Individual skill

llm-research-workflow

Iterative workflow for developing LLM-based data pipelines and LLM-generated measures in empirical economics and finance research, based on Ferrara (2026, NBER WP 35374). Use this skill whenever the user wants to use an LLM (or asks whether they can) to extract, classify, score, link, harmonize, or transcribe research data — e.g., tone/sentiment of earnings calls or filings, classifying news or analyst text, extracting structured data from PDFs/scans/tables, matching entities without unique identifiers, scoring images or audio, or building any variable that will later enter a regression. Also trigger when the user says "help me set up a pipeline", "can an LLM do X with my data", "classify these documents", or proposes sending a research corpus to a model. Trigger even if the user does not say "workflow" — the point of the skill is to impose the workflow they didn't ask for.

research-workflow/llm-research-workflow/SKILL.md

Source commit 9a4b2db21fc4b217136ae4a0e6faad42d179ca03

What was checked

Matches the observed repository HEAD

Yes

Scanner rules are current

Yes

Repository scan complete

No

Skill scan complete

No

Observed behavior

Network or broad shell

Last checked

Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.