Data Queries logo

Data Queries

Community
jstanden
data-queries

Cerb data queries -- the `key:value` language behind worklists, metrics, charts, and reports. Load it when choosing a `type:`, a `format:`, or an aggregation.

Overview

Publisherjstanden
Repositorycerb
Skill namedata-queries
Stars
83
Forks
38
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by jstanden on GitHub. Read the source before you install it.

Installation

Install the Data Queries AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/jstanden/cerb/tree/12.0.x/features/cerberusweb.core/assets/agent_filesystems/cerb-agents/skills/data-queries
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jstanden/cerb.git /tmp/cerb
mkdir -p .claude/skills
cp -r /tmp/cerb/features/cerberusweb.core/assets/agent_filesystems/cerb-agents/skills/data-queries .claude/skills/data-queries
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Data Queries in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Data Queries on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Data Queries is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Cerb data queries

The text-based key:value query language used for worklists, metrics, charts, and other data.

Essentials

  • A data query is a set of key:value pairs. No space after the colon. type:worklist.records is one pair; type: worklist.records is the key type with an empty value plus a stray bare term, which is not what you meant and usually will not error.
  • Quote a value only when it contains a space. of:ticket, limit:25, and sort:-updated need no quotes; query:"status:open" does. Quotes are not what makes something a string, and unnecessary ones are just noise to read past.
  • Group a key's children with ( ).
  • Pairs are separated by whitespace, and a newline IS whitespace, so break a long query across lines wherever it reads best:
type:worklist.records
of:ticket
query:(
  status:open
  sort:-updated
  limit:10
)
format:dictionaries
  • Every query MUST include a type:. The available types — e.g. worklist.records, worklist.subtotals, worklist.metrics, worklist.series, worklist.xy, metrics.timeseries, record.fields, record.filters, record.types, ui.icons — are documented under /cerb-docs/references/docs/data-queries/; data.query.types lists them all.
  • A format: prepares the response for its consumer (e.g. dictionaries).
  • For worklist queries, confirm the record type's valid search filters (their names, example values, and which are sortable) and its fields before writing query:/sort: — don't assume field names. The record.filters and record.fields query types exist precisely for this discovery; point people at them when useful.
  • Reach for worklist.subtotals / metrics.timeseries / worklist.series for aggregation and reporting rather than hand-rolling; use worklist.records for a filtered list of record dictionaries.

Untrusted input goes in query_params:, never in the query text

Interpolating someone's words straight into query: is an injection: their text is parsed as query syntax, so a value can add filters, widen the result set, or reach records they should never see.

Pass it as a binding instead. data.query: takes a query_params: block, and the query references each entry as ${name}:

data.query:
  output: results
  inputs:
    query_params:
      term: {{search_text}}
    query@text:
      type:worklist.records
      of:ticket
      query:(subject:${term} status:open)

A substituted value is forced to a quoted string token, so whatever it contains -- colons, parentheses, another key:value -- lands as one literal value and cannot become syntax. record.search: and record.upsert: take the same thing under record_query_params:.

Ground truth — read the docs, don't guess

The cerb-docs filesystem is the full, authoritative Cerb documentation. When a query type, key, field, search filter, format, or icon is in question, look it up before you write it, and cite what you relied on. Invented field or filter names silently return nothing (or error), so confirm them.

  • /cerb-docs/references/docs/data-queries/ — one page per type (e.g. worklist/records.md, worklist/subtotals.md, record/filters.md).

Related skills

  • records — confirm a record type's alias for of:, and its real filter keys, against THIS install rather than the baseline docs.
  • search-queries — the grammar for the query: you put inside a worklist data query.

Frequently asked questions

What does the Data Queries AI skill do?

Cerb data queries -- the `key:value` language behind worklists, metrics, charts, and reports. Load it when choosing a `type:`, a `format:`, or an aggregation.

Why use Data Queries on TypingMind?

Because you install it once and use it with any model. Data Queries is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Data Queries in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jstanden/cerb/tree/12.0.x/features/cerberusweb.core/assets/agent_filesystems/cerb-agents/skills/data-queries. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Data Queries?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Data Queries?

As many as you like. As long as a model supports skills, you can use Data Queries with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Data Queries AI skill free?

It is published on GitHub by jstanden. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇