Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/data-finder
Find and assess datasets for a research question. Dispatches Explorer agents to search across data source categories, then Explorer-Critic to stress-test each candidate. Produces a ranked list with feasibility grades. Make sure to use this skill whenever the user wants to identify or evaluate data sources — not to search for papers or run analysis. Triggers include: "find data", "what data should I use", "find a dataset for this", "where can I get data on X", "assess datasets", "what datasets ex
Passed 16 of 21 test cases with the skill, and 9 of 21 without it.
and 6 more in the full report
8 fixed9 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need to search for datasets for our project. Should we read the research specification from `docs/spec.txt` or search in the project directory?
| Checked | Without skill | With skill |
|---|---|---|
| Looks for project specification files inside the quality_reports directory. | Missed | Passed |
The instructions your model reads when the skill loads.
Find and assess datasets for your research question. Two Explorer agents search in parallel across data source categories; an Explorer-Critic then stress-tests each candidate against the research design.
Input: $ARGUMENTS — a topic, or from spec to read the research question from quality_reports/.
Find the most recent quality_reports/project_spec_*.md or quality_reports/specs/*.md — extract:
Read references/domain-profile.md if it exists — extract the Common Datasets section (domain-specific datasets to check first).
If no research spec exists, extract the variables and strategy from $ARGUMENTS directly. If the request is vague, ask: "What are the treatment and outcome variables, and what empirical strategy did you have in mind?"
Split the source categories between two Explorer agents to parallelize the search.
Explorer A — Institutional Data:
Task prompt: "You are an Explorer agent. Research question: [question].
Empirical strategy: [strategy].
Variables needed — Treatment: [X], Outcome: [Y], Controls: [list],
Time period: [period], Geography: [geo], Unit: [unit].
Domain datasets (check first): [list from domain-profile if available].
Your source categories to search:
1. Public microdata (CPS, ACS, NHIS, MEPS, SIPP, QWI)
test cases passed, vs 9 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.