How do I install the Transcript To CSV skill?

Run npx skillmds@latest add bookwormsuf/transcript-to-csv in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Transcript To CSV safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Transcript To CSV?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Transcript To CSV free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Transcript To CSV?

bookwormsuf (@bookwormsuf) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Transcript To CSV by bookwormsuf — Agent Skill

Name: Transcript To CSV
Author: bookwormsuf

Transcript To CSV

Convert interview/UX research transcripts into CSV files for qualitative coding analysis. Use when the user has a transcript with SPEAKER_XX: utterance format (markdown or plain text) and wants to create a spreadsheet for coding, tagging, or analysis. Triggers on: 'convert transcript to csv', 'parse transcript', 'create coding sheet from transcript', 'transcript for qualitative analysis', interview transcripts, UX research sessions.

bookwormsuf 23bb447 2 files · 4.7 KB Updated Sep 17, 2026

File contents

Transcript to CSV Skill

Converts interview transcripts into CSV format suitable for qualitative content analysis and coding.

Input Formats Supported

Markdown format:

**SPEAKER_00**: This is what they said.
**SPEAKER_01**: And this is the response.

Plain text format:

SPEAKER_00: This is what they said.
SPEAKER_01: And this is the response.

Output Format

CSV with these columns:

# - Sequential utterance number (1, 2, 3...)
Speaker - Speaker identifier (SPEAKER_00, SPEAKER_01, etc.)
Utterance - The spoken text
Code 1 - Empty column for primary coding
Code 2 - Empty column for secondary coding
Notes - Empty column for analyst notes

How to Convert

Option 1: Use the bundled script (recommended for large files)

cd /path/to/transcript/folder
bash scripts/parse-transcript.sh transcript.md output.csv
# scripts/parse-transcript.sh is resolved relative to this skill's folder

Option 2: One-liner for markdown transcripts

echo '#,Speaker,Utterance,Code 1,Code 2,Notes' > output.csv && \
grep '^\*\*SPEAKER' transcript.md | \
awk -F': ' 'BEGIN{n=1} {
  speaker=$1;
  gsub(/\*\*/,"",speaker);
  utterance=$0;
  sub(/^[^:]+: /,"",utterance);
  gsub(/"/, "\"\"", utterance);
  print n","speaker",\""utterance"\",,,";
  n++
}' >> output.csv

Option 3: One-liner for plain text transcripts

echo '#,Speaker,Utterance,Code 1,Code 2,Notes' > output.csv && \
grep '^SPEAKER' transcript.txt | \
awk -F': ' 'BEGIN{n=1} {
  speaker=$1;
  utterance=$0;
  sub(/^[^:]+: /,"",utterance);
  gsub(/"/, "\"\"", utterance);
  print n","speaker",\""utterance"\",,,";
  n++
}' >> output.csv

Script Explanation

The parsing script does the following:

grep '^\*\*SPEAKER' - Find lines starting with **SPEAKER (markdown) or SPEAKER (plain text)
awk -F': ' - Split each line on : (colon-space)
gsub(/\*\*/,"",speaker) - Remove ** markdown formatting from speaker name
sub(/^[^:]+: /,"",utterance) - Extract utterance text (everything after the first colon-space)
gsub(/"/, "\"\"", utterance) - Escape quotes by doubling them (CSV standard)
Output - Format as numbered CSV row with empty coding columns

Workflow Tips

Naming convention: Use P1-YYYY-MM-DD.csv format for participant files
Folder structure: Keep transcript.md, summary.md, and the CSV in the same participant folder
After conversion: Open in Excel/Sheets to add codes in the empty columns

---name: transcript-to-csvdescription: Convert interview/UX research transcripts into CSV files for qualitative coding analysis. Use when the user has a transcript with SPEAKER_XX: utterance format (markdown or plain text) and wants to create a spreadsheet for coding, tagging, or analysis. Triggers on: 'convert transcript to csv', 'parse transcript', 'create coding sheet from transcript', 'transcript for qualitative analysis', interview transcripts, UX research sessions.---# Transcript to CSV SkillConverts interview transcripts into CSV format suitable for qualitative content analysis and coding.## Input Formats Supported**Markdown format:**```**SPEAKER_00**: This is what they said.**SPEAKER_01**: And this is the response.```**Plain text format:**```SPEAKER_00: This is what they said.SPEAKER_01: And this is the response.```## Output FormatCSV with these columns:- `#` - Sequential utterance number (1, 2, 3...)- `Speaker` - Speaker identifier (SPEAKER_00, SPEAKER_01, etc.)- `Utterance` - The spoken text- `Code 1` - Empty column for primary coding- `Code 2` - Empty column for secondary coding- `Notes` - Empty column for analyst notes## How to Convert### Option 1: Use the bundled script (recommended for large files)```bashcd /path/to/transcript/folderbash scripts/parse-transcript.sh transcript.md output.csv# scripts/parse-transcript.sh is resolved relative to this skill's folder```### Option 2: One-liner for markdown transcripts```bashecho '#,Speaker,Utterance,Code 1,Code 2,Notes' > output.csv && \grep '^\*\*SPEAKER' transcript.md | \awk -F': ' 'BEGIN{n=1} { speaker=$1; gsub(/\*\*/,"",speaker); utterance=$0; sub(/^[^:]+: /,"",utterance); gsub(/"/, "\"\"", utterance); print n","speaker",\""utterance"\",,,"; n++}' >> output.csv```### Option 3: One-liner for plain text transcripts```bashecho '#,Speaker,Utterance,Code 1,Code 2,Notes' > output.csv && \grep '^SPEAKER' transcript.txt | \awk -F': ' 'BEGIN{n=1} { speaker=$1; utterance=$0; sub(/^[^:]+: /,"",utterance); gsub(/"/, "\"\"", utterance); print n","speaker",\""utterance"\",,,"; n++}' >> output.csv```## Script ExplanationThe parsing script does the following:1. **`grep '^\*\*SPEAKER'`** - Find lines starting with `**SPEAKER` (markdown) or `SPEAKER` (plain text)2. **`awk -F': '`** - Split each line on `: ` (colon-space)3. **`gsub(/\*\*/,"",speaker)`** - Remove `**` markdown formatting from speaker name4. **`sub(/^[^:]+: /,"",utterance)`** - Extract utterance text (everything after the first colon-space)5. **`gsub(/"/, "\"\"", utterance)`** - Escape quotes by doubling them (CSV standard)6. **Output** - Format as numbered CSV row with empty coding columns## Workflow Tips1. **Naming convention**: Use `P1-YYYY-MM-DD.csv` format for participant files2. **Folder structure**: Keep transcript.md, summary.md, and the CSV in the same participant folder3. **After conversion**: Open in Excel/Sheets to add codes in the empty columns

Frequently asked questions