Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Add, remove, and manage page-level and visual-level filters on Power BI PBIR reports using pbi-cli. Invoke this skill whenever the user mentions "filter", "TopN filter", "top 10", "bottom 5", "relative date filter", "last 30 days", "categorical filter", "include values", "exclude values", "clear filters", "slicer filter", "page filter", "visual filter", or wants to restrict which data appears on a page or in a specific visual.
.claude/skills/minasaad1-power-bi-filters/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-22 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -46% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -16% | 0% |
Add and manage filters on PBIR report pages and visuals. Filters are stored in the filterConfig section of page.json (page-level) or visual.json (visual-level). No Power BI Desktop connection is needed.
bash# List all filters on a page pbi filters list --page page_abc123 # List filters on a specific visual pbi filters list --page page_abc123 --visual visual_def456
Returns each filter's name, type, field, and scope (page or visual).
Include or exclude specific values from a column:
bash# Include only East and West regions pbi filters add-categorical --page page1 \ --table Sales --column Region \ --values "East" "West"
The filter appears in the page's filterConfig.filters array. Power BI evaluates it as an IN-list against the specified column.
Show only the top (or bottom) N items ranked by a measure:
bash# Top 10 products by revenue pbi filters add-topn --page page1 \ --table Product --column Name \ --n 10 \ --order-by-table Sales --order-by-column Revenue # Bottom 5 by quantity (ascending) pbi filters add-topn --page page1 \ --table Product --column Name \ --n 5 \ --order-by-table Sales --order-by-column Quantity \ --direction Bottom
The --table and --column define which dimension to filter (the rows you want to keep). The --order-by-table and --order-by-column define the measure used for ranking. These can be different tables -- for example, filtering Product names by Sales revenue.
Direction defaults to Top (descending -- highest N). Use --direction Bottom for ascending (lowest N).
Filter by a rolling window relative to today:
bash# Last 30 days pbi filters add-relative-date --page page1 \ --table Calendar --column Date \ --period days --count 30 --direction last # Next 7 days pbi filters add-relative-date --page page1 \ --table Calendar --column Date \ --period days --count 7 --direction next
Period options: days, weeks, months, quarters, years. Direction: last (past) or next (future).
Add a filter to a specific visual instead of the whole page by including --visual:
bashpbi filters add-categorical --page page1 --visual vis_abc \ --table Sales --column Channel \ --values "Online"
bash# Remove a specific filter by name pbi filters remove --page page1 --name filter_abc123 # Clear ALL filters from a page pbi filters clear --page page1
Filter names are auto-generated unique IDs. Use pbi filters list to find the name of the filter you want to remove.
bash# 1. Add a date filter to the overview page pbi filters add-relative-date --page overview \ --table Calendar --column Date \ --period months --count 12 --direction last # 2. Add a TopN filter to show only top customers pbi filters add-topn --page overview \ --table Customer --column Name \ --n 20 \ --order-by-table Sales --order-by-column Revenue # 3. Verify pbi filters list --page overview
By default, every write command automatically syncs Power BI Desktop. When applying filters to multiple pages or visuals in sequence, Desktop reloads after each command.
Use --no-sync on the filters command group to batch all filter changes, then call pbi report reload once at the end:
bash# Suppress sync while applying filters pbi filters --no-sync add-categorical --page overview --table "Calendar Lookup" --column "Year" --values "2024" pbi filters --no-sync add-categorical --page details --table "Product Lookup" --column "Category" --values "Bikes" # Single reload when all filters are done pbi report reload
bashpbi --json filters list --page page1
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-22 | fail→pass | 11,787 | 2,334 | -80% | 1 | 1 | 0% | 2,045 | 1,511 | -26% | 0 | 0 | — |
case-10 | fail→pass | 12,678 | 1,719 | -86% | 1 | 1 | 0% | 2,072 | 1,320 | -36% | 0 | 0 | — |
case-20 | pass→fail | 14,078 | 7,743 | -45% | 1 | 1 | 0% | 2,656 | 2,302 | -13% | 0 | 0 | — |
case-01 | fail→pass | 17,557 | 3,351 | -81% | 1 | 1 | 0% | 3,113 | 1,672 | -46% | 0 | 0 | — |
case-02 | fail→pass | 14,867 | 3,513 | -76% | 1 | 1 | 0% | 2,579 | 1,713 | -34% | 0 | 0 | — |
case-03 | fail→pass | 8,607 | 2,328 | -73% | 1 | 1 | 0% | 1,718 | 1,451 | -16% | 0 | 0 | — |
case-04 | fail→pass | 11,872 | 2,496 | -79% | 1 | 1 | 0% | 2,233 | 1,484 | -34% | 0 | 0 | — |
case-05 | fail→pass | 12,860 | 2,098 | -84% | 1 | 1 | 0% | 2,211 | 1,388 | -37% | 0 | 0 | — |
case-06 | fail→pass | 5,411 | 2,325 | -57% | 1 | 1 | 0% | 870 | 1,440 | +66% | 0 | 0 | — |
case-07 | fail→pass | 7,275 | 2,001 | -72% | 1 | 1 | 0% | 1,280 | 1,359 | +6% | 0 | 0 | — |
case-08 | fail→pass | 8,062 | 2,864 | -64% | 1 | 1 | 0% | 1,360 | 1,535 | +13% | 0 | 0 | — |
case-09 | fail→pass | 7,541 | 1,260 | -83% | 1 | 1 | 0% | 1,105 | 1,231 | +11% | 0 | 0 | — |
case-11 | fail→pass | 9,987 | 1,713 | -83% | 1 | 1 | 0% | 1,551 | 1,335 | -14% | 0 | 0 | — |
case-12 | fail→pass | 13,086 | 2,183 | -83% | 1 | 1 | 0% | 2,299 | 1,444 | -37% | 0 | 0 | — |
case-13 | fail→pass | 9,673 | 1,965 | -80% | 1 | 1 | 0% | 1,564 | 1,396 | -11% | 0 | 0 | — |
case-14 | fail→pass | 15,275 | 2,328 | -85% | 1 | 1 | 0% | 2,417 | 1,408 | -42% | 0 | 0 | — |
case-21 | pass→pass | 9,644 | 8,141 | -16% | 1 | 1 | 0% | 1,651 | 2,368 | +43% | 0 | 0 | — |
case-15 | fail→pass | 21,515 | 3,951 | -82% | 1 | 1 | 0% | 3,576 | 1,765 | -51% | 0 | 0 | — |
case-16 | fail→pass | 11,980 | 1,674 | -86% | 1 | 1 | 0% | 1,805 | 1,287 | -29% | 0 | 0 | — |
case-17 | fail→pass | 16,796 | 1,899 | -89% | 1 | 1 | 0% | 2,465 | 1,318 | -47% | 0 | 0 | — |
case-18 | fail→pass | 15,638 | 2,720 | -83% | 1 | 1 | 0% | 2,303 | 1,536 | -33% | 0 | 0 | — |
case-19 | pass→pass | 7,479 | 7,909 | +6% | 1 | 1 | 0% | 1,415 | 2,350 | +66% | 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 +82 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.