dril-dataset-construction — Claude Code skill: how it works & setup
dril-dataset-construction implements the DRIL methodology to assemble economic datasets from primary sources via AI agents. Ideal for constructing panel data, legal variables, and cited codebooks.
no license ★ 240 updated 2026-09-18
npx skills add franklee16/academic-research-skills --skill dril-dataset-construction -a claude-codeWhat dril-dataset-construction does
This skill brings the Deep Research on a Loop (DRIL) framework from Afonso et al. (NBER w35188) into Claude Code. It turns open-ended web digging into a standardized data extraction routine across enumerable units like countries and years. The pipeline separates protocol design from per-unit data collection.
During the design stage, the agent writes a frozen protocol consisting of codebook.yaml and a unit index in units.csv. The execution phase then iterates through every mapped row, issuing search queries, scoring variables against rules, and compiling answers into dataset.csv. Every coded cell pairs with exact quotes and source locators inside evidence_records.json.
Reviewing the codebook requires domain knowledge. You must inspect it before full-scale extraction begins. If target dimensions remain vague, the agent cannot freeze a valid instrument.
What it helps with
- Build cross-country panel datasets from primary legal and government documents
- Generate formal codebooks with explicit coding rules and value types
- Extract institutional variables while preserving verbatim citation evidence
- Log search queries and document missing data reasons systematically
Example prompts for the agent
- Build a dataset on central bank independence for OECD countries between 2010 and 2023 using DRIL.
- Create a codebook and unit space to compare subnational borrowing rules across Latin America.
- Collect corporate tax rates across our target countries and document exact legal citations for each year.
How to install dril-dataset-construction
1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill dril-dataset-construction -a claude-code2Manually: put the files in place
~/.claude/skills/dril-dataset-construction/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/dril-dataset-construction/
1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill dril-dataset-construction -a codex2Manually: put the files in place
.agents/skills/dril-dataset-construction/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill dril-dataset-construction -a cursor2Manually: put the files in place
.cursor/skills/dril-dataset-construction/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install franklee16/academic-research-skills data-sourcing/dril-dataset-construction/SKILL.md2Manually: put the files in place
.github/skills/dril-dataset-construction/SKILL.md1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill dril-dataset-construction -a gemini-cli2Platform CLI
gemini skills install https://github.com/franklee16/academic-research-skills --path data-sourcing/dril-dataset-constructionManually: put the files in place
.devin/skills/dril-dataset-construction/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about dril-dataset-construction
How do I install dril-dataset-construction in Claude Code?
Run npx skills add franklee16/academic-research-skills --skill dril-dataset-construction -a claude-code in your terminal. This configures the skill inside ~/.claude/skills/dril-dataset-construction/SKILL.md.
What is the DRIL methodology?
DRIL structures automated web research by separating research design from data collection. An agent codes variables against a frozen codebook and records exact text excerpts for every extracted observation.
What prerequisites are needed before running this skill?
You need a stated research goal and an approximate set of target units, such as a country list and date range. You also need domain understanding to inspect and approve the generated codebook before data extraction starts.