Skip to content
Skills Library
Data & analytics · Learning & explanation

analyze-data

/analyze-data

Explain AQL queries and their results, and provide data insights. Use this whenever the user asks what a query does, wants to understand results, or needs to dig deeper into why a metric changed.

Repository
skills ↗
Licence
Apache-2.0
Last repository change
27.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Explain AQL queries and their results, and provide data insights. Use this whenever the user asks what a query does, wants to understand results, or needs to dig deeper into why a metric changed.

Original author description

Explain AQL queries and their results, and provide data insights. Use this whenever the user asks what a query does, wants to understand results, or needs to dig deeper into why a metric changed.

How it works

  1. Pre-requisites
  2. Syntactic and descriptive
  3. Diagnostic and predictive
  4. General guidelines
Original SKILL.md headings · 14 lines, 153 words
SKILL.md preview
---
name: analyze-data
description: Explain AQL queries and their results, and provide data insights. Use this whenever the user asks what a query does, wants to understand results, or needs to dig deeper into why a metric changed.
---

## Pre-requisites
* Set up Holistics MCP

## Syntactic and descriptive
Always use `explain_result` tool to syntactically/descriptively explain AQLs and their results. It can understand AQL accurately and provide accurate answers.

## Diagnostic and predictive
Run additional queries to analyze and provide diagnostic and predictive answers. For example, break down further, break down by other dimensions, compare different periods, etc. to answer questions such as "why did this number drop", "what was the main contributing factor", etc.

## General guidelines
* Start with using `explain_result` to understand the query, then proceed to further diagnostic/predictive analysis.
* Beware of incomplete time periods when doing period comparisons.
  * For example, if today is 2025 Oct, and you are comparing the sales of 2025 Q4 to 2024 Q4, the sales of 2025 Q4 might be lower simply because it's only the beginning of the quarter. Check the SQL (included in output of `execute_aql`, `execute_viz`) to verify.

Versions

RepositoryScoreLicence
This page · holistics/skills100Apache-2.0
allenai/asta-plugins100Apache-2.0

Identical content appears in 1 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version 7cf58b1f3548 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100write-aql
    Write and run AQL (Analytic Query Language) queries to answer data questions. Use this whenever the user asks for data, wants to query a dataset, needs to filter/aggregate/join data, or asks about metrics and dimensions in Holistics.
  • 100aql
    Core AQL (Analytic Query Language) knowledge — syntax, semantics, functions, worked examples, and gotchas. Use whenever you need to write, read, or debug AQL yourself.
  • 90analyze-results
    Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.
  • 100deep-research
    Conducts a structured metric investigation in Mixpanel. Use when the user asks why a metric changed, what's driving a trend, requests a "deep dive" or "root cause," or wants to understand a phenomenon in their data. Walks through project / event / property scoping, plan…
  • 100metric-diagnostics
    Diagnose why a metric changed or differs from expectation. Use when the task is to identify likely drivers of a metric movement, anomaly, gap, or discrepancy.
  • 100arangodb-multi-model-database-operations
    Covers operating ArangoDB, a multi-model database combining document, graph, and key-value collections in a single engine with a unified query language (AQL): collection type selection, graph traversal via AQL, and cluster configuration (coordinators, DB-servers, agency). Use…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.