Interview cleanup
Clean up raw interview transcripts while preserving meaning and speaker voice. Use after conducting interviews.From its SKILL.md
npx -y skills add itseffi/agentic-os --skill interview-cleanupAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
SKILL.md
1.3 KB, 258 tokens by cl100k_base, as published. Nobody here has run it
Interview Transcript Cleanup
Clean up raw interview transcripts while preserving meaning and speaker voice.
When to Use
After conducting user interviews when you have raw transcripts that need cleanup before analysis.
The Process
-
Read the full transcript to understand context and flow
-
Remove noise without losing meaning:
- Filler words (um, uh, like, you know)
- False starts (incomplete/abandoned sentences)
- Redundancies (repeated words that don't add meaning)
-
Preserve what matters:
- Original meaning and intent
- Speaker's unique voice and style
- Speaker labels (Interviewer:, Interviewee:)
- Unclear/inaudible markers [inaudible]
-
Light editing only:
- Fix punctuation and capitalization
- Don't over-formalize casual language
- Don't cut unnecessarily
Quality Check
- Does the cleaned transcript read naturally?
- Is the original meaning preserved?
- Can you still hear the speaker's voice?
- Are all speakers clearly labeled?
When Not to Use
Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.
What ships with it: 1 file
192 B alongside SKILL.md
agents/
- openai.yaml192 B