Jtbd clustering
Cluster forces from multiple JTBD interviews to identify patterns. Use after extracting from multiple interviews.From its SKILL.md
npx -y skills add itseffi/agentic-os --skill jtbd-clusteringAssembled 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, 261 tokens by cl100k_base, as published. Nobody here has run it
JTBD Forces Clustering
Cluster and categorize forces from multiple interviews for pattern analysis.
When to Use
When you have JTBD extractions from multiple interviews and need to identify patterns across them.
The Process
-
Create a matrix:
- Rows = interview stories
- Columns = distinct forces
-
Code each interview:
- Start with first story's forces as initial columns
- For each new story:
- If force matches existing column: mark "1"
- If force is novel: add new column
-
Abstraction pass:
- Review columns for grouping opportunities
- Rename with overarching descriptors
- Merge similar forces
-
Analysis questions:
- Which forces appear most frequently?
- Which stories introduced unique forces?
- What patterns emerge across segments?
Output
- Spreadsheet summary: Number of stories and forces identified
- Force categories: Abstract labels for each column
- Unique contributors: Stories that introduced novel forces
- Patterns and insights: Notable observations
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