dril-dataset-construction
100 / 100 · Low risk
Fine to try.
Implement the DRIL (Deep Research on a Loop) methodology to construct economic datasets from primary sources using AI agents. Use this skill whenever the user wants to build a dataset, construct panel data, collect cross-country or cross-sectional data, compile institutional or legal variables, automate research-assistant data collection, or create a codebook for systematic source coding. This includes tasks like "collect corporate tax rates by country," "build a dataset on central bank indepen…
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'dril-dataset-construction' ] || [ -L ~/.agents/skills/'dril-dataset-construction' ]; then echo 'A skill folder named dril-dataset-construction already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/franklee16/academic-research-skills' "$d" && git -C "$d" checkout --quiet '9a4b2db21fc4b217136ae4a0e6faad42d179ca03' -- 'data-sourcing/dril-dataset-construction' && mkdir -p ~/.agents/skills && cp -R "$d"/'data-sourcing/dril-dataset-construction' ~/.agents/skills/'dril-dataset-construction' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'dril-dataset-construction' ~/.claude/skills/'dril-dataset-construction' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/franklee16/academic-research-skills/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | 9a4b2db | 100 |