Synthetic user
A Claude skill that builds reusable customer profiles from clusters of real interview evidence, with every attribute cited to the session it came from and every gap marked.
Download the skill
Enter your details to download the skill file.
What it does
A synthetic user is a customer profile a model can speak as. Grounding decides whether it's worth anything: each trait traces to something a real person said in a real session, and the profile carries that citation wherever it goes. A profile spun up from a market description answers just as fluently with nothing behind it, which is the failure mode the technique is known for. The idea also travels under synthetic participant, AI persona, evidence-based persona and, in market research, digital twin.
This skill builds profiles from your research repository. It clusters sessions that behave alike, writes the profile from what the cluster actually contains, and footnotes each attribute to the session and moment it came from. Where the evidence stops, it says so and logs the gap as a question for your next round. Once a profile exists you can hand it an artifact, a PRD, a concept, a design or a draft survey question, and get a reaction written from that evidence base, citations still attached so you can check whether the reaction was earned.
What you get back
- One profile per cluster, listing the sessions it was built from by name and date.
- Per-attribute citations: the session, the moment and the line of transcript behind each claim.
- A gap list covering what the profile cannot speak to, written as questions for your next study.
- Reactions to any artifact you paste in, each traced to supporting evidence or marked as unsupported.
- A strength note per profile: how many sessions it rests on and how old the newest one is.
Install it in Claude, ChatGPT, Copilot or Gemini
The same skill file works in all four. Pick your tool for the steps.
Install in Claude
- 1
Download the skill
Fill in the short form to get the .skill file.
- 2
Add it to Claude
In the Claude app go to Settings → Capabilities → Skills and upload the file. In Claude Code, run the npx command shown after the form, or drop the folder into your project's skills folder.
- 3
Just ask
Ask in plain language. Claude picks up the skill on its own when the request matches.
Install in ChatGPT
- 1
Download and unzip the skill
The .skill file is a zip. Inside is SKILL.md, the instructions, plus any reference files the skill uses.
- 2
Make a Custom GPT or a Project
Create a Custom GPT (Explore GPTs → Create → Configure) or a Project. Paste SKILL.md into its instructions and upload the reference files as knowledge.
- 3
Just ask
Open that GPT or Project and ask in plain language. It follows the skill's method every time.
If the instructions box won't take the whole of SKILL.md, upload SKILL.md as a knowledge file instead and write one line of instructions: follow SKILL.md for every request.
Install in Microsoft Copilot
- 1
Download and unzip the skill
The .skill file is a zip. Inside is SKILL.md, the instructions, plus any reference files the skill uses.
- 2
Build a Copilot agent
In Microsoft 365 Copilot, open Agent Builder and create an agent. Paste SKILL.md into its instructions and add the reference files as knowledge.
- 3
Just ask
Open the agent and ask in plain language. Share it with your team so everyone runs the same method.
If the instructions box won't take the whole of SKILL.md, upload SKILL.md as a knowledge file instead and write one line of instructions: follow SKILL.md for every request.
Install in Gemini
- 1
Download and unzip the skill
The .skill file is a zip. Inside is SKILL.md, the instructions, plus any reference files the skill uses.
- 2
Make a Gem
In Gemini, go to Gems → New Gem. Paste SKILL.md into its instructions and add the reference files as knowledge.
- 3
Just ask
Open the Gem and ask in plain language. It follows the skill's method every time.
If the instructions box won't take the whole of SKILL.md, upload SKILL.md as a knowledge file instead and write one line of instructions: follow SKILL.md for every request.
How to use it
Once it's installed, ask in plain language. Your AI follows the skill's method when the request matches.
Build synthetic users from our onboarding research from the last two quarters.
Have the finance lead profile read this PRD and tell me which parts it has no evidence about.
Which of these profiles is resting on the thinnest evidence?
What it won't do
It won't stand in for talking to real people, and nothing it produces should be reported as a finding. A profile can only recombine what your repository already holds, so it will never surprise you the way a real interview does, and it knows nothing about what changed after your last session. Use it to sharpen what you'll ask before you spend recruiting budget.
Questions
Are synthetic users a replacement for interviews?
No. A profile is a compressed reading of research you already ran, so it can only repeat what real people already told you. Anything you need to learn fresh, and anything you would defend in front of a stakeholder, still means talking to real people.
What stops it inventing things?
Every attribute has to point at a session, and anything without one is marked as unsupported rather than written in. When a profile is asked something outside its evidence, it says the evidence doesn't cover it and adds the question to the gap list.
How much research do I need before profiles are useful?
Enough sessions in one cluster that a pattern is visible instead of a single person's story. The skill reports the cluster size behind each profile and flags the thin ones, so you can see when a profile is really one interview wearing a persona name.
More skills
See all skillsTranscript cleaner
Works on its ownA Claude skill that turns raw Otter, Fireflies, Granola and Zoom exports into transcripts you can analyse, with speakers resolved and timestamps kept where quoting needs them.
Research opsJune 4, 2026
Unmoderated test builder
Needs the Great Question MCPA Great Question skill that turns a concept or a task you describe into a working unmoderated study in your account, built and waiting for you to check it.
Study designAugust 27, 2026
Affinity mapper
Works on its ownA Claude skill that clusters raw research observations into themes bottom-up, then tells you which of those themes you should not trust yet.
SynthesisAugust 20, 2026
