Userbrain (userbrain.com) platform help — a self-serve, video-first unmoderated usability-testing tool: real testers record their screen and think aloud while doing your tasks on a website, mobile app, or prototype (Figma/Adobe XD), with AI-marked highlights, transcripts, auto reports, and shareable clips. Recruit from a 170k+ tester panel (pay-per-session) or invite your own users via a share link, and run continuous auto-recurring tests. UI-only — no public API, webhooks, Zapier, or MCP; results leave as video, clips, transcripts, or PDF reports. Use when setting up a think-aloud usability test, getting surface-level tester feedback, hitting demographic-targeting limits, testing on mobile (iOS/Android), confused by subscription vs pay-per-tester pricing, or exporting results without an API. Do NOT use for card sorting / tree testing / first-click IA tests or comparing usability tools (use /sales-uxtweak or /sales-idea-validation), or an API-native interview pipeline (use /sales-userintuition).
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Une commande directe contourne le prompt de vérification. Examinez la source avant de l'exécuter.
Userbrain (userbrain.com) platform help — a self-serve, video-first unmoderated usability-testing tool: real testers record their screen and think aloud while doing your tasks on a website, mobile app, or prototype (Figma/Adobe XD), with AI-marked highlights, transcripts, auto reports, and shareable clips. Recruit from a 170k+ tester panel (pay-per-session) or invite your own users via a share link, and run continuous auto-recurring tests. UI-only — no public API, webhooks, Zapier, or MCP; results leave as video, clips, transcripts, or PDF reports. Use when setting up a think-aloud usability test, getting surface-level tester feedback, hitting demographic-targeting limits, testing on mobile (iOS/Android), confused by subscription vs pay-per-tester pricing, or exporting results without an API. Do NOT use for card sorting / tree testing / first-click IA tests or comparing usability tools (use /sales-uxtweak or /sales-idea-validation), or an API-native interview pipeline (use /sales-userintuition).
argument-hint
[describe what you need help with in Userbrain]
license
MIT
version
1.0.2
tags
["sales","pre-launch","platform"]
Userbrain Platform Help
Userbrain (userbrain.com) is a self-serve, video-first unmoderated usability-testing tool — the
narrow, cheap pick when you want to watch real people use your website, app, or prototype and hear
why they struggle. Testers record their screen and voice and think aloud while completing
the tasks you write; you get back AI-marked highlights, transcripts, auto-generated
reports, and clips. Recruit from its 170k+ tester panel (per session) or invite your own users via a share link; tests can run continuously (auto-recurring).
Two things to say almost every time:
Userbrain tests a built thing, and a smooth think-aloud session is not validated demand. Watching
a stranger complete a task tells you the design works and why it confuses them — it does not
tell you they'd pay. If the user is still deciding whether to build at all, that willingness-to-pay
go/no-go belongs to a real behavior test (smoke test, pre-sale) — route to /sales-idea-validation.
Userbrain is UI-only. There is no public API, no webhooks, no Zapier, no MCP — so any "pipe
results into my CRM/warehouse/Slack" ask is manual export (video download, clip, transcript, PDF
report), not a REST integration. If the user needs an API-native research pipeline, that's
/sales-userintuition, not Userbrain.
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 Userbrain?
A) Set up a test — write tasks/questions, pick device (desktop / mobile / prototype), use a template
B) Recruit testers — the 170k+ panel (pay-per-session) vs inviting your own users via share link
C) Read results — AI highlights, transcripts, auto reports, cutting clips
D) Fix bad feedback — testers giving surface-level "looks easy" answers instead of real critique
E) Get data out — export video/clips/transcripts/PDF (no API — manual only)
F) — Userbrain vs UserTesting / Maze / Lyssna / UXtweak for your use case
Choose
Are you testing something you've already built/designed, or still deciding whether to build? The
second is an idea-validation question, not a usability question — flag it in Step 2.
Skip-ahead: if the user's prompt already names the task and their question is specific, go to Step 3.
Step 2 — Route or answer directly
If the user's question is about…
Route to
Card sorting / tree testing / first-click / five-second / preference IA tests (Userbrain has none)
/sales-uxtweak {question}
Comparing usability/research/idea tools across the market, or the validate-before-building method
/sales-idea-validation {question}
An API / webhook / MCP-native research or interview pipeline (Userbrain has none)
/sales-userintuition {question}
Running a real behavior demand test (smoke-test page, waitlist, pre-sale) instead of a usability test
/sales-idea-validation or /sales-funnel{question}
Analyzing existing NPS/CSAT/VoC/review feedback (post-launch, not new tests)
/sales-customer-feedback {question}
When routing, give the exact command: "This is a {domain} question — run: /sales-uxtweak {original question}"
Otherwise, answer Userbrain-specific questions using Step 3.
Step 3 — Userbrain platform reference
Read references/platform-guide.md for the full reference — the capability/automation-surface table
(what's exportable vs UI-only), best-effort pricing and plan gates (test-setup and own-tester limits, the
per-session panel price), the Test → Task → Tester → Recording data model, the panel-vs-own-testers
recruiting split, how to write tasks that get real critique, and the no-API data-out playbook. Userbrain
has no public API, so there is no API-reference file.
Answer using only the relevant section — don't dump the full reference.
Step 4 — Actionable guidance
You no longer need the platform guide — focus on the user's specific situation.
Say the caveat: a smooth usability session is not demand. Whatever the user asks, make explicit that
Userbrain shows whether a built design works and why testers struggle — it does not prove
strangers will pay. If they're still deciding whether to build, keep the usability findings but take
the go/no-go from a real behavior test (smoke test, pre-sale) via /sales-idea-validation.
Flag it as UI-only whenever automation or export comes up. Userbrain has no public API, webhooks,
Zapier, or MCP (verify against current docs — it may change). "Sync results to HubSpot/Snowflake/Slack"
is a manual export — download the video/MP4, cut a clip, copy the transcript, or share
the PDF/auto report — not a REST pipeline. If the user needs a programmatic pipeline, tell them so
and route to /sales-userintuition.
When feedback is surface-level, fix the tasks, not the panel. The #1 complaint is testers who "read
the page" or say "it's easy to use." Tell the user to write scenario-based tasks with a goal and no
hints (e.g. "You want to return an item you bought last week — do it"), add open follow-up questions
("what did you expect to happen?", "what was confusing?"), avoid leading/yes-no wording, and screen
with a qualifying question. Note Userbrain refunds/replaces low-quality or broken recordings — tell
them to flag bad sessions to support rather than eat the cost.
Set the tester count realistically. For qualitative think-aloud usability, ~5 testers per user group surfaces most major issues; more testers mostly repeat the same findings. Say the number is a rule-of-thumb, not a guarantee, and suggest continuous small recurring tests over one big batch.
Present all pricing as best-effort and separate the two costs. There are two things to pay for:
the subscription (test setups + own-tester slots + seats) and panel testers billed per session
(best-effort ~$45 each). Say inviting your own users via the share link is free of the per-session
fee, and point to userbrain.com/pricing to confirm current numbers.
Flag the device and targeting ceilings. Userbrain supports desktop, mobile web, and app testing, but
Android app coverage has historically lagged the iPhone app (verify at userbrain.com before promising
it), and panel screening is coarser than enterprise tools — no fine income/location/employment/student
targeting. If precise mobile or niche demographics matter, recommend inviting your own users via the
share link instead of the panel.
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, the per-session panel price, plan limits, mobile/Android
support, and the (absent) API/export surface move; verify at userbrain.com.
Usability ≠ demand. Userbrain proves a design works and shows why it confuses testers, not that
anyone will buy — the go/no-go on building still belongs to a real behavior test (smoke test, pre-sale).
Route that to /sales-idea-validation.
No API, no webhooks, no Zapier, no MCP. Userbrain is UI-only; data-out is manual — video/MP4
download, clips, transcript copy, or the PDF/auto report. Don't design a live REST pipeline around it —
route pipeline needs to /sales-userintuition.
No IA tests. Userbrain is task-based think-aloud video only — no card sorting, tree testing,
first-click, five-second, or preference tests. If the user needs the IA/mixed-methods battery, that's
UXtweak/Maze/Lyssna — route to /sales-uxtweak.
Surface-level feedback is a task-design problem. Testers who narrate the screen or say "easy to use"
usually got vague or leading tasks — fix with goal-based scenarios + open follow-ups, not by blaming the
panel. Flag genuinely bad/broken sessions to support for a refund/replacement.
Two costs, easy to confuse. The subscription covers test setups + own-tester slots + seats;
panel testers are billed per session (~$45, best-effort) on top, including on Free. Inviting your own
users via the share link avoids the per-session fee.
Coarse demographic targeting. No fine income/location/employment/student screening — for precise
audiences, recruit your own users rather than the panel.
Mobile/Android caveat. App testing has historically favored iPhone; verify current Android app
support before promising it.
Free plan is tight. Best-effort ~3 test setups/month, ~5 own testers/month, 1 seat — enough for a
spot check, not a continuous program (that's Pro).
Related skills
/sales-uxtweak — The self-serve usability + information-architecture peer that adds what Userbrain lacks — card sorting, tree testing, first-click / five-second / preference tests — in one seat; route here when the job is IA or mixed-methods, not think-aloud video. Install: npx skills add sales-skills/sales --skill sales-uxtweak -a claude-code
/sales-useberry — The prototype-first usability peer that adds the metrics/IA battery Userbrain omits — card sort, tree test, first-click / five-second / preference, plus deep Figma/Sketch/ProtoPie prototype-flow testing (recruits via Prolific, not video-narration-first); route here for task metrics rather than think-aloud video. Install: npx skills add sales-skills/sales --skill sales-useberry -a claude-code
/sales-idea-validation — The tool-agnostic validate-before-building method + the full research/usability/validator tool landscape (use this to actually decide build-or-not; a passing usability test is not demand). Install: npx skills add sales-skills/sales --skill sales-idea-validation -a claude-code
/sales-userintuition — The API/webhook/MCP-native real-human interview peer — the pick when you need a programmatic research pipeline Userbrain can't offer. Install: npx skills add sales-skills/sales --skill sales-userintuition -a claude-code
/sales-customer-feedback — Real-customer NPS/CSAT/VoC strategy across tools (use to analyze existing feedback; Userbrain proactively runs new usability tests). Install: npx skills add sales-skills/sales --skill sales-customer-feedback -a claude-code
/sales-funnel — Build the smoke-test / fake-door landing page that turns a design hypothesis into a real demand test. Install: npx skills add sales-skills/sales --skill sales-funnel -a claude-code
/sales-userfeel — The international usability peer — the same think-aloud job plus the IA battery Userbrain omits, across 40+ languages / 40+ countries; route here when testers must be in a market you don't speak (note its pricing moved to annual credit plans, and its headline panel is largely User Interviews'). Install: npx skills add sales-skills/sales --skill sales-userfeel -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: "My testers just read the screen and say it's easy — I get no real insight"
User says: "I ran a Userbrain test and the testers basically narrated the page and said 'looks easy to use.' Useless. What am I doing wrong?"
Skill does: Explains this is almost always a task-design problem, not a bad panel. Rewrites the tasks
as goal-based scenarios with no hints (e.g. "You want to cancel your subscription — do it") and adds
open follow-ups ("what did you expect?", "what was confusing here?"), warns against leading/yes-no
wording, and suggests a screening question to qualify testers. Notes Userbrain will refund/replace
genuinely broken or low-effort recordings if flagged to support, and that ~5 testers per group is enough.
Adds the caveat that even a clean session proves the design works, not that anyone will pay.
Result: The user rewrites tasks, re-runs, and gets substantive think-aloud critique.
Example 2: "How do I get every completed Userbrain test into our data warehouse / Slack automatically?" (developer/automation)
User says: "I want each finished usability test's transcript and highlights to flow into Snowflake and post a summary to Slack."
Skill does: States plainly that Userbrain is UI-only — no public API, webhooks, Zapier, or MCP — so
there's no automated REST path. The data-out options are manual: download the video/MP4, cut and
share clips, copy the transcript, or export the PDF/auto report; a warehouse leg means exporting
transcripts and running your own ETL over the files. If a live programmatic pipeline is a hard requirement,
routes to /sales-userintuition (REST API + HMAC webhooks + MCP), noting the trade-off (that's AI-moderated
interviews, not Userbrain's think-aloud usability tests).
Result: The user stops hunting for an API that doesn't exist and sets up a manual export routine.
Example 3: "Is the free plan enough, and how much do testers actually cost?"
User says: "I'm a solo founder. Can I run a real usability test on the Userbrain free plan, and what do the testers cost?"
Skill does: Separates the two costs as best-effort: the subscription (Free ≈ 3 test setups/mo,
5 own-testers/mo, 1 seat; Pro ≈ $49/mo with unlimited setups + 100 own testers) and panel testers billed
per session (~$45 each) on top, including on Free. Explains the cheap path for a solo founder is inviting
your own users via the share link (no per-session fee) for a small think-aloud round, keeping the
panel for when they need strangers. Points to userbrain.com/pricing to confirm, flags every figure as
best-effort, and suggests ~5 testers.
Result: The founder runs a small self-recruited test on Free without surprise per-session charges.
Troubleshooting
"The tester feedback is shallow — they don't critique anything"
Symptom: Testers narrate the page or say "it's easy," with no actionable insight.
Cause: Tasks are too vague, leading, or hint at the answer, so testers have nothing real to do.
Solution: Write scenario-based tasks with a concrete goal and no hints ("You want to return an item
you bought last week — do it"), add open-ended follow-up questions ("what did you expect to happen?",
"what was confusing?"), avoid yes/no and leading wording, and add a screening question to qualify
testers. For genuinely low-effort or broken recordings, flag them to support for a refund/replacement.
Run ~5 testers per group; if a whole batch is weak, the tasks — not the panel — are usually the cause.
"Why is my bill more than my subscription price?"
Symptom: The subscription is one number but the invoice is higher.
Cause: Userbrain has two costs — the subscription (test setups + own-tester slots + seats) and
panel testers billed per session (best-effort ~$45 each), charged on top, including on the Free plan.
Solution: Budget the per-session panel cost separately (testers × ~$45). To avoid the per-session fee
entirely, invite your own users via the share link — those don't incur the panel charge. Confirm
current subscription tiers and the per-session price at userbrain.com/pricing (treat figures as best-effort).
"Can I test my Android app / target a specific niche audience?"
Symptom: The user needs mobile app testing on Android or precise demographic targeting and isn't sure Userbrain supports it.
Cause: Userbrain's app testing has historically favored iPhone, and its panel screening is coarser
than enterprise tools (no fine income/location/employment/student targeting).
Solution: Verify current Android app support at userbrain.com before relying on it — mobile web is
broadly supported, native-app coverage less so. For precise audiences, invite your own users via the
share link (you control who tests) rather than filtering the panel; if enterprise-grade targeting or the
largest mobile panel is essential, compare with UserTesting via /sales-idea-validation.
