Skip to content
Agentmart
Submit a tool

interview-synthesis

Synthesize supplied customer interview transcripts or notes into traceable Jobs-to-Be-Done, behavioral patterns, problems, contradictions, and research…

Skill by ThorStarlord

IndexedMIT
Write a review

Chalk Labs

Need help deploying interview-synthesis?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/thorstarlord-interview-synthesis

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

Synthesize supplied customer interview transcripts or notes into traceable Jobs-to-Be-Done, behavioral patterns, problems, contradictions, and research implications. Use when the active agent has a research-synthesis responsibility and actual interview evidence is available. Produce synthesis_report with source traceability; do not invent respondents, quotes, frequencies, or customer evidence.

Use cases: research, productivity, agent-building

Reviews

Write a review

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/interview-synthesis

What's inside

Skill name
interview-synthesis
Description
Synthesize supplied customer interview transcripts or notes into traceable Jobs-to-Be-Done, behavioral patterns, problems, contradictions, and research implications. Use when the active agent has a research-synthesis responsibility and actual interview evidence is available. Produce synthesis_report with source traceability; do not invent respondents, quotes, frequencies, or customer evidence.
License
MIT
Instructions
30 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • methodology.md · references/
  • output-contract.md · references/

SKILL.md (first lines)

# Interview synthesis

Satisfy a `research_synthesis` responsibility by producing `synthesis_report` from supplied interview evidence.

## Inputs

Require one or more identifiable interview sources plus the research context or question. Multiple interviews improve cross-respondent pattern analysis, but never invent extra respondents to meet a preferred sample size.

## Procedure

1. Read [references/methodology.md](references/methodology.md).
2. Assign or retain a stable source reference for every interview.
3. Extract candidate jobs, pains, gains, behaviors, alternatives, triggers, and direct quotes per source.
4. Cluster only patterns supported by supplied sources. Preserve meaningful contradictions and outliers.
5. Count frequency only from the actual supplied set.
6. Rank problems only when ranking dimensions are supportable; label agent-estimated severity separately from measured frequency.
7. Separate findings from recommendations and next research.
8. Render [references/output-contract.md](references/output-contract.md) and return control.

## Stop or reject

- If there is no actual interview evidence, do not manufacture a synthesis report; surface the missing input.
- Never invent respondents, quotes, frequencies, or source support.
- If source identity is too ambiguous to support traceability, request or derive stable local labels without fabricating provenance.

## Boundary

`source traceability != finding truth`, and `pattern frequency != strategic importance`.

From ThorStarlord/sensemaking-skills, MIT.

More from ThorStarlord/sensemaking-skills

Signals

Stars
0
Forks
0
Open issues
7
Last commit (this folder)
Sep 10, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/ThorStarlord/sensemaking-skills
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from ThorStarlord

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get interview-synthesis running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying interview-synthesis?

CallGet help
Cite this page

interview-synthesis skill. Agent Mart. https://agentmart.dev/skills/thorstarlord-interview-synthesis (last updated 2026-10-24)