@toolbeltai/skills 0.2.1 → 0.2.3

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@toolbeltai/skills",
-  "version": "0.2.1",
+  "version": "0.2.3",
   "description": "Official Toolbelt skills — named /toolbelt-* flows (start, analyze, find, entities, geo, stream, invite) that teach any MCP-capable agent to orchestrate Toolbelt's MCP tools end-to-end.",
   "license": "MIT",
   "homepage": "https://toolbelt.ai",

package/toolbelt-analyze/SKILL.md

@@ -18,7 +18,7 @@ compatibility: >
   before invocation.
 metadata:
   author: toolbeltai
-  version: "2.0"
+  version: "2.0.0"
   homepage: "https://toolbelt.ai/docs/sql"
 ---
 

package/toolbelt-entities/SKILL.md

@@ -16,7 +16,7 @@ compatibility: >
   before invocation.
 metadata:
   author: toolbeltai
-  version: "1.0"
+  version: "1.0.0"
   homepage: "https://toolbelt.ai/docs/toolbelt-entities"
 ---
 

package/toolbelt-find/SKILL.md

@@ -16,7 +16,7 @@ compatibility: >
   before invocation.
 metadata:
   author: toolbeltai
-  version: "1.0"
+  version: "1.0.0"
   homepage: "https://toolbelt.ai/docs/vectors"
 ---
 

package/toolbelt-geo/SKILL.md

@@ -16,7 +16,7 @@ compatibility: >
   before invocation.
 metadata:
   author: toolbeltai
-  version: "1.0"
+  version: "1.0.0"
   homepage: "https://toolbelt.ai/docs/geospatial"
 ---
 
@@ -139,7 +139,7 @@ uploaded asset. Store it as `sensor_table` for use in Phase 3.
 
 ## Phase 3: Run Geospatial Queries
 
-Run all three queries using `toolbelt_execute`. Pass `namespace_id` and `query`
+Run all three queries using `toolbelt_sql`. Pass `namespace_id` and `query`
 for each call. Collect results.
 
 **Note:** `ST_DISTANCE`, `ST_CONTAINS`, and `ST_MAKELINE` are Kinetica-native geospatial
@@ -235,5 +235,5 @@ and continue with remaining queries. Only halt on Phase 0–2 failures.
 | 0. Verify connection | `toolbelt_list_namespaces` |
 | 1. Resolve namespace | (from Phase 0 result) |
 | 2. Upload sensor data | `toolbelt_save`, `toolbelt_jobs`, `toolbelt_context` |
-| 3. Run geospatial queries | `toolbelt_execute` × 3 |
+| 3. Run geospatial queries | `toolbelt_sql` × 3 |
 | 4. Emit result | (structured output) |

package/toolbelt-invite/SKILL.md

@@ -15,7 +15,7 @@ compatibility: >
   before invocation.
 metadata:
   author: toolbeltai
-  version: "1.0"
+  version: "1.0.0"
   homepage: "https://toolbelt.ai/docs/multi-agent"
 ---
 

package/toolbelt-start/SKILL.md

@@ -15,7 +15,7 @@ compatibility: >
   before invocation.
 metadata:
   author: toolbeltai
-  version: "2.0"
+  version: "2.0.0"
   homepage: "https://toolbelt.ai/docs/mcp"
 ---
 
@@ -173,7 +173,7 @@ Call `toolbelt_connect`:
 
 Omit `extra_options` if `kafka_group_id` was not provided.
 
-Verify the table is queryable with `toolbelt_execute`:
+Verify the table is queryable with `toolbelt_sql`:
 ```json
 {
   "namespace_id": "<namespace_id>",
@@ -231,5 +231,5 @@ RESULT:
 | 1. Resolve namespace | (from Phase 0 result) |
 | 2. Inspect state | `toolbelt_context` |
 | 3. Add document | `toolbelt_save`, `toolbelt_jobs`, `toolbelt_context` |
-| 4. Connect Kafka | `toolbelt_connect`, `toolbelt_execute` |
+| 4. Connect Kafka | `toolbelt_connect`, `toolbelt_sql` |
 | 5. Ask a question | `toolbelt_search` |

package/toolbelt-stream/SKILL.md

@@ -16,7 +16,7 @@ compatibility: >
   simulated stream data.
 metadata:
   author: toolbeltai
-  version: "1.0"
+  version: "1.0.0"
   homepage: "https://toolbelt.ai/docs/streaming"
 ---
 
@@ -181,7 +181,7 @@ Call `toolbelt_context` to get the table name. Store as `stream_table`.
 
 ## Phase 3: Confirm Data Arrival
 
-Call `toolbelt_execute` to verify the stream table is queryable and report
+Call `toolbelt_sql` to verify the stream table is queryable and report
 the initial row count:
 
 ```sql
@@ -209,7 +209,7 @@ Record `final_row_count`. If `final_row_count > initial_row_count`, set
 
 ## Phase 4: Aggregation Queries
 
-Run the following aggregation queries via `toolbelt_execute`. Substitute
+Run the following aggregation queries via `toolbelt_sql`. Substitute
 `<stream_table>` with the resolved table name throughout.
 
 ### Query 1 — Per-sensor stats
@@ -264,7 +264,7 @@ Record `window_rows` (number of rows returned).
 ## Phase 5: Anomaly Detection
 
 Detect readings that deviate more than `anomaly_threshold` standard deviations
-from the per-sensor mean. Run via `toolbelt_execute`:
+from the per-sensor mean. Run via `toolbelt_sql`:
 
 ```sql
 SELECT
@@ -341,7 +341,7 @@ section and continue. Only halt on Phase 0–2 failures.
 | 0. Verify connection | `toolbelt_list_namespaces` |
 | 1. Resolve namespace | (from Phase 0 result) |
 | 2. Connect stream | `toolbelt_connect` (Kafka) or `toolbelt_save` + `toolbelt_jobs` + `toolbelt_context` (simulated) |
-| 3. Confirm data arrival | `toolbelt_execute` × 1–2 |
-| 4. Aggregation queries | `toolbelt_execute` × 2 |
-| 5. Anomaly detection | `toolbelt_execute` × 1 |
+| 3. Confirm data arrival | `toolbelt_sql` × 1–2 |
+| 4. Aggregation queries | `toolbelt_sql` × 2 |
+| 5. Anomaly detection | `toolbelt_sql` × 1 |
 | 6. Emit result | (structured output) |