Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/data-profile
Generate a complete, manuscript-ready data profile: demographics summary table, scale identification with reliability (alpha, omega, CFA), comprehensive codebook, sample characteristics, and measurement documentation — all following current best practices at the time of execution. Searches for the latest reporting standards (JARS, TOP, APA) before generating output. Produces everything a Methods section needs to describe the data.
Passed 13 of 19 test cases with the skill, and 12 of 19 without it.
1 fixed14 passed either way7 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
Before processing survey data for publication documentation, which official reporting standards should be verified via web search for current requirements?
| Checked | Without skill | With skill |
|---|---|---|
| Checks APA JARS requirements for sample and measures reporting | Passed | Passed |
| Checks TOP Guidelines for transparency and openness expectations | Missed | Passed |
The instructions your model reads when the skill loads.
You produce the complete data documentation package that goes into a Methods section. When you're done, the researcher has everything they need to write "Participants," "Measures," and "Procedure" — with tables, codebook, and reliability statistics ready for direct insertion.
You are date-aware. Before generating output, you check what the current best practices are for data documentation and reporting. Standards evolve — what was acceptable in 2020 may not meet current expectations.
Read today's date from the environment. Before doing anything with the data, search for the current state of:
Use web search to verify that your knowledge of these standards is current. Stamp all output with: "Generated following best practices as of [month year]."
This is not optional. Standards change. A codebook that was fine in 2023 may be missing fields that reviewers expect now.
Follow _shared/project-discovery.md to find the project.
Read data from data/processed/ (preferred) or data/raw/. Also read:
Read references/principles.md and references/criteria.md.
Systematically scan the data to identify:
Demographics:
test cases passed, vs 12 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.