agents / data

data-researcher

what it does

Use this agent when you need to discover, collect, and validate data from multiple sources to fuel analysis and decision-making. Invoke this agent for identifying data sources, gathering raw datasets, performing quality checks, and preparing data for downstream analysis or modeling.

tools it asks for

Reads files · Uses the web

Verified Before and after: 2 models 1 try per case View source Install from your agent Download .zip

Compare the answers

Answers from Claude Sonnet 5.5 and GPT-6.1 Sol · try 1 of 1

Same request, same model, once with the agent’s instructions as its system prompt and once without. Neither could use a tool. Read both and judge for yourself.

Compare the answers

The models

2 models

Claude Sonnet 5.5

made by Anthropic

claude-sonnet-5-5 · revision not reported by the provider

1 try per case · tested 7 Nov 2026

GPT-6.1 Sol

made by OpenAI

gpt-6.1-sol · revision not reported by the provider

1 try per case · tested 7 Nov 2026

The tasks

written by Carte Blanche
example-1

“I'm building a model to forecast monthly electric vehicle adoption by US state. Can you identify the best public data sources for EV registrations, charging station counts, state incentives, and gas prices? For each, tell me the publisher, update frequency, granularity, known quirks, and how I'd join them (e.g., state FIPS codes plus month). Rank them by reliability and flag gaps.”

example-2

“I have a CSV of customer survey responses with columns: respondent_id, age, income, zip, satisfaction_score (1-10), signup_date. I'm seeing ages like 214 and -3, satisfaction scores of 0 and 11, duplicate respondent_ids, and mixed date formats (2023-01-05 and 05/01/23). Please lay out a validation plan with specific quality checks, rules for handling each issue, and a cleaning checklist so the data is ready for regression modeling.”

Install

Download the .zip and unzip it. Put data-researcher.md here:

Claude Code~/.claude/agents/Every project. For one project only, use .claude/agents/ inside it. It gives the agent the tools it asks for, and no others.
Cursor~/.cursor/agents/Cursor also reads the Claude Code folder above. It has no tools field, so it gives every agent every tool, whatever this one asks for.
CodexCodex’s custom agents are TOML files, not Markdown, so this agent doesn’t install there.

Keep its license file beside it, as data-researcher.LICENSE: a name that doesn’t end in .md, since every .md file there is read as an agent.

Then start a new session and ask for it by name. Folders checked 6 November 2026.

Or install from your agent: ask it to install data-researcher from Carte Blanche.