Optimal Workshop (optimalworkshop.com) platform help — the category-defining information-architecture research suite: OptimalSort (card sorting), Treejack (tree testing), Chalkmark (first-click), Reframer (qualitative interviews/notes), Questions (surveys), plus prototype and live-site usability testing, AI qualitative analysis, and a large own participant panel. UI-only — no public API, webhooks, Zapier, or MCP; data leaves via CSV/spreadsheet export or Figma import. Use when running a card sort to design site categories, a tree test to fix navigation findability, a first-click test on a screen, recruiting participants or budgeting panel recruitment credits, choosing between the Starter and Enterprise plans, comparing Optimal Workshop with UXtweak/Lyssna/Maze/UserTesting, or exporting study results without an API. Do NOT use for comparing research tools across the market or the validate-before-building method (use /sales-idea-validation), or an API-native interview 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.
Optimal Workshop (optimalworkshop.com) platform help — the category-defining information-architecture research suite: OptimalSort (card sorting), Treejack (tree testing), Chalkmark (first-click), Reframer (qualitative interviews/notes), Questions (surveys), plus prototype and live-site usability testing, AI qualitative analysis, and a large own participant panel. UI-only — no public API, webhooks, Zapier, or MCP; data leaves via CSV/spreadsheet export or Figma import. Use when running a card sort to design site categories, a tree test to fix navigation findability, a first-click test on a screen, recruiting participants or budgeting panel recruitment credits, choosing between the Starter and Enterprise plans, comparing Optimal Workshop with UXtweak/Lyssna/Maze/UserTesting, or exporting study results without an API. Do NOT use for comparing research tools across the market or the validate-before-building method (use /sales-idea-validation), or an API-native interview pipeline (use /sales-userintuition).
argument-hint
[describe what you need help with in Optimal Workshop]
license
MIT
version
1.0.0
tags
["sales","pre-launch","platform"]
github
https://github.com/optimalworkshop
Optimal Workshop Platform Help
Optimal Workshop (optimalworkshop.com) is the category-defining information-architecture (IA)
research suite — the "reference standard" teams reach for when the question is how should content be
organized and can users find it. Its named tools carry the category: OptimalSort (card sorting),
Treejack (tree testing), Chalkmark (first-click), Reframer (qualitative interviews / notes /
tagging / affinity mapping), and Questions (surveys) — plus newer prototype testing (Figma
import), live-site testing, moderated interviews, and AI qualitative analysis. Recruit from its
own panel ("10M+, 150+ countries") or bring your own. Closest self-serve peer: UXtweak
(/sales-uxtweak); other peers Lyssna, Maze, UserTesting.
Two things to say almost every time:
A clean tree test or card sort proves the structure works, not that anyone will pay. IA is
not validated demand — if the user is still deciding whether to build, take that go/no-go to a
real behavior test (smoke test, pre-sale) via /sales-idea-validation.
Optimal Workshop is UI-first — no public API, webhooks, Zapier, or MCP. Any "pipe results into my
CRM/warehouse" ask is manual CSV/spreadsheet export (or Figma import), not REST; an API-native
pipeline is /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 Optimal Workshop?
A) Pick a study type — card sort (OptimalSort) vs tree test (Treejack) vs first-click
(Chalkmark) vs qualitative (Reframer) vs survey (Questions) vs prototype/live-site test
B) Recruit participants — the own panel (pay-per-participant / credit bundles)
vs recruiting your own users via a share link
D) Get data out — export CSV/spreadsheet or import a Figma design (no API — manual only)
E) Choose — Optimal Workshop vs UXtweak / Lyssna / Maze / UserTesting, or Starter vs Enterprise
Are you testing something you've already built/designed, or still deciding whether to build? The
second is an idea-validation question, not an IA question — flag it in Step 2.
Skip-ahead: if the prompt already names the study type and the 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 (Optimal Workshop has none)
/sales-userintuition {question}
Running a real behavior demand test (smoke-test page, waitlist, pre-sale) instead of an IA test
/sales-idea-validation or /sales-funnel{question}
The self-serve all-in-one usability peer (broader battery, own panel, lower entry price)
/sales-uxtweak {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-idea-validation {original question}"
Otherwise, answer Optimal Workshop-specific questions using Step 3.
Step 3 — Optimal Workshop platform reference
Read references/platform-guide.md for the full reference — the tool-by-tool study catalog (what
each measures + how to read its output), the module/automation-surface table (what's exportable vs
UI-only), best-effort pricing and plan gates (Starter study-launch cap, Enterprise, recruitment
credits, panel minimum spend), the Study → Question/Task → Participant → Response data model,
recruiting (own panel vs self-recruit share link), and the no-API data-out playbook. Optimal Workshop
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
Say the caveat: an IA metric is not demand. Make explicit that Optimal Workshop measures whether
a structure/designworks (findability, category agreement, first-click accuracy) — it does
not prove strangers will pay. If they're still deciding whether to build, keep the IA findings
but take the go/no-go from a real behavior test (smoke test, pre-sale) via /sales-idea-validation.
Flag it as UI-first when any automation/export comes up. Optimal Workshop has no public API,
webhooks, Zapier, or MCP (verify — it may change). "Sync results to HubSpot/Snowflake" is a manual
CSV/spreadsheet export or a Figma import, not REST. If they need a programmatic pipeline, say so
and route to /sales-userintuition.
Match the tool to the question. Recommend by job: OptimalSort (card sorting) = how users
group/label content (open = discover, closed = validate → similarity matrix / dendrogram);
Treejack (tree testing) = can users find things in your nav (findability + first-click path, no
visuals → pietree + success/directness); Chalkmark (first-click) = where users click first
(heatmap); Reframer = tag/theme qualitative data; Questions = surveys. Design the tree
with a card sort, then validate it with a tree test — don't run a tree test to judge visuals.
Warn about recruitment cost and the Starter study cap before they hit them. Panel participants are
billed per participant (standard ≈ 1 credit; managed more), so for a handful of testers
self-recruiting via a share link is far cheaper. And Starter caps studies launched per year
(best-effort ~5) even though responses per study are unlimited — a many-study program needs bundles or
Enterprise.
Present all pricing as best-effort — Starter is the entry tier, Enterprise is custom
(SSO/workspaces/admin/CSM); point the user to optimalworkshop.com/pricing.
Set participant counts realistically. Quantitative IA (card sort / tree test) needs ~30+ for a
stable similarity matrix / findability score; qualitative (Reframer) surfaces most themes with a
handful. Say it's a rule-of-thumb, not a guarantee.
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 Starter study-launch cap, recruitment credit
costs, the panel minimum spend, and the (absent) API/export surface move; verify at optimalworkshop.com.
IA success ≠ demand. Optimal Workshop proves a structure/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. Optimal Workshop is UI-first; data-out is manual
CSV/spreadsheet export or Figma import. Don't design a live REST pipeline around it — route
pipeline needs to /sales-userintuition.
The tools have legacy names — don't get lost. OptimalSort = card sorting, Treejack = tree
testing, Chalkmark = first-click, Reframer = qualitative research, Questions = surveys. Users and
docs still say the product names; translate to the method so you recommend the right one.
Starter caps studies launched, not responses. Best-effort ~5 studies/year on Starter with
unlimited responses per study and unlimited seats — the opposite of a per-response cap. Buy
study bundles or go Enterprise for a high-volume program; confirm the current number at pricing.
Card sort vs tree test is the #1 confusion. Card sorting discovers/validates categories &
labels; tree testing validates findability in an existing structure. Run the card sort first to
design the tree, then the tree test to validate it. (Recruitment is billed separately — panel credits
≈ 1/participant — so self-recruit via a share link for small samples; workspaces / SSO / CSM are Enterprise-only.)
Related skills
/sales-uxtweak — The closest self-serve all-in-one peer: the same IA battery (card sorting,
tree testing, first-click) plus five-second/preference, prototype/website tests, session recording,
surveys, and moderated interviews in one seat, with its own 130-country panel — often a
lower-entry-price alternative to Optimal Workshop when you want breadth beyond pure IA. Route here to
compare, or when the job is broader mixed-methods usability. Install: npx skills add sales-skills/sales --skill sales-uxtweak -a claude-code
/sales-lyssna — The ex-UsabilityHub usability + IA twin with a larger 690k+ panel and a
usable free plan (3 seats, unlimited quick studies) plus AI follow-ups/summaries — route here to
compare, or when free-tier generosity / panel size matters. Install: npx skills add sales-skills/sales --skill sales-lyssna -a claude-code
/sales-useberry — The prototype-first usability peer (deep Figma/Sketch/ProtoPie import); route here when prototype-flow depth matters more than deep IA (no panel of its own — recruits via Prolific). Install: npx skills add sales-skills/sales --skill sales-useberry -a claude-code
/sales-validatethat — The budget, MCP-native IA/usability micro-tool: the same card-sort/tree-test/first-click battery far cheaper (Free tier → ~$19/mo), plus an Idea-Validation Engine and — unlike Optimal Workshop — an MCP server (run studies from Claude/Cursor), on-site embeddable studies, and Prolific recruitment; route here when price or agent-driven workflows matter more than benchmark IA depth (it still has no REST API/webhooks). Install: npx skills add sales-skills/sales --skill sales-validatethat -a claude-code
/sales-idea-validation — The tool-agnostic validate-before-building method + the full research/usability/validator landscape (use this to decide build-or-not; a passing IA 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 Optimal Workshop 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 (analyze existing feedback; Optimal Workshop proactively runs new IA/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 an IA/design 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: "Users can't find things in my site's menu — what should I run?"
User says: "People keep missing our pricing page in the nav. How do I test the menu structure in Optimal Workshop?"
Skill does: Recommends a tree test in Treejack (findability without visual design — success
rate + first-click path), optionally preceded by an open card sort in OptimalSort if the
labels/categories are in question. Explains reading the pietree + success/directness, suggests
~30+ participants for a stable result, and notes self-recruiting via a share link beats paying panel
credits. Adds that a clean tree test proves the nav works, not that the offer sells — take the
build-or-not call to a real behavior test.
Result: The user runs a Treejack tree test with the right participant count and reads the pietree correctly.
Example 2: "How do I get Optimal Workshop 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 Notion page."
Skill does: States plainly that Optimal Workshop is UI-first — no public API, webhooks, Zapier,
or MCP — so there's no automated REST path. Data-out is manual CSV/spreadsheet export (+ Figma
import for designs in); the warehouse leg is an ETL over the exported CSV, and Notion is a manual
paste or a Zapier "Email/Webhook → Notion" glue around the export, not a native trigger. If a live
pipeline is a hard requirement, routes to /sales-userintuition (REST API + HMAC webhooks + MCP),
noting that's interviews, not Optimal Workshop's IA battery.
Result: The user stops hunting for an API that doesn't exist and wires up a scheduled CSV export instead.
Example 3: "Is Starter enough, or do I have to pay to recruit testers?"
User says: "I'm a solo founder. Can I run a real card sort on Starter, and how much are participants?"
Skill does: Lays out Starter as best-effort — an entry plan capping studies launched per year
(~5) with unlimited responses and seats — so one card sort fits easily. Explains recruitment is
billed separately (panel ≈ 1 credit/participant, managed more), so the economical path is
self-recruiting via a share link (no per-participant fee), and points to
optimalworkshop.com/pricing to confirm numbers. Flags every figure as best-effort.
Result: The founder runs a card sort within Starter using self-recruited testers and avoids panel credits.
Troubleshooting
"Which tool do I use — OptimalSort or Treejack?"
Symptom: The user isn't sure whether to test categories/labels or navigation findability (the product names hide the method).
Solution: Use OptimalSort (card sorting) when the question is how users group and name content
(open = create/label to discover a structure; closed = sort into your categories to validate them).
Use Treejack (tree testing) when the structure exists and the question is whether users can find
an item (findability + first-click path, no visual design). Run the card sort to design the tree, then
the tree test to validate it — read the card sort via similarity matrix / dendrogram, the tree
test via pietree + success/directness.
"Why did my study stop letting me launch a new one?"
Symptom: A new study won't go live even though existing studies still collect responses.
Solution: The Starter plan caps studies launched per year (best-effort ~5) while responses
per study are unlimited — it's a study-count limit, not a response cap. Finish/close studies you no
longer need, buy a study bundle, or move to Enterprise (custom volume + workspaces + admin).
Confirm the current number and bundle pricing at optimalworkshop.com/pricing (best-effort).
"How do I automate exports / connect Optimal Workshop to my stack?"
Symptom: The user wants results flowing into a CRM, warehouse, or Slack automatically.
Solution: Optimal Workshop has no public API, webhooks, Zapier, or MCP — it's UI-first. Use
manual CSV/spreadsheet export for handoff/ETL and Figma import for designs in; there's no
native results-out trigger, so glue an export into a scheduled job or a Zapier "Email/Webhook parse →
destination" flow. If an automated programmatic pipeline is required, use an API-native tool instead —
route to /sales-userintuition (REST API + HMAC-signed webhooks + MCP server).
