Great Question (greatquestion.co) platform help — an all-in-one UX research platform: recruit real participants (6M+ B2B/B2C panel or your own customers in a built-in Research CRM), run moderated and AI-moderated (beta) interviews, unmoderated Figma prototype tests, surveys, card sorting, tree testing and focus groups, then analyze in a repository (AI synthesis, highlight reels). Unusually complete automation: a V1.0 REST API (Bearer; studies, candidates, sessions), HMAC-signed webhooks, AND a native MCP server (112+ actions, Enterprise). Use when setting up a Great Question study or recruit, syncing research into a CRM or warehouse, building a Great Question API or webhook pipeline, wiring its MCP server into Claude Code, or reading its per-seat self-serve vs Enterprise pricing. Do NOT use for the validate-before-building method or comparing research tools broadly (use /sales-idea-validation), or analyzing existing NPS/CSAT/VoC feedback (use /sales-customer-feedback).
Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
Great Question (greatquestion.co) platform help — an all-in-one UX research platform: recruit real participants (6M+ B2B/B2C panel or your own customers in a built-in Research CRM), run moderated and AI-moderated (beta) interviews, unmoderated Figma prototype tests, surveys, card sorting, tree testing and focus groups, then analyze in a repository (AI synthesis, highlight reels). Unusually complete automation: a V1.0 REST API (Bearer; studies, candidates, sessions), HMAC-signed webhooks, AND a native MCP server (112+ actions, Enterprise). Use when setting up a Great Question study or recruit, syncing research into a CRM or warehouse, building a Great Question API or webhook pipeline, wiring its MCP server into Claude Code, or reading its per-seat self-serve vs Enterprise pricing. Do NOT use for the validate-before-building method or comparing research tools broadly (use /sales-idea-validation), or analyzing existing NPS/CSAT/VoC feedback (use /sales-customer-feedback).
argument-hint
[describe what you need help with in Great Question]
license
MIT
version
1.0.2
github
https://github.com/GreatQuestion
tags
["sales","pre-launch","platform"]
Great Question Platform Help
Great Question (greatquestion.co) is an all-in-one UX research platform — "the UX research platform
for every team building and improving products." It bundles three jobs teams usually buy separately:
recruit (a 6M+ B2B/B2C paneland your own customers via a built-in Research CRM —
segmentation, eligibility rules, scheduling, automated incentives via Tremendous), run studies
(moderated + AI-moderated [beta] interviews, unmoderated Figma prototype testing, surveys, focus
groups, card sorting, tree testing, online tasks, observer rooms, blind studies), and analyze & store
(a centralized research repository, AI synthesis, highlight reels).
Its place in the landscape is the research-ops / real-participant class — closest to User Interviews
(recruitment) + Dovetail (repository) combined, run on real people. It is not a synthetic-persona
tool (Synthetic Users, Ditto) and not a pure AI-moderated-interview tool (User Intuition, Strella,
Voicepanel) — moderation is primarily human/scheduled, with AI moderation in beta.
Two things to say almost every time:
Real research, but a stated "I'd pay" is still not a purchase. Interviews and unmoderated tasks surface
genuine reasoning/objections/language (strong signal) — but the WTP go/no-go belongs to a real behavior test (pre-sale, smoke test), not a transcript → /sales-idea-validation.
The automation surface is unusually complete — pick the right one. Great Question has a REST API, HMAC-signed webhooks,
and a native MCP server all at once (MCP for agent ops, REST for a pipeline, webhooks for event sync) — but note the gates: API tokens need Team/Enterprise, and MCP is Enterprise/early-access.
Step 1 — Gather context
If references/learnings.md exists, read it first for accumulated platform knowledge.
Ask only what you can't infer:
What do you want from Great Question?
A) Set up a study — pick a method (moderated/AI-moderated interview, unmoderated Figma test,
survey, card sort, tree test, focus group), objective, screener, incentive
B) Recruit — the 6M+ panel (screening/eligibility) vs your own customers (Research CRM import)
C) Analyze — repository, AI synthesis, highlight reels, sessions
D) Automate / integrate — REST API pipeline, webhooks, the MCP server, or Zapier/Make
E) Choose / price — self-serve ($129/seat, 5-seat cap) vs Enterprise, or GQ vs another tool
Is this discovery (strangers on the panel) or feedback from your own users? That decides panel
vs Research-CRM and how honest the signal is.
Skip-ahead: if the user wants to compare research tools across the market or the
validate-before-building method, that's a /sales-idea-validation question — route in Step 2.
Step 2 — Route or answer directly
If the user's question is about…
Route to
Comparing research/idea/synthetic tools across the market, or the validate-before-building method
/sales-idea-validation {question}
Running a real behavior demand test (smoke-test page, waitlist, pre-sale) after research
/sales-idea-validation or /sales-funnel{question}
Analyzing existing NPS/CSAT/VoC feedback (post-launch surveys, not new studies)
/sales-customer-feedback {question}
A synthetic-persona approach (AI personas instead of real people)
/sales-syntheticusers or /sales-ditto{question}
A pure AI-moderated real-human interview tool with a self-serve API/webhooks
/sales-userintuition {question}
When routing, give the exact command: "This is a {domain} question — run: /sales-idea-validation {original question}"
Otherwise, answer Great Question-specific questions using Step 3.
Step 3 — Great Question reference
Read references/platform-guide.md for the full reference — the module/automation-surface table
(API vs webhook vs MCP vs UI-only), best-effort pricing/plan gates, the Study → Candidate → Participant →
Session data model, recruiting (panel vs Research CRM), and quick-start recipes (REST sync, CRM upsert,
webhook verification, MCP). Read references/great-question-api-reference.md for the verbatim API
surface (Bearer auth + non-standard header, endpoints, JSON models, webhook HMAC, MCP). Answer using only
the relevant section — don't dump the full reference.
Step 4 — Actionable guidance
Say the caveat: real research is not a purchase. Whatever the user asks, make explicit that Great
Question studies real people (a step up from synthetic personas — genuine reasoning, objections,
language), but a stated "I'd pay" in an interview/survey is not observed demand. Keep the
why/objections/language; take the go/no-go from a real behavior test (smoke-test click, pre-sale)
→ /sales-idea-validation.
Match the automation surface to the job, and name the gates. Great Question has all three: REST
API (data pipeline into a CRM/warehouse), HMAC-signed webhooks (event-driven sync), and a
native MCP server (agent-driven study/candidate ops from Claude/Cursor). Recommend by job — but
always state the plan gates: API tokens require Team/Enterprise (admin-generated at Account >
API tokens; access enabled by support), and MCP is Enterprise/early-access. No self-serve API key.
For webhooks, warn it's concierge + no retries. Endpoints are set up by contacting support (no
self-serve UI) and there's no documented retry policy — verify the HMAC signature
(X-Signature-SHA256: t=<ts>,v1=<sig>, sign ts + "." + body, timing-safe compare) and add a
reconcile poll (GET /v1/studies/{id}/participants) to catch missed participation.completed events.
Note the non-standard auth header and beta status. The documented header is literally
Authorization: "BEARER: <token>" (with BEARER: and quotes) and the API is V1.0 / beta, under
active development — tell the user to confirm the exact header spelling and base host in their
Account > API tokens screen, and to code defensively against changes.
Watch the 5-seat self-serve cap. Self-Serve is $129/seat/mo, capped at 5 seats (unlimited free
observer seats). Focus groups, card sort/tree test, Salesforce/Snowflake/Qualtrics/Databricks
connectors, SSO/SCIM, HIPAA, and MCP are Enterprise-only (quote-only). If the user needs any of
those or a 6th seat, they're on the Enterprise path — flag it early; present all pricing as best-effort
(confirm at greatquestion.co/pricing).
Panel vs Research CRM: match to the question. The 6M+ panel reaches strangers for
discovery/concept tests; your own customers (CSV import, POST /v1/candidates upsert by email, or
Salesforce/Snowflake connectors) are the honest audience for churn/win-loss feedback — check
consented_at/unsubscribed before contacting; use POST /v1/studies/{id}/candidates (≤5,000, poll
status_url) for a study-scoped batch. Before wiring MCP, enable "Hide PII via MCP" and connect
with a role scoped to what the agent should do (MCP mirrors your in-app permissions).
If you discover a gotcha or tip not in references/learnings.md, append it there with today's date.
Gotchas
Best-effort from research (2026-07) — pricing ($129/seat self-serve, 5-seat cap; Enterprise quote-only),
panel size ("6M+"), the V1.0-beta API surface, and MCP early-access status all move; verify at
greatquestion.co/pricing and developer.greatquestion.co.
Real ≠ demand. Studies reveal the why better than any synthetic tool, but a stated intent to pay
is not a purchase — the go/no-go still belongs to a real behavior test (pre-sale, smoke test).
API tokens are plan-gated (Team/Enterprise) and access must be enabled. Not available on the
$129 self-serve plan by default — admins generate tokens at Account > API tokens, and support must
enable API access for the workspace. Don't assume an instant key.
The auth header is non-standard. Documented as Authorization: "BEARER: <token>" (with the colon
and quotes) — verify exact spelling in-app; the API is V1.0/beta, so code defensively.
Webhooks are concierge-registered with no documented retries. Email support to set up an endpoint;
verify the HMAC signature and poll to reconcile missed participation.completed events.
MCP is Enterprise / early-access.https://greatquestion.co/api/mcp/v1 (OAuth, 112+ actions) is
not instant self-serve — request access. Enable "Hide PII via MCP" and connect with a scoped role.
The 5-seat self-serve cap + Enterprise-only methods are the real constraints. A growing team (6th
seat), focus groups, card sorting, tree testing, warehouse/CRM connectors, SSO, HIPAA, or MCP all
push you to Enterprise (quote-only) — don't design a self-serve card-sort study.
G2 reviewers flag occasional bugs, slow performance, and "limited survey features." Set
expectations for complex surveys; the platform's strength is consolidation, not depth in every module.
Related skills
/sales-idea-validation — The tool-agnostic validate-before-building method + the full research/persona/validator tool landscape (use this to decide build-or-not; a research "yes" is not demand). Install: npx skills add sales-skills/sales --skill sales-idea-validation -a claude-code
/sales-customer-feedback — Analyze existing NPS/CSAT/VoC feedback across tools (Great Question runs new studies and stores them in its repository; this is the post-launch feedback-strategy peer). Install: npx skills add sales-skills/sales --skill sales-customer-feedback -a claude-code
/sales-notably — Notably (notably.ai) — the analysis-only research repository peer: it synthesizes qualitative data you already have (transcripts/notes/open-ends) into AI-clustered themes + insights, where Great Question recruits and runs the studies that produce that data. The pick for the synthesis step once you have data — but it has no panel/recruiting and no API/webhooks/MCP (Miro/FigJam sync + manual export only). Install: npx skills add sales-skills/sales --skill sales-notably -a claude-code
/sales-userintuition — Pure real-human AI-moderated interviews with a self-serve REST API + webhooks + MCP — the pick when you want deep automated interviews, not an all-in-one recruit+repository suite. Install: npx skills add sales-skills/sales --skill sales-userintuition -a claude-code
/sales-respondent — Respondent (respondent.io) — the recruit-only peer (the direct twin of User Interviews): recruit + screen + schedule + pay real participants from a 4M+ B2B/professional panel via a Partner REST API, then run the study in your own tool. The pick when you only need recruiting (not Great Question's run + repository). Install: npx skills add sales-skills/sales --skill sales-respondent -a claude-code
/sales-lookback — Lookback (lookback.com) — the self-serve, run-the-live-session peer: live/moderated video interviews + usability tests with observer rooms and best-in-class mobile screen+gesture recording (recruits via User Interviews, no own panel). The pick when you want to run the live session yourself rather than Great Question's all-in-one recruit+repository suite — but it's UI-first (no self-serve API). Install: npx skills add sales-skills/sales --skill sales-lookback -a claude-code
/sales-participant-kit — Participant Kit (participantkit.com, formerly Consent Kit) — the consent + participant-ops peer: informed consent forms/NDAs with e-signatures + audit trail, a participant CRM + opt-in panels, retention/deletion reminders, and UK/EU data residency — the compliance/ops layer around studies, where Great Question runs and stores them. The pick when the job is consent/GDPR governance, not recruit-and-run — but its API is Enterprise + request-only (no webhooks/MCP). Install: npx skills add sales-skills/sales --skill sales-participant-kit -a claude-code
/sales-syntheticusers — Synthetic-research studies (AI personas, not real people) for a fast, cheap directional pre-test before spending on real recruits. Install: npx skills add sales-skills/sales --skill sales-syntheticusers -a claude-code
/sales-funnel — Build the smoke-test / fake-door landing page that turns a research hypothesis into a real demand test. Install: npx skills add sales-skills/sales --skill sales-funnel -a claude-code
/sales-do — Not sure which skill to use? The router matches any sales objective to the right skill. Install: npx skills add sales-skills/sales --skill sales-do -a claude-code
Examples
Example 1: "How do I sync completed Great Question research into my warehouse?" (developer/automation)
User says: "I want completed interviews and participant data flowing into Snowflake automatically."
Skill does: Lays out the three surfaces and picks by job — a REST pipeline (GET /v1/studies?status=closed → GET /v1/studies/{id}/participants, paginated 100/page, Bearer auth) for a
scheduled pull, plus participation.completed webhooks (HMAC-verified) for near-real-time sync,
with a poll to reconcile since retries are undocumented. Flags that API tokens require a
Team/Enterprise plan and API access must be enabled by support, and that the header is the
non-standard Authorization: "BEARER: <token>". Notes native Snowflake/Salesforce connectors are
Enterprise-gated as a no-code alternative.
Result: The user builds a webhook + reconcile-poll pipeline and knows the plan gate up front.
Example 2: "The interviews loved my concept — should I build it?"
User says: "I ran 15 Great Question interviews and a survey; people said they'd pay. Green light?"
Skill does: Credits the signal as real (actual people, genuine reasoning — far better than a
synthetic tool), then draws the line: a stated "I'd pay" in a study is not a purchase. Tells the
user to mine the repository highlight reels and transcripts for objections, hesitation, and pricing
language, then take the go/no-go from a real behavior test (pre-sale or "buy" click) via
/sales-idea-validation.
Result: The founder keeps the qualitative depth and runs a pre-sale before committing to build.
Example 3: "Is the $129 plan enough for my team, and can I run a card sort?"
User says: "We're 6 people and want card sorting and Salesforce sync on the self-serve plan."
Skill does: Flags two Enterprise gates on Self-Serve: it's capped at 5 seats (a 6th person
pushes you to Enterprise), and card sorting, tree testing, and the Salesforce/Snowflake connectors
are Enterprise-only. Explains Self-Serve is $129/seat/mo (unlimited free observer seats, 100
participants / 100 hr storage) and Enterprise is quote-only, all best-effort — confirm at
greatquestion.co/pricing.
Result: The team plans the Enterprise conversation instead of hitting the wall mid-setup.
Troubleshooting
"Where's my Great Question API key? I'm on the self-serve plan"
Symptom: You can't find an API token screen or your calls 401.
Cause: API tokens require a Team or Enterprise plan, are admin-generated (Account > API
tokens), and API access must be enabled for the workspace by Great Question support.
Solution: Confirm you're on Team/Enterprise, have an admin generate the token, and email
support@greatquestion.co to enable API access. Use the documented header exactly:
Authorization: "BEARER: <token>" (verify the spelling in-app; the API is V1.0/beta).
"My webhook never fired / I missed a completion event"
Symptom: participation.completed didn't arrive, or arrived and you can't verify it.
Cause: Webhook endpoints are registered by contacting support (no self-serve UI), and there's
no documented retry policy.
Solution: Ask support to register your endpoint; verify each request's X-Signature-SHA256
(t=<ts>,v1=<sig> — sign ts + "." + rawBody with HMAC-SHA256, timing-safe compare); and add a
reconcile poll (GET /v1/studies/{id}/participants) to catch anything the webhook missed.
"My agent can't run a card sort / can't see a study over MCP"
Symptom: The MCP connection works but a method or study is unavailable.
Cause: MCP mirrors your in-app role and plan — card sorting/tree testing/focus groups are
Enterprise-only, and if a study is hidden from your UI role it's hidden from MCP. MCP itself is
Enterprise/early-access.
Solution: Confirm MCP access is enabled (request it), connect with a role scoped to the studies you
need, and enable "Hide PII via MCP" to redact candidate PII before it reaches the agent. For
Enterprise-only methods, use the UI on an Enterprise plan.
