2,101 | +87% | 0 | 0 | — |
case-22 | pass→pass | 7,213 | 11,493 | +59% | 1 | 1 | 0% | 1,400 | 2,570 | +84% | 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 +27 percentage points is the difference between those two pass rates over the 22 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.