@toolbeltai/skills 0.1.1 → 0.1.2

package/data-blend/SKILL.md

@@ -1,26 +1,23 @@
 ---
 name: data-blend
 description: >
-  Join and correlate multiple datasets in a single Toolbelt namespace without
-  writing infrastructure code. Toolbelt is a multi-modal data platform combining
-  SQL analytics, vector search, and real-time streaming. Uploads two or more CSV
-  tables, then runs cross-table JOIN queries to surface relationships between
-  datasets. Use when an AI agent needs to combine data from different sources —
-  orders with customers, sensors with metadata, events with dimensions — and
-  answer questions that span multiple tables.
+  Upload two or more CSV tables into one Toolbelt namespace and run cross-table
+  JOIN queries to correlate them. Use when an agent has related datasets that
+  need to be combined — orders + customers, sensors + metadata, events +
+  dimensions, transactions + accounts — and questions span multiple tables that
+  share a key. NOT for single-table analysis (use sql-analyst), unstructured
+  text (use knowledge-graph), or entity-level relationship mapping across free
+  text (use knowledge-graph).
 license: MIT
 compatibility: >
   Requires a Toolbelt account (provision free at https://toolbelt.ai) and an
-  MCP-compatible AI agent (Claude Code, Claude Desktop, or any client that
-  supports MCP server connections). MCP connection must be pre-established
+  MCP-compatible AI agent (Claude Code, Claude Desktop, OpenClaw, or any client
+  that supports MCP server connections). MCP connection must be pre-established
   before invocation.
 metadata:
   author: toolbeltai
   version: "1.0"
-  openclaw:
-    emoji: "🔀"
-    homepage: "https://toolbelt.ai/docs/sql"
-    skillKey: "data-blend"
+  homepage: "https://toolbelt.ai/docs/sql"
 ---
 
 Upload multiple tables and run cross-table JOIN queries using Toolbelt MCP tools.

package/geo-analyst/SKILL.md

@@ -1,25 +1,23 @@
 ---
 name: geo-analyst
 description: >
-  GPU-accelerated geospatial analytics powered by Toolbelt MCP. Toolbelt is a
-  multi-modal data platform combining SQL analytics, vector search, and real-time
-  streaming. Uploads lat/lon sensor data, runs geospatial SQL queries (distance,
-  point-in-polygon, track creation), and emits structured results. Use when an AI
-  agent needs to analyze spatial data, compute distances, test point containment,
-  or build movement tracks without writing infrastructure code.
+  GPU-accelerated geospatial analytics on Toolbelt — distance, point-in-polygon
+  containment, nearest-neighbor, track creation, spatial joins. Upload lat/lon
+  sensor readings or WKT geometries, then run spatial SQL queries. Use when an
+  agent needs to answer geographic questions — how close is X to Y, which points
+  fall inside a region, along which route, coverage overlap, or movement tracks
+  from raw GPS. NOT for non-spatial tabular analysis (use sql-analyst) or
+  document content (use vector-search).
 license: MIT
 compatibility: >
   Requires a Toolbelt account (provision free at https://toolbelt.ai) and an
-  MCP-compatible AI agent (Claude Code, Claude Desktop, or any client that
-  supports MCP server connections). MCP connection must be pre-established
+  MCP-compatible AI agent (Claude Code, Claude Desktop, OpenClaw, or any client
+  that supports MCP server connections). MCP connection must be pre-established
   before invocation.
 metadata:
   author: toolbeltai
   version: "1.0"
-  openclaw:
-    emoji: "🌍"
-    homepage: "https://toolbelt.ai/docs/geospatial"
-    skillKey: "geo-analyst"
+  homepage: "https://toolbelt.ai/docs/geospatial"
 ---
 
 Execute GPU-accelerated geospatial analytics end-to-end using Toolbelt MCP tools.

package/knowledge-graph/SKILL.md

@@ -1,26 +1,23 @@
 ---
 name: knowledge-graph
 description: >
-  Automatically extract entities and relationships from any document and explore
-  the results as a knowledge graph — no schema or ontology required. Toolbelt is
-  a multi-modal data platform combining SQL analytics, vector search, and
-  real-time streaming. Upload a document, then surface entities, relationship
-  types, and hidden connections via graph queries. Use when an AI agent needs to
-  turn unstructured text into structured, navigable knowledge without writing any
-  extraction code.
+  Upload a document; Toolbelt automatically extracts entities (people, orgs,
+  places, concepts) and their relationships into a knowledge graph — no schema
+  or ontology required. Query the graph with Cypher or natural language to
+  trace connections. Use when an agent needs to map who-relates-to-whom, surface
+  hidden links across documents, answer multi-hop relationship questions, or
+  identify central entities in a corpus. NOT for flat semantic passage retrieval
+  (use vector-search) or tabular analytics (use sql-analyst).
 license: MIT
 compatibility: >
   Requires a Toolbelt account (provision free at https://toolbelt.ai) and an
-  MCP-compatible AI agent (Claude Code, Claude Desktop, or any client that
-  supports MCP server connections). MCP connection must be pre-established
+  MCP-compatible AI agent (Claude Code, Claude Desktop, OpenClaw, or any client
+  that supports MCP server connections). MCP connection must be pre-established
   before invocation.
 metadata:
   author: toolbeltai
   version: "1.0"
-  openclaw:
-    emoji: "🕸️"
-    homepage: "https://toolbelt.ai/docs/knowledge-graph"
-    skillKey: "knowledge-graph"
+  homepage: "https://toolbelt.ai/docs/knowledge-graph"
 ---
 
 Extract a knowledge graph from a document and explore it autonomously using

package/multi-agent-workspace/SKILL.md

@@ -1,25 +1,22 @@
 ---
 name: multi-agent-workspace
 description: >
-  Set up a shared Toolbelt workspace for multi-agent collaboration. Toolbelt is a
-  multi-modal data platform combining SQL analytics, vector search, and real-time
-  streaming. Uploads a document to a namespace, generates a shareable asset URL,
-  and emits connection instructions for a second agent to join the same workspace.
-  Use when two or more agents need to share data, or when handing off context
-  between sessions without duplicating ingestion work.
+  Set up a Toolbelt namespace that multiple agents can share. Uploads a document,
+  then emits a connection URL another agent can use to join the same workspace
+  without re-ingesting. Use when handing off context between agents or sessions,
+  when two agents need to collaborate on the same dataset, or when pre-staging
+  data for a downstream agent. NOT needed for single-agent workflows — use
+  run-toolbelt instead.
 license: MIT
 compatibility: >
   Requires a Toolbelt account (provision free at https://toolbelt.ai) and an
-  MCP-compatible AI agent (Claude Code, Claude Desktop, or any client that
-  supports MCP server connections). MCP connection must be pre-established
+  MCP-compatible AI agent (Claude Code, Claude Desktop, OpenClaw, or any client
+  that supports MCP server connections). MCP connection must be pre-established
   before invocation.
 metadata:
   author: toolbeltai
   version: "1.0"
-  openclaw:
-    emoji: "🤝"
-    homepage: "https://toolbelt.ai/docs/multi-agent"
-    skillKey: "multi-agent-workspace"
+  homepage: "https://toolbelt.ai/docs/multi-agent"
 ---
 
 Set up a shared Toolbelt workspace and generate collaboration artifacts for a

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@toolbeltai/skills",
-  "version": "0.1.1",
+  "version": "0.1.2",
   "description": "Official Toolbelt skills for Claude Code and MCP agents — run-toolbelt, geo-analyst, knowledge-graph, sql-analyst, vector-search, streaming-analyst, multi-agent-workspace, data-blend.",
   "license": "MIT",
   "homepage": "https://toolbelt.ai",

package/run-toolbelt/SKILL.md

@@ -1,12 +1,12 @@
 ---
 name: run-toolbelt
 description: >
-  Toolbelt is a multi-modal data platform combining SQL analytics, vector search,
-  and real-time streaming — all queryable through natural language via MCP. This
-  skill provisions a namespace, ingests documents, connects Kafka topics, and
-  answers questions over the ingested data, end-to-end and autonomously. Use when
-  an AI agent needs to onboard to Toolbelt, add assets, connect a streaming source,
-  or run queries without any human interaction.
+  Provision a Toolbelt namespace, ingest a document or Kafka stream, and answer
+  a question end-to-end — autonomously, without human steps. Use when an agent
+  needs to set up a fresh Toolbelt workspace, add assets from scratch, connect a
+  streaming source, or run a complete ingest→query pipeline. NOT for querying
+  data that is already ingested — use sql-analyst, vector-search, or
+  knowledge-graph for that.
 license: MIT
 compatibility: >
   Requires a Toolbelt account (provision free at https://toolbelt.ai) and an
@@ -16,10 +16,7 @@ compatibility: >
 metadata:
   author: toolbeltai
   version: "2.0"
-  openclaw:
-    emoji: "🧰"
-    homepage: "https://toolbelt.ai/docs/mcp"
-    skillKey: "run-toolbelt"
+  homepage: "https://toolbelt.ai/docs/mcp"
 ---
 
 Execute Toolbelt end-to-end autonomously using the Toolbelt MCP tools.

package/sql-analyst/SKILL.md

@@ -1,24 +1,23 @@
 ---
 name: sql-analyst
 description: >
-  Text-to-SQL analyst powered by Toolbelt MCP. Toolbelt is a multi-modal data
-  platform combining SQL analytics, vector search, and real-time streaming.
-  Uploads a CSV, auto-generates schema context, then answers natural language
-  questions by generating and executing SQL. Use when an AI agent needs to analyze
-  tabular data without writing queries manually — upload, ask, get answers.
+  Upload a CSV and answer natural-language questions by generating and executing
+  SQL. Covers totals, averages, group-by, filtering, and single-table joins on
+  tabular data. Use when an agent has structured rows/columns and needs analytical
+  answers — trends, breakdowns, comparisons, rankings. NOT for unstructured
+  documents (use knowledge-graph or vector-search), lat/lon or WKT data (use
+  geo-analyst), live streams (use streaming-analyst), or multi-table JOINs across
+  independent datasets (use data-blend).
 license: MIT
 compatibility: >
   Requires a Toolbelt account (provision free at https://toolbelt.ai) and an
-  MCP-compatible AI agent (Claude Code, Claude Desktop, or any client that
-  supports MCP server connections). MCP connection must be pre-established
+  MCP-compatible AI agent (Claude Code, Claude Desktop, OpenClaw, or any client
+  that supports MCP server connections). MCP connection must be pre-established
   before invocation.
 metadata:
   author: toolbeltai
   version: "1.0"
-  openclaw:
-    emoji: "📊"
-    homepage: "https://toolbelt.ai/docs/sql"
-    skillKey: "sql-analyst"
+  homepage: "https://toolbelt.ai/docs/sql"
 ---
 
 Upload tabular data and answer natural language questions about it using

package/streaming-analyst/SKILL.md

@@ -1,27 +1,23 @@
 ---
 name: streaming-analyst
 description: >
-  Real-time streaming analytics powered by Toolbelt MCP. Toolbelt is a
-  multi-modal data platform combining SQL analytics, vector search, and real-time
-  streaming. Connects a Kafka topic, runs windowed aggregation queries, and detects
-  anomalies using standard deviation. Falls back to simulated stream data when no
-  Kafka broker is provided. Use when an AI agent needs to analyze streaming data —
-  IoT sensors, event logs, security events, or fleet telemetry — without writing
-  infrastructure code.
+  Connect a live Kafka topic (or use built-in simulated data) and run windowed
+  aggregations plus standard-deviation anomaly detection on the stream. Use when
+  an agent needs to analyze real-time or time-series data — IoT sensor readings,
+  event logs, security events, fleet telemetry, transaction feeds — and answer
+  questions about rates, trends, and outliers over time windows. NOT for static
+  tabular files (use sql-analyst) or document content (use vector-search).
 license: MIT
 compatibility: >
   Requires a Toolbelt account (provision free at https://toolbelt.ai) and an
-  MCP-compatible AI agent (Claude Code, Claude Desktop, or any client that
-  supports MCP server connections). MCP connection must be pre-established
+  MCP-compatible AI agent (Claude Code, Claude Desktop, OpenClaw, or any client
+  that supports MCP server connections). MCP connection must be pre-established
   before invocation. Kafka parameters are optional — omit them to run with
   simulated stream data.
 metadata:
   author: toolbeltai
   version: "1.0"
-  openclaw:
-    emoji: "📡"
-    homepage: "https://toolbelt.ai/docs/streaming"
-    skillKey: "streaming-analyst"
+  homepage: "https://toolbelt.ai/docs/streaming"
 ---
 
 Connect a Kafka topic (or simulate one) and run real-time aggregation and

package/vector-search/SKILL.md

@@ -1,25 +1,23 @@
 ---
 name: vector-search
 description: >
-  Find semantically relevant passages from documents without keyword matching.
-  Toolbelt is a multi-modal data platform combining SQL analytics, vector search,
-  and real-time streaming. Upload a document, then retrieve the passages most
-  semantically similar to a natural language query. Use when an AI agent needs to
-  ground answers in source documents (RAG), find related content without exact
-  keyword matches, or rank passages by meaning rather than text overlap.
+  Upload a document and retrieve passages by semantic similarity to a
+  natural-language query. Ranks content by meaning, not keyword overlap. Use
+  when an agent needs to ground answers in source documents (RAG), find related
+  content, retrieve passages by concept, or answer "what does this doc say
+  about X" where X isn't a verbatim phrase. NOT for exact keyword/regex search,
+  structured table queries (use sql-analyst), or entity-relationship extraction
+  (use knowledge-graph).
 license: MIT
 compatibility: >
   Requires a Toolbelt account (provision free at https://toolbelt.ai) and an
-  MCP-compatible AI agent (Claude Code, Claude Desktop, or any client that
-  supports MCP server connections). MCP connection must be pre-established
+  MCP-compatible AI agent (Claude Code, Claude Desktop, OpenClaw, or any client
+  that supports MCP server connections). MCP connection must be pre-established
   before invocation.
 metadata:
   author: toolbeltai
   version: "1.0"
-  openclaw:
-    emoji: "🔍"
-    homepage: "https://toolbelt.ai/docs/vectors"
-    skillKey: "vector-search"
+  homepage: "https://toolbelt.ai/docs/vectors"
 ---
 
 Upload a document and retrieve semantically similar passages using Toolbelt MCP