Skip to content
Agentmart
Submit a tool

user-interviews

Plan, conduct, and analyze user interviews.

Skill by henrique-simoes

IndexedMIT★ 16
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/henrique-simoes-user-interviews

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Plan, conduct, and analyze user interviews. Generate interview guides, process transcripts, extract nuggets and themes, synthesize findings.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/user-interviews

What's inside

Skill name
user-interviews
Description
Plan, conduct, and analyze user interviews. Generate interview guides, process transcripts, extract nuggets and themes, synthesize findings.
License
MIT
Instructions
41 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# User Interviews

## Capabilities

- Generate semi-structured interview guides from research questions and project context
- Process interview transcripts (TXT, PDF, DOCX) — extract nuggets, themes, patterns
- Identify follow-up questions and research gaps
- Synthesize findings across multiple interviews with cross-cutting themes
- Calculate intercoder reliability when multiple coders are involved

## Workflow

1. **Plan** — Provide research questions → receive interview guide with probes
2. **Conduct** — Use the guide (Istara provides facilitation tips)
3. **Upload** — Drop transcript files into the project
4. **Analyze** — Istara extracts nuggets, tags themes, scores confidence
5. **Synthesize** — Cross-interview patterns → facts → insights → recommendations

## Input

- Research questions (text)
- Interview transcripts (TXT, PDF, DOCX, MD)
- Project context (auto-loaded from context layers)

## Output

- Interview guide (Markdown)
- Nuggets with source references and timestamps
- Thematic analysis with strength indicators
- Pain points with severity ratings
- Synthesis report with cross-cutting themes and evidence chains

## Best Practices

- 5-8 participants per segment for saturation
- 45-60 min per session
- Always record with consent
- "Tell me more" > "Did you like it?"
- Probes yield the best insights, not scripted questions

From henrique-simoes/Istara, MIT.

More from henrique-simoes/Istara

Signals

Stars
16
Forks
5
Open issues
15
Last commit (this folder)
Mar 30, 2026 (7 months ago)
Last release
Sep 27, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from henrique-simoes

Cite this page

user-interviews skill. Agent Mart. https://agentmart.dev/skills/henrique-simoes-user-interviews (last updated 2026-10-24)