# Data Analyzer

> Inspect a dataset, calculate trustworthy summaries, identify patterns and anomalies, and explain decision-relevant findings with explicit assumptions. Use when the user wants answers or insights from CSV, spreadsheet, JSON, database extracts, tables, or pasted data.

- **Type:** Skill
- **Install:** `agentstack add skill-rylaispirit-rylai-codex-hermes-skills-data-analyzer`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Rylaispirit](https://agentstack.voostack.com/s/rylaispirit)
- **Installs:** 0
- **Category:** [Databases](https://agentstack.voostack.com/c/databases)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Rylaispirit](https://github.com/Rylaispirit)
- **Source:** https://github.com/Rylaispirit/rylai-codex-hermes-skills/tree/main/skills/data-analyzer

## Install

```sh
agentstack add skill-rylaispirit-rylai-codex-hermes-skills-data-analyzer
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Rylai Data Analyzer

Turn supplied data into supported conclusions. Prefer a smaller set of reliable findings over a long list of weak observations.

## Analysis Workflow

1. **Clarify the question**
   - Identify the decision, target metric, comparison, population, and time window.
   - If the user asks broadly, begin with a profile and surface the most consequential patterns.

2. **Inspect the data**
   - Record row count, columns, types, units, date coverage, and likely keys.
   - Check missing values, duplicates, impossible values, inconsistent categories, and parsing failures.
   - Preserve the original data and make exclusions visible.

3. **Create trustworthy summaries**
   - Use counts and rates for categorical data.
   - Use center, spread, range, and quantiles for numeric data.
   - Segment results only where group sizes and definitions remain meaningful.
   - Use robust statistics when outliers make ordinary averages misleading.

4. **Investigate**
   - Compare periods, groups, or cohorts relevant to the question.
   - Examine trend, seasonality, concentration, relationships, and anomalies.
   - Test alternative explanations before calling a pattern important.

5. **Interpret**
   - Separate observed facts from inference.
   - Quantify magnitude and denominator, not only percentage change.
   - State uncertainty, sample limitations, and data-quality risks.
   - Do not claim causation without a design that supports it.

6. **Verify**
   - Recalculate important totals independently.
   - Check that filters, joins, units, and date boundaries match the stated scope.
   - Trace each headline finding back to a reproducible calculation.

## Output Contrac

Return a compact report with:

### Scope

Question, data source, period, record count, and filters.

### Data Quality

Missingness, duplicates, exclusions, parsing issues, and material caveats.

### Findings

For each finding, provide the value, comparison, denominator, and why it matters.

### Recommended Actions

Tie actions to evidence and distinguish immediate decisions from further analysis.

### Methods

List calculations, statistical assumptions, and transformations needed to reproduce the result.

Use tables or charts only when they make comparison easier. Never fabricate missing observations or silently replace them with zeros.

## Runtime Notes

- Use the runtime's structured data and spreadsheet tools when available.
- Inspect generated tables and charts before reporting completion.
- Keep temporary analysis artifacts separate from user-facing deliverables.
- State clearly when the dataset is too incomplete to support the requested conclusion.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Rylaispirit](https://github.com/Rylaispirit)
- **Source:** [Rylaispirit/rylai-codex-hermes-skills](https://github.com/Rylaispirit/rylai-codex-hermes-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-rylaispirit-rylai-codex-hermes-skills-data-analyzer
- Seller: https://agentstack.voostack.com/s/rylaispirit
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.