Data & analytics
Answer a question from your business data
Frame a business-data question, inspect the available evidence and prepare an analysis with checks and clearly stated limitations.
Claude
DATA & ANALYTICS / ANALYSIS
A source-backed explore data workflow for data & analytics. Review its inputs, setup and geographic limits before your first draft.
01 / WHAT TO TRY
Publisher description excerpt: “Profile and explore a dataset to understand its shape, quality, and patterns. Use when encountering a new table…” Source ↗
These are Fieldwork’s preparation notes. Follow the source’s full input checklist for the specific task.
An analysis or visualisation with source-linked findings
This is a source-inspected starting point. Fieldwork has not run-tested this skill or measured time savings.
02 / CHECK THE FIT
Claude
Publisher documents a Claude/Agent Skills setup. Review the complete pack and its current installation instructions.
Geography-neutral workflow. Set Australian spelling, AUD, dates and business context explicitly; local compliance is not supplied by this label.
Source mentions: Excel. Actual integration access depends on your setup.
Public instructions do not imply free access to Claude, ChatGPT, paid apps, API usage or generation services.
03 / SET IT UP
Pinned source snapshot; review publisher release and installation notes.
Platform-by-platform setup guide →04 / YOUR FIRST DRAFT
Replace the brackets and supply the required inputs. This prompt is Fieldwork’s example, not a tested guarantee or a replacement for installation.
Use explore-data for [business task]. Our business is in [country and state/territory], our currency is [currency], and the intended reader is [audience]. Use only the attached authorised inputs and approved policies. First identify missing information and unavailable tools. Prepare a draft for human review; cite the supplied evidence, separate assumptions, and do not send, publish, lodge, purchase or change records.Download prompt ↓
Check the data scope, calculations, definitions and missing values. Separate observed results from causal claims; protect personal and confidential information.