data analyst workflow

Data Community

Skill notes

Overview

Run analysis with an explicit chain from raw data to plain-English conclusions.

Core Workflow

Inspect schema, types, missingness, duplicate risk, and obvious quality issues before analyzing outcomes. Clean or normalize data carefully and document every meaningful assumption. Compute descriptive statistics and comparisons that answer the actual question, not just what is easy to chart. Check anomalies, outliers, seasonality, and segmentation effects before drawing conclusions. Present the findings in plain language with tables or charts only when they improve understanding.

Deliver

Show the key numbers and what they mean. Call out data-quality limitations and assumption-sensitive results. Keep a clear distinction between observed facts and interpretation.

Guardrails

Do not bury cleaning choices that materially change the result. Prefer reproducible steps over one-off spreadsheet-style reasoning. Avoid false precision when the dataset or method does not support it.

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Data
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
88 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@00PrabalK00 · no license declared
Token usage
Lean
Setup complexity
Plug-and-play
External API key
Not required
Operating systems
Unspecified (assume cross-platform)
Runtime requirements
No explicit requirements detected
Detected file/system behavior
  • Read-only
Network behavior
Local-only
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

Author source file SKILL.md

# Data Analyst Workflow

## Overview

Run analysis with an explicit chain from raw data to plain-English conclusions.

## Core Workflow

1. Inspect schema, types, missingness, duplicate risk, and obvious quality issues before analyzing outcomes.
2. Clean or normalize data carefully and document every meaningful assumption.
3. Compute descriptive statistics and comparisons that answer the actual question, not just what is easy to chart.
4. Check anomalies, outliers, seasonality, and segmentation effects before drawing conclusions.
5. Present the findings in plain language with tables or charts only when they improve understanding.

## Deliver

- Show the key numbers and what they mean.
- Call out data-quality limitations and assumption-sensitive results.
- Keep a clear distinction between observed facts and interpretation.

## Guardrails

- Do not bury cleaning choices that materially change the result.
- Prefer reproducible steps over one-off spreadsheet-style reasoning.
- Avoid false precision when the dataset or method does not support it.

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.