@bicharts/chart-mcp 0.6.96 → 0.6.97

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bicharts/chart-mcp",
-  "version": "0.6.96",
+  "version": "0.6.97",
   "description": "AI Data Components for Power BI, Excel, Fabric Apps and the web, over MCP: bivariate maps, what-if projections and about 90 everyday chart types, with selection and cross-filtering already wired. It profiles your table locally; the code it writes is yours and runs with no license.",
   "keywords": [
     "mcp",
@@ -47,8 +47,8 @@
   },
   "// dependencies": "NONE, deliberately. dist/ bundles every module the server uses, so a runtime dependency installs nothing it needs - it only makes npx fetch that package (and its tree) before the first start. Everything the bundle carries is a devDependency; scripts/verify-package.mjs fails the release if a dependency appears or a shipped file imports anything but Node's built-ins.",
   "devDependencies": {
-    "@bicharts/chart-host": "^0.6.96",
-    "@bicharts/shape-core": "^0.6.96",
+    "@bicharts/chart-host": "^0.6.97",
+    "@bicharts/shape-core": "^0.6.97",
     "@modelcontextprotocol/sdk": "^1.0.0",
     "@types/node": "^20.0.0",
     "@types/papaparse": "^5.3.14",

package/skills/bic-charts/SKILL.md

@@ -589,7 +589,7 @@ without naming:
 | how far apart the outcomes of several assumptions land | What-if scenarios |
 | every place drawn at the same size, because which are high or low matters more than where | World tile-grid cartogram (or US hex-tile cartogram for states) |
 | actual against a budget, plan or target, with the gap shown for each period or unit | Variance chart (budget vs actual) |
-| circling a group of points to see what sets them apart from the rest | Selection explainer (a preview type) - the lasso and the comparison are drawn inside the chart; put the other fields to compare in the same table; on a page, give it `selects` so a circled group filters the page (step 6) |
+| circling a group of points to see what sets them apart from the rest | Selection explainer (a preview type) - the lasso and the comparison are drawn inside the chart; put the other fields to compare in the same table (which ones: below); on a page, give it `selects` so a circled group filters the page (step 6) |
 
 If the list doesn't offer what you expected, read its notes: it names a type refused on a count
 when your table is small, and it says when `name_filter` hid description matches.
@@ -599,6 +599,11 @@ list even when the data fits. When `list_eligible_charts` doesn't list it for yo
 for this data right now, and ask how they want to go on. Don't silently draw a plain scatter in its place, and don't write the
 group statistics (what the circled points share, against the rest) into the app yourself: that comparison is the chart's.
 
+Which other fields to put in its query: 4 to 8 a reader would ask about that can differ across the plot - segments and
+categories (region, main channel), mix shares (online, retail, partner), size (population, a revenue band), and one or two
+measures at most. Leave out row keys, the axes and fields that just track an axis (revenue beside marketing spend): the
+panel tests every field, and each extra field makes the test for every field stricter.
+
 A chart that draws its own rate control needs the history and the goal, not the model's what-if parameter:
 leave the parameter's table (a `'Price Change'[Price Change]` column, say) out of its query. Grouping by it repeats
 every period once per parameter value - 12 months by 17 values is 204 rows for 12 points - and the chart's own