Interview Note Cluster

Group interview notes into themes while keeping the participant.

Single skill Verified 20 Nov researchinterviewssynthesis

Use it for

Six or more interviews and a synthesis meeting next week

Skip it if

Two interviews — read them directly

What it is

Clusters notes into themes with participant counts and keeps contradictory observations separate. The discipline is arithmetic: a theme needs at least two participants to be called a theme, and single observations stay in their own list. That keeps the minority view from disappearing.

Install

Clone the repository, then copy the skill folder into your agent's skills directory — ~/.claude/skills/ for Claude Code. Skills are plain files: no build step, no daemon.

Terminal
npx skills add interview-cluster

How to judge it

Read the SKILL.md before you install. A good skill states when it applies, what it must not do, and how to verify the result. A skill that only lists adjectives will change the agent's tone without improving its output — skip those.

Other research skills

  • Source Dating — Add the date and context to claims that need them.
  • Market Map — Lay out a category by segment and player, with what each claims.
  • Evidence Table — One row per source, one column per question, quotes in cells.

Tools it pairs with

All tools

Servers it runs on

All servers
  • 01
    Telegram MCPCommunity

    Reads channels and groups through the Bot API: recent messages, search, and posting. The distinction that matters is bot token versus user session — a bot sees what …

    #chat#monitoring#research
    Pythonstdio
  • 02
    YouTube MCPCommunity

    Wraps the YouTube Data API for search, channel and video metadata, and captions where available. The transcript path is the useful one for research; anything that re…

    #video#research#transcripts
    Pythonstdio
  • 03
    Hugging Face MCPCommunity

    Searches Hugging Face models and datasets and returns metadata: task, licence, downloads, and the card text. The useful workflow is the decision before the download …

    #models#datasets#research
    Pythonstdio