BB toolbelt
Toolbelt is a collaborative substrate over your data. Upload any document — entities and relationships extracted automatically, queryable immediately. Ask questions that span structured tables, documents, and relationships in a single call. No stitching databases together. Toolbelt orchestrates semantic, structured, and hybrid retrieval through one MCP server — vector, knowledge graph, SQL, geospatial, streaming. Share the URL and any agent can query the same workspace — like a shared Google Doc for your data. Built by Kinetica. Use this skill at the start of any task where an agent needs to ingest documents and have entities/relationships auto-extracted, query structured + unstructured data together in natural language, or share findings with other agents across sessions. The skill handles first-time setup: provisions a free Toolbelt account if none exists, configures the MCP connection in the agent's client, and hands off to Toolbelt's MCP tools for the actual work. NOT for one-off lookups that don't benefit from automatic extraction, hybrid retrieval, or shared state — use the agent's native tools for those.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1129 chars, limit 1024
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4008 tokens
- 100Steps. 31 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 1128: 120–800 characters recommended
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 19 headings
- +3Step-by-step instructions: 31 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.