← All skills · Automation · Customer Research Synthesizer

Customer Research Synthesizer — finished output

Runs inClaude Code Codex Cursor

Muse

Dot Grok Bot

Cue OpenClaw

Hermes

Install guidesClaude Code Codex Cursor Muse

Needs:Your interview notes: research.txt (Project and Goal lines, then one Interview line per participant — id | who they are — one Quote line per verbatim quote — participant id | "exact words" | theme tag — one Note line per paraphrased observation, and one Job line per jobs-to-be-done statement — When…, I want…, so I can… | theme tag).

Automation Premium

Customer Research Synthesizer

Turn interview notes into themes, verbatim-backed quotes, and jobs-to-be-done statements: each theme scored by how many distinct participants said it, each quote printed exactly as recorded, and each job linked to the quotes that support it — or marked a draft when it has none.

Version 1.0.0

Subscribe — All Skills, one subscription.No exclusions. Curated, verified, and continuously updated.

Get this Skill with Premium See plans

Reads one plain-text file you write — research.txt, with a Project line and a Goal line, plus Interview lines (id | who they are), Quote lines (participant id | "the exact words" | theme tag), Note lines (participant id | observation), and Job lines (When…, I want…, so I can… | theme tag) — and produces synthesis.md: the project and goal first, then the themes table (each theme with its participant count, quote count, and strength: Strong at 3+ distinct participants, Emerging at exactly 2, Thin at 1), then the verbatim quotes behind each theme, then the jobs to be done with their supporting quotes. Strength counts distinct people, not quote volume: one person saying the same thing three times is still Thin. Local-only, standard library only; a quote or note naming a participant who was never interviewed is dropped and named, a duplicate quote is dropped and named, and a job with no supporting quotes is listed as a draft — the synthesis is a document, it runs no interviews and decides nothing about what to build.

Good fit Seeing what keeps coming up across a pile of interview notes Backing a conclusion with participants' own words instead of your paraphrase Checking which job actually has evidence before building on it

Similar Skills

Premium

Email Triage Automation

Read full threads
Sort into 3 buckets
Draft in your voice
Approve & send

Premium

Smart Scheduling Automation

Gather constraints
Check all calendars
Offer local times
Hold or invite

Free

Deadline-Driven Follow-Up

Capture the cutoff
Watch for stalls
Nudge at 3 points
Close the loop

Premium

Durable Bulk Execution

Shard the list
Checkpoint each item
Idempotent runs
Verify completion

View all skills →

What you get

A themes table: each theme's participant count, quote count, and strength (Strong / Emerging / Thin)
Up to two verbatim quotes behind each theme, with participant id and who they are
Each jobs-to-be-done statement with its supporting-quote count; unsupported jobs marked as drafts
Every gap, input error, and warning named in the report

Good fit

Seeing what keeps coming up across a pile of interview notes
Backing a conclusion with participants' own words instead of your paraphrase
Checking which job actually has evidence before building on it

Not for

Treating repetition as consensus — strength counts people, not quote volume
Rewriting or smoothing quotes — verbatim words are printed exactly as recorded
Running interviews or recruiting participants — the synthesis is a document

Sample output

An example of what this Skill produces. Sample content, shown for illustration.

Customer Research Synthesizer report — sample

Interviews: 3 | Quotes: 6 | Themes: 3 | Jobs: 3 | Gaps: 1 | Errors: 0 | Warnings: 0

Themes: Trust in the login link — Strong (3 people, 3 quotes) · The first download — Emerging (2 people, 2 quotes) · The daily check-in — Thin (1 person, 1 quote).

Jobs: "When I buy a skill, I want the first download to work on the first try…" — 2 supporting quotes (first-download); "When I sign in with a magic link, I want to see immediately that it worked…" — 3 supporting quotes (login-trust).

Gaps: 1 theme is thin (daily-habit) — treat as a lead, not a finding.

About this Skill

You say

Synthesize these interview notes — themes with verbatim quotes, and jobs to be done with their supporting evidence.

How to install

Copy the install prompt into your agent: Read https://skillu.dev/install/agent.md, then install the Customer Research Synthesizer skill (customer-research-synthesizer).
Or download the Skill package from this page after launch and place its folder in your agent’s skills directory.
Call it with a slash command, e.g. /customer-research-synthesizer, and describe what you want in plain words.

FAQ

How is a theme's strength decided?

Only by how many distinct participants said that theme: 3 or more is Strong, exactly 2 is Emerging, 1 is Thin — Thin is a lead, not a finding. One person saying the same thing three times is still Thin; strength counts people, not quote volume.

What happens to a job with no supporting quotes?

It stays in the synthesis and is marked as a draft, not evidence, with a gap naming how many jobs have no supporting quotes — a job statement with no verbatim words behind it is your interpretation, not something participants said. Add Quote lines with the relevant quotes and re-run.

Get Premium access Browse more skills