Clean Interviews Skill for ChatGPT: Standardize Metadata and Research Notes
Normalize supplied interview notes into consistent records. Preserve source excerpts, date, project, participant alias, and follow-up without flattening contradictory observations.
中文Install in ChatGPT
Use an eligible ChatGPT workspace with permission to create skills and, for uploads, upload permission. The installation path for this text-only adaptation was checked against OpenAI documentation. Workspace runtime verification is pending.
- Download skills/clean-interviews/SKILL.md from the pinned GitHub source. Keep the name, description, and instructions for clean-interviews together as a standalone text skill.
- In a ChatGPT workspace with skills and uploads enabled, open Plugins, Skills, Create, and Upload from your computer. Choose a skill package format accepted by the file picker. You can also choose Create with editor and enter the original name, description, and instructions.
- After the scan completes, check that clean-interviews appears in Installed. Type @ in a new chat, select the skill, and use the fictional example on this page to check the output.
Example task
Fictional note A says save was hard to find on a phone. B found it immediately on desktop. A has no date. Both use aliases. Produce two standardized notes and one index row.What to check
Keep device conditions and each statement. Mark A's date unknown and retain aliases. Treat discoverability differences as a follow-up to test.
Original SKILL.md on GitHub · Updated
Frequently asked question
Can conflicting interview notes be merged into one average conclusion?
Preserve individual observations and conditions. Check differences in device, task, and experience before identifying a shared theme.