Data Analysis Agent Skills That Find Real

Data analysis skills help an AI agent support the full analytical process: framing the decision, understanding what data exists and what it means, preparing trustworthy tables, running summaries, tests, or models, evaluating whether results hold up, and communicating findings to decision-makers. These skills are for developers who need an agent to assist with real analysis work, not just spreadsheet manipulation. Use the ranked list below to find a skill that matches your current step. Start with the sub-topic that reflects your immediate need—question framing, data understanding, preparation, modeling, evaluation, or communication. Read each skill's description to confirm it covers the specific move you need, then pick the one that fits your workflow. The list is ordered by observed search demand, with direct matches first.

8 to start with17 top options

Start with these.

Analysis is a process: frame the question, get and clean the data, explore it, model if needed, then evaluate and communicate — not 'open a spreadsheet and hope'.

These are the closest matches for this work. Start with the first one and open it to install.

What decision this analysis is for, and how you will know you answered it. A sub-problem of this domain with no skills yet.What data exists, what it means, and what is missing or biased. A sub-problem of this domain with no skills yet.Make a trustworthy table (or tables) from the raw inputs.The actual analytical move: summary, test, or model.Whether the result holds up, or just fit this particular extract. A sub-problem of this domain with no skills yet.Turn the result into something a decision-maker can use.

17 top options

  1. Rank 04
    Direct

    datanalysis-credit-risk

    Credit risk data cleaning and variable screening pipeline for pre-loan modeling. Use when working with raw credit data that needs quality assessment, missing value analysis, or variable selection before modeling. it covers data loading and formatting, abnormal period filtering, missing rate…

    • Preparation
    7,300 · popularity
    View Agent Skill
  2. Rank 05
    Direct

    sql-pro

    Optimizes SQL queries and designs schemas: CTEs, window functions, indexing, EXPLAIN/ANALYZE interpretation, and dialect differences. Directly supports the preparation and analysis facets for SQL-based data work.

    6,047 · popularity
    View Agent Skill
  3. Rank 06
    Direct

    data-storytelling

    Turns analytics into narratives using story structure, narrative arcs, and visuals for stakeholder and executive presentations. Covers the communication facet of data analysis rather than computation.

    • Communication
    16,019 · popularity
    View Agent Skill
  4. Rank 07
    Direct

    dbt-transformation-patterns

    dbt patterns for analytics engineering: staging/intermediate/marts layering, naming conventions, testing, documentation, and incremental models. Covers the preparation and modeling facets of analytics work.

    10,543 · popularity
    View Agent Skill
  5. Rank 08
    Direct

    clickhouse-io

    ClickHouse patterns for high-performance analytics: MergeTree schema design, aggregation and window queries, query optimization, and large-volume ingestion. Targets analytical query work on a specific OLAP engine.

    9,781 · popularity
    View Agent Skill
Explore 9 more Agent Skills
  1. Rank 09
    Direct

    azure-kusto

    Official

    Query and analyze data in Azure Data Explorer (Kusto/ADX) using KQL for log analytics, telemetry, and time series analysis. WHEN: KQL queries, Kusto database queries, Azure Data Explorer, ADX clusters, log analytics, time series data, IoT telemetry, anomaly detection.

    514,672 · popularity
    View Agent Skill
  2. Rank 10
    Possible

    xlsx

    Official

    Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

    View Agent Skill
  3. Rank 11
    Possible

    ml-pipeline-workflow

    Builds end-to-end MLOps pipelines covering data preparation, training, validation, and deployment with DAG orchestration patterns. Overlaps the preparation and modeling facets but is engineering-oriented.

    • Preparation
    • Modeling & analysis
    10,692 · popularity
    View Agent Skill
  4. Rank 12
    Possible

    nature-statistics

    Audits and improves manuscript statistical reporting: experimental units, replication, uncertainty, tests, and figure statistics. Focused on scientific reporting rather than general data analysis.

    • Modeling & analysis
    10,201 · popularity
    View Agent Skill
  5. Rank 13
    Possible

    amazon-opensearch-service

    Guides Amazon OpenSearch Service across migration, provisioning, search, log analytics, trace analytics, and an AI assistant for natural-language data exploration and root cause analysis. Supports log and search analytics on a specific plat

    Needs (stated): MCP server

    4,901 · popularity
    View Agent Skill
  6. Rank 14
    Possible

    stock-analysis

    Analyzes stocks and crypto via Yahoo Finance with eight dimensions, portfolio tracking, and periodic performance reports. Domain-specific financial analysis rather than general data analysis.

    • Communication
    11,879 · popularity
    View Agent Skill
  7. Rank 15
    Possible

    datalineage-bigquery-asset-impact-analysis

    Official

    >- Analyzes the downstream impact (blast radius) when a BigQuery table or view is broken, stale, or modified. Identifies all downstream tables, dashboards, and processes that will be affected. Use when: - Performing a blast radius or impact analysis for a BigQuery table or view. - Assessing the consequences of modifying, deleting, or pausing updates to a BigQuery asset. - Identifying downstream dependencies (tables, dashboards, processes) of a BigQuery asset. Don't use for: - General BigQuery querying or data analysis (use BigQuery-related tools instead). - Non-BigQuery assets (e.g., Cloud Storage files) unless they are part of the BigQuery lineage. - Creating or modifying lineage links directly.

    • Preparation
    View Agent Skill
  8. Rank 16
    Possible

    gke-cost-analysis

    Official

    >- Answer natural language questions and perform analysis on GKE cluster and workload costs using BigQuery billing exports, cost allocation data, and live cluster monitoring metrics. Use when querying GKE costs across projects, namespaces, or workloads, analyzing billing reports in BigQuery (`bq`), checking cluster cost budgets (`gcloud billing`), or diagnosing cost drivers like pod requests vs. actual utilization (`kubectl top`). Don't use for applying cost optimization changes, creating rightsizing manifests (VPA/MPA), or selecting ComputeClasses (use gke-cost-optimization instead).

    View Agent Skill
  9. Rank 17
    Possible

    google-analytics-data-api-basics

    Official

    Manages Google Analytics reporting data, enables the Analytics Data API via the Cloud CLI, and creates reports using the Google Analytics Data API (v1beta). Use when you need to interact with Google Analytics properties, run customized analytics reports, query metrics (like activeUsers,…

    6,412 · popularity
    View Agent Skill
What this topic covers

What this topic covers

Each sub-topic groups Agent Skills for a specific situation.

Question & context
What decision this analysis is for, and how you will know you answered it.
Data understanding
What data exists, what it means, and what is missing or biased.
Preparation
Make a trustworthy table (or tables) from the raw inputs.
Modeling & analysis
The actual analytical move: summary, test, or model.
Evaluation
Whether the result holds up, or just fit this particular extract.
Communication
Turn the result into something a decision-maker can use.
Frequently asked questions

Frequently asked questions

How is the ranked list ordered?
The list is ranked by observed search demand. Direct matches to the topic appear first, and there is a cap on any single publisher.
What sub-topics are covered under Data Analysis?
The sub-topics are Question & context, Data understanding, Preparation, Modeling & analysis, Evaluation, and Communication. Each corresponds to a stage in the analytical process.
Why treat analysis as a process instead of just opening a spreadsheet?
Analysis is a process: frame the question, get and clean the data, explore it, model if needed, then evaluate and communicate. Skipping steps leads to untrustworthy results.

How to install an Agent Skill

Start with the first skill on this page. Claude Code reads a SKILL.md once it is in the skills directory:

  • Claude Code — copy the SKILL.md for analyze into ~/.claude/skills/analyze/ for yourself, or .claude/skills/analyze/ to share it with a project.
  • From the registry — run npx skills add anthropics/knowledge-work-plugins@analyze.
  • Or download analyze from its source and place that SKILL.md in the directory above.

How to choose Check the source and the skill’s own instructions before you install. Official and Notable describe where a skill comes from.