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.
- Author
- holistics ↗
- Repository
- skills ↗
- Licence
- Apache-2.0
- Last repository change
- 27.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.
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
- Pre-requisites
- Syntactic and descriptive
- Diagnostic and predictive
- General guidelines
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
| Repository | Score | Licence |
|---|---|---|
| This page · holistics/skills | 100 | Apache-2.0 |
| allenai/asta-plugins | 100 | Apache-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…