Lyssna (lyssna.com, formerly UsabilityHub) platform help — a self-serve UX research and usability-testing suite on a 690k+ participant panel: five-second, first-click, preference tests, card sorting, tree testing, prototype (Figma) + live-website tests, surveys, and moderated interviews, plus AI follow-ups and summaries. UI-only — no public API, webhooks, Zapier, or MCP; data leaves via CSV export or native Figma / calendar / Zoom / Teams integrations. Use when setting up a five-second or first-click test, running a card sort or tree test to fix navigation, testing a Figma prototype with real users, fixing junk 'clicked-through' panel responses with better screeners, hitting the free-plan response cap or study limit, recruiting from the panel vs your own users, or choosing between Lyssna and UXtweak / Maze / UserTesting / Optimal Workshop. Do NOT use for the validate-before-building method or comparing research tools (use /sales-idea-validation), or an API-native research pipeline (use /sales-userintuition).
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.
Lyssna (lyssna.com, formerly UsabilityHub) platform help — a self-serve UX research and usability-testing suite on a 690k+ participant panel: five-second, first-click, preference tests, card sorting, tree testing, prototype (Figma) + live-website tests, surveys, and moderated interviews, plus AI follow-ups and summaries. UI-only — no public API, webhooks, Zapier, or MCP; data leaves via CSV export or native Figma / calendar / Zoom / Teams integrations. Use when setting up a five-second or first-click test, running a card sort or tree test to fix navigation, testing a Figma prototype with real users, fixing junk 'clicked-through' panel responses with better screeners, hitting the free-plan response cap or study limit, recruiting from the panel vs your own users, or choosing between Lyssna and UXtweak / Maze / UserTesting / Optimal Workshop. Do NOT use for the validate-before-building method or comparing research tools (use /sales-idea-validation), or an API-native research pipeline (use /sales-userintuition).
argument-hint
[describe what you need help with in Lyssna]
license
MIT
version
1.0.3
tags
["sales","pre-launch","platform"]
Lyssna Platform Help
Lyssna (lyssna.com, formerly UsabilityHub) is a self-serve UX research and usability-testing
suite — the tool you reach for when you have a design, prototype, or live site and want real users
to test it fast. It bundles the whole battery: quick design tests (five-second, first-click,
preference), IA research (card sorting, tree testing), task-based prototype (Figma import) +
live-website testing, surveys, and moderated interviews (scheduling + optional AI follow-ups
and AI summaries) — recruiting from its 690k+ verified panelor your own users via a share link.
Its peers are UXtweak, Maze, UserTesting, Optimal Workshop; its edge is the large panel, a
usable free plan (3 seats, unlimited quick studies), and a quick-study vs in-depth-study split.
Two things to say almost every time: (1) A task-completion metric is not validated demand — a
high success rate / clean tree test / strong preference tells you the design works, not that strangers
will buy; if they're still deciding whether to build, route the go/no-go to a real behavior test via /sales-idea-validation. (2) Lyssna is UI-only — no public API, webhooks, Zapier, or MCP, so any
"pipe results into my CRM/warehouse" ask is manual CSV export or a native integration (Figma import;
calendar/Zoom/Teams for interview scheduling), not REST — route real pipelines to /sales-userintuition.
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 Lyssna?
A) Pick a test type — five-second / first-click / preference / card sort / tree test / prototype / website / survey / interview
B) Recruit participants — the 690k+ panel (pay-per-use) vs sharing a link with your own users
C) Fix bad results — junk "clicked-through" / "Yes" responses, weak screeners, US-skewed panel
D) Read results / get data out — click maps, first-click accuracy, card-sort similarity, tree-test findability; CSV export (no API)
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 test type and their question is specific, go to Step 3.
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}
An API / webhook / MCP-native research or interview pipeline (Lyssna 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}
Deep think-aloud video recordings (Lyssna's unmoderated tests aren't video-narration-first)
/sales-userbrain {question}
When routing, give the exact command: "This is a {domain} question — run: /sales-idea-validation {original question}"
Otherwise, answer Lyssna-specific questions using Step 3.
Step 3 — Lyssna platform reference
Read references/platform-guide.md for the full reference — the test-type catalog (what each test
measures + how to read its output), the automation-surface table, best-effort pricing/plan gates (Free
15-response cap, Growth in-depth-study limit, pay-per-use panel), the data model, recruiting (panel vs
share-your-own), and the no-API data-out playbook. Lyssna has no public API — no API-reference file.
Answer using only the relevant section — don't dump the full reference.
Step 4 — Actionable guidance
Say the caveat: a usability metric is not demand. Whatever the user asks, make explicit that
Lyssna measures whether a built design/flow works (task success, first-click accuracy,
findability, preference) — 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 when any automation/export comes up. Lyssna has no public API, webhooks,
Zapier, or MCP (verify current docs). "Sync results to HubSpot/Snowflake" is a manual CSV export,
or the native Figma (prototype import) and calendar/Zoom/Teams (scheduling) integrations — not
a REST pipeline. If the user needs a programmatic pipeline, tell them so and route to /sales-userintuition.
Fix junk responses with task/screener design first, not by blaming the panel. The top complaint is
fast "clicked-through" answers and "Yes" to open-ended questions. Almost always a design fix: write
goal-based task scenarios with no hints (not opinion questions), add screener + attention/qualifying
questions, and prefer specific closed + one open follow-up over vague "share your thoughts." Lyssna
will credit/replace genuinely bad panel responses if you flag them to support. Also warn the panel
skews US-based, so for non-US/niche audiences tighten screeners or self-recruit via a share link.
Match the test type to the question (full catalog in references/platform-guide.md): five-second
= first impression/recall; first-click = where users click first (predicts task success);
preference = A/B of designs; card sorting = how users group/label content; tree testing =
findability in your nav (no visual design); prototype/website test = task success/time. Don't run a
five-second test for navigation or a tree test to judge visuals.
Warn about the plan limits before they hit them, as best-effort. The Free plan gives 3 seats
and unlimited quick studies but only ~15 self-recruited responses and lacks recordings, AI
follow-ups/summaries, CSV export, conditional logic, and live-website testing. Growth adds those
and 5 in-depth studies/month with unlimited self-recruited responses. Panel participants are
billed pay-per-use on every plan (separate from the subscription — the two costs are easy to
confuse). State all figures as best-effort and point to lyssna.com/pricing.
Set participant counts realistically (rule-of-thumb): ~5 per user group for qualitative usability (task tests, interviews); ~30+ for quantitative tests (first-click, card sort, tree test, preference).
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 Free response cap, the quick-vs-in-depth split, the pay-per-use panel, and the (absent) API/export surface move; verify at lyssna.com.
Usability ≠ demand. Lyssna proves a design works, 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. Lyssna is UI-only; data-out is manual CSV export or
native integrations (Figma prototype import; calendar / Google Meet / Zoom / Teams for
interview scheduling only — not data export). Don't design a live REST pipeline around it — route
pipeline needs to /sales-userintuition.
Panel quality: fast "clicked-through" and "Yes"-to-everything responses. The #1 gripe — almost
always a task/screener-design problem, not a broken panel: fix with goal-based tasks, screeners,
attention checks, and specific (not "share your thoughts") questions; flag genuinely bad responses to
support for credit/replacement. The panel also skews US-based, so tighten screeners or
self-recruit via a share link for niche/non-US audiences.
Two separate costs, and a capped free plan. The subscription (Free / Growth / Enterprise) and
panel participants (pay-per-use on every plan) are billed separately (self-recruiting via a
share link avoids the panel fee). Free caps ~15 self-recruited responses and gates recordings, AI
follow-ups/summaries, CSV export, conditional logic, and live-website testing — all start on Growth.
"Quick" vs "in-depth" studies drive the limits. Quick studies (five-second/first-click/preference/
card sort/etc.) are unlimited on paid plans; interviews and other in-depth studies are metered
(5/mo on Growth). Plan around that split.
Figma prototype import can be slow or flaky. Large prototypes sometimes stall or fail to import
(reviewers blame the Figma API) — simplify the flow and re-import.
Related skills
/sales-uxtweak — The closest usability + information-architecture peer — the same battery (card sort, tree test, first-click / five-second / preference, prototype/website tests) in one seat, with its own panel; route here to compare the two or when the UI-heavy IA depth (similarity matrix / dendrogram / pietree) matters. Install: npx skills add sales-skills/sales --skill sales-uxtweak -a claude-code
/sales-userbrain — The video-first think-aloud usability peer — real testers narrate screen + voice while doing your tasks (AI highlights, transcripts, clips); route here when you want to watch people use it and hear why, not Lyssna's quick-test metrics. Install: npx skills add sales-skills/sales --skill sales-userbrain -a claude-code
/sales-useberry — The prototype-first usability peer (design-led, deep Figma/Sketch/ProtoPie import like Maze) — route here to compare, or when the user wants that prototype-flow depth; note Useberry has no panel of its own (recruits via Prolific) where Lyssna brings a 690k+ panel. Install: npx skills add sales-skills/sales --skill sales-useberry -a claude-code
/sales-uxarmy — The APAC-first usability + IA peer (same battery, plus DeepDive moderated dyads/triads/focus groups) — route here when the study targets Asia-Pacific users, where its 20+ country panel beats Lyssna's larger but US/Europe-weighted one; its per-response, per-method credit model also prices card sorts and tree tests at a fraction of a credit. Install: npx skills add sales-skills/sales --skill sales-uxarmy -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 Lyssna 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; Lyssna proactively runs new 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 peer running the same battery (unmoderated + moderated, card sort, tree test, surveys) across 40+ languages / 40+ countries; route here when the market matters more than the free tier — but note Userfeel now sells annual credit plans (~$2,250/yr) rather than the pay-per-test model its reviews still describe. 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 answer 'Yes' and click through — the feedback is useless"
User says: "I ran a Lyssna test asking people to review my landing page and share thoughts, and half
just said 'Yes' or wrote one word. What am I doing wrong?"
Skill does: Explains this is almost always a task/question-design problem, not a bad panel.
Rewrites the ask as goal-based task scenarios with no hints (e.g. "You want to find the pricing — do
it") plus specific questions and one open follow-up, warns against vague "share your thoughts"
and yes/no wording, and adds a screener + attention check. Notes Lyssna will credit/replace
genuinely low-effort panel responses if flagged, that the panel skews US-based (tighten screeners or
self-recruit), and that even clean feedback proves the design works, not that anyone will pay.
Result: The user rewrites the study, re-runs, and gets substantive, usable feedback.
Example 2: "How do I get Lyssna results into Notion / my warehouse automatically?" (developer/automation)
User says: "I want every completed study's results to flow into our data warehouse and a dashboard."
Skill does: States plainly that Lyssna is UI-only — no public API, webhooks, Zapier, or MCP — so
there's no automated REST path. Data-out is manual CSV export (Growth+); the native integrations are
Figma (prototype import, inbound) and calendar/Zoom/Teams (interview scheduling, not data
export) — none move result data into a warehouse. If a live pipeline is a hard requirement, routes to
/sales-userintuition (REST API + HMAC webhooks + MCP), noting that's real-human interviews, not
Lyssna's quick-test battery.
Result: The user stops hunting for an API that doesn't exist and sets up a scheduled CSV export/ETL.
Example 3: "Is the free plan enough, or do I have to pay to recruit testers?"
User says: "I'm a solo founder. Can I run a real first-click test on the free plan, and how much are
participants?"
Skill does: Lays out the Free plan (best-effort) — 3 seats, unlimited quick studies, but only
~15 self-recruited responses and no recordings / AI follow-ups / CSV export. Explains the two
separate costs (subscriptionand the panel, pay-per-use on every plan), so the cheapest path is
a first-click test self-recruited via a share link (no panel fee) within the 15-response cap,
upgrading to Growth only for more volume, recordings, or the 5 monthly in-depth studies. Points to
lyssna.com/pricing; flags every figure as best-effort.
Result: The founder runs a first-click test on the free plan with self-recruited testers.
Troubleshooting
"The responses are junk — people just click through as fast as possible"
Symptom: Open-ended answers are one word or "Yes"; feedback is superficial or irrelevant.
Cause: A task/question-design problem (vague or opinion-only prompts invite low-effort answers),
compounded by unqualified panel participants — not usually a broken panel.
Solution: Rewrite as goal-based task scenarios (specific action, no hints), add screener
questions + an attention check, ask specific questions with one open follow-up rather than
"share your thoughts," and keep studies short. Flag genuinely low-effort panel responses to support for
credit/replacement; for non-US or niche audiences tighten screeners or self-recruit via a share link
(the panel skews US-based).
"The free plan won't let me collect more responses / use recordings or export"
Symptom: Responses stop recording around ~15, or recordings / AI summaries / CSV export are locked.
Cause: The Free plan caps self-recruited responses (best-effort ~15) and gates recordings, AI
follow-ups/summaries, CSV export, conditional logic, custom branding, and live-website testing.
Solution: Self-recruit via a share link to stretch the free responses, export/screenshot results
before you need volume, and upgrade to Growth for recordings, AI features, CSV export, live-website
testing, and 5 in-depth studies/month (interviews and other in-depth studies are metered even on
Growth). Confirm current caps and price at lyssna.com/pricing — treat all figures as best-effort.
"How do I automate exports / connect Lyssna to my stack?"
Symptom: The user wants results flowing into a CRM, warehouse, or Slack automatically.
Cause: Lyssna has no public API, webhooks, Zapier, or MCP — it's UI-only (verify current docs).
Solution: Use manual CSV export (Growth+) for ad-hoc handoff or a scheduled ETL over the exported
file. The native integrations — Figma (prototype import) and Google Calendar / Outlook / Google
Meet / Zoom / Teams (interview scheduling only) — don't move result data out. If an automated,
programmatic pipeline is a requirement, use an API-native research tool instead — route to
/sales-userintuition (REST API + HMAC-signed webhooks + MCP server).
