Stakeholder readout generator
What it does
A stakeholder readout is the version of the research other people actually read: findings stated plainly, ordered by what the audience has to decide, with evidence attached. It gets called a research share-out, a debrief, a topline, or just the deck, depending on the team. The failure mode is always the same. Findings get flattened into assertions and the evidence stays in a folder nobody opens. Six weeks later somebody asks where a number came from and nobody can answer.
This skill builds the readout from a study that already exists in your Great Question repo. It reads the sessions, transcripts and highlights from that study, writes the findings, and keeps each one attached to the highlights it came from, so a stakeholder who doubts a finding can watch the moment it rests on. Traceability is the point of running this against the repo rather than a folder of documents. It works from Claude, Cursor or ChatGPT once the Great Question MCP is connected, and what it produces lands as an insight in your repo, the object that already holds your findings and stories.
What you get back
- Findings written from the study's own sessions, ordered for the audience you name.
- The session highlights behind each finding, linked so anyone can open the source.
- The participants each finding rests on, and how many of them there were.
- Open questions the study did not answer, kept in rather than quietly dropped.
- A readout saved into your Great Question repo as an insight, sitting with the rest of your findings.
How to use it
Example Prompts:
"Build the readout for the reconciliation study, audience is the payments PM and her eng lead."
"Same study, but a five-minute version for the exec review on Thursday."
"Which findings only rest on one participant? Flag them in the readout."
What it won't do
It won't decide what your team should do about the findings, and it won't manufacture confidence in a thin one. A finding that rests on two people is reported as resting on two people. It also references highlights rather than creating them, so a study nobody has clipped yet gives it less to work from, and sessions that never made it into the repo are invisible to it.
Questions
How is this different from the stakeholder readout Claude skill?
The Claude skill works on files you hand it and needs no account, which suits work that lives outside the platform. This one reads the actual study in your repo and links every finding back to the session highlight it came from. Same output shape, different evidence trail.
Where does the readout end up?
As an insight in your Great Question repo. Insights are the object that holds research findings and stories in the platform, so the readout sits with the studies and sessions it was built from and stays searchable next to the rest of your work.
Does it use highlights my team made, or does it make its own?
It uses the ones your team already made. There is no operation for creating a highlight, so the clips people took while reviewing sessions are the evidence it reaches for. A study nobody has been through yet gives it less to work with.
