sales-skills/sales-ideacheck

IdeaCheck Platform Help

IdeaCheck (ideacheck.ai) is an AI startup-idea validation tool. You describe your business idea, spend one credit to run the full analysis pipeline, and get a saved evidence report across seven modules (market opportunity, competitive landscape, target-audience profiling, financial viability/unit economics, risk assessment, industry context, scenario modeling), exportable to PDF, Word, and Excel. Its distinguishing trait in a crowded field is pricing flexibility: the same complete report is sold three ways at once — pay-per-report (Try Once), a credit 5-pack whose credits never expire, and a low monthly Starter subscription — with no feature gating between plans (only quantity and expiry differ). It's a fast structured second opinion and document generator — not a substitute for real demand validation — and it has no public API (UI tool).

Step 1 — Gather context

If references/learnings.md exists, read it first for accumulated platform knowledge.

Ask only what you can't infer:

1. What do you want from IdeaCheck?
   • A) Run an idea through it and interpret the report / a specific module
   • B) Understand the pricing — which of the three models (pay-per-report, never-expire pack, monthly) fits how you'll use it
   • C) Get the report out (PDF / Word / Excel export)
   • D) Automate or export programmatically (API reality)
2. What's the real question — "is this idea worth building?" or "how do I use this tool?" If it's the go/no-go decision, that's /sales-idea-validation (a report is not demand) — route in Step 2.
3. Will you re-validate the same idea multiple times as it pivots? This decides which pricing model is actually cheapest — cover it in Step 4.

Skip-ahead: if the user wants the validate-before-building method or to compare validators across the market, route to /sales-idea-validation immediately.

Step 2 — Route or answer directly

| If the user's question is about… | Route to | |---|---| | The validate-before-building method, or the go/no-go decision itself | /sales-idea-validation {question} | | Comparing IdeaCheck against other validators (Informly, IdeaProof, Validator AI, DimeADozen…) | /sales-idea-validation {question} | | Building the smoke-test / fake-door landing page to test real demand | /sales-funnel {question} | | Growing a pre-launch waitlist / capturing real demand | /sales-audience-growth {question} | | Turning the report's marketing/audience sections into a real content program | /sales-content {question} |

When routing, give the exact command: "This is a {domain} question — run: /sales-idea-validation {original question}"

Otherwise, answer IdeaCheck-specific questions using Step 3.

Step 3 — IdeaCheck platform reference

Read references/platform-guide.md for the full reference — the seven modules and what each produces, the credit system (one credit = one full report), the three co-existing pricing models and which is cheapest for how you'll use it, the PDF/Word/Excel export options, why an AI report reads optimistic, and the no-public-API automation reality.

Answer using only the relevant section — don't dump the full reference.

Step 4 — Actionable guidance

• Treat the report and any score as a directional gut check, not demand. The report is an LLM opinion generated from a short idea description — its market sizing, financials, and competitor set are AI estimates, not measured demand. Tell the user to keep the structured outputs (competitor/positioning, target-audience profiles, risks, unit-economics scaffold) to sharpen the pitch, and take the go/no-go from real behavior — a smoke test or pre-sale — not from the report. Route the real test to /sales-idea-validation.
• Pick the pricing model by your re-run count, not the sticker price. IdeaCheck sells the same report three ways: Try Once (pay-per-report), a 5-pack whose credits never expire, and a monthly Starter (a batch of credits that expire at period end). The trap: a founder re-validates the same idea several times as it pivots, so the "cheapest" single report can cost more across the iteration cycle. Rule of thumb: one idea, one run → Try Once; a few ideas over months with no deadline → the never-expire pack; validating many ideas within one month → the monthly plan (but its unused credits expire). All plans get the identical full report — you're buying quantity and expiry terms, not features. Always flag the exact prices and credit terms as best-effort and tell the user to confirm current pricing on ideacheck.ai — the tiers and expiry rules move.
• Finalize the idea framing before you spend a credit. One credit = one full report, and a thin or vague input produces a thin report — tell the user to sharpen the one-line idea, audience, and problem first so they don't burn a credit (or a re-run) fixing the input.
• Use the module outputs as first drafts, then replace them with tested ones. The target-audience profiles, competitive positioning, and financial scaffold are fast starting drafts — good enough to launch a smoke test with, but the copy/positioning that survive are the ones that convert. Push real ad/landing testing to /sales-content and /sales-funnel; export to Word/Excel to edit the numbers by hand (they're estimates, not projections).
• There's no public API — don't plan an integration around it. If asked to automate, export in bulk, or pipe reports into another system, say plainly there's no documented public API, no webhooks, no Zapier/Make, no MCP. The only way to get data out is to export the report (PDF/Word/Excel) and parse it yourself. The thing actually worth automating is the real signal (landing-page conversions), not the generated report — route that to /sales-idea-validation and /sales-funnel.

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) — IdeaCheck's pricing, credit terms, and module set move; verify at ideacheck.ai.

• The report is an AI opinion, not demand. A polished multi-module report generated from a short description validates nothing on its own — follow it with a real-behavior test (smoke test / pre-sale).
• Three pricing models, one report — buy on re-run count. Pay-per-report, a never-expire 5-pack, and a monthly plan all deliver the identical full report; the monthly plan's unused credits expire at period end while the pack's don't. Match the model to how often you'll re-validate.
• Market-size / financial numbers are AI estimates. Verify TAM, unit economics, and projections against primary sources before quoting them; export to Excel and replace the numbers by hand.
• One credit = one full report, and thin input → thin report. A vague idea description wastes a credit — sharpen the framing first; re-running after a pivot spends another credit.
• No public API, no webhooks, no Zapier/Make/MCP. It's a UI tool; the only export is PDF/Word/Excel you download and parse. You can't script or batch it.
• Niche indie tool, thin independent review presence. Few third-party reviews — weigh marketing claims (module counts, "deep research tier") accordingly and confirm the current feature set live.

Related skills

• /sales-idea-validation — The tool-agnostic validate-before-building method + the full validator landscape (use this to actually decide build-or-not; a report is not demand)
• /sales-informly — Informly platform help (a close per-report sibling — one idea → a large multi-report PDF; contrast IdeaCheck's three co-existing pricing models against Informly's single per-report price)
• /sales-ideaproof — IdeaProof platform help (credit-based 120s validation + a pre-launch asset suite — another credit-metered sibling)
• /sales-funnel — Build the smoke-test / fake-door landing page the real demand test runs on
• /sales-audience-growth — Grow a pre-launch waitlist and capture real demand
• /sales-content — Turn the report's marketing/audience sections into a real content/ad program
• /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: "IdeaCheck gave my idea a solid report — should I build it?"

User says: "IdeaCheck ran all the modules and the report looks good. Is my idea validated?" Skill does: Explains the report is an LLM opinion generated from a short description — its market sizing, financials, and competitor set are AI estimates, not demand. Tells the user to keep the structured parts (competitor/positioning, target-audience profiles, risks) to sharpen the pitch, then route the real go/no-go to /sales-idea-validation — a smoke test or pre-sale where a stranger takes an action — rather than trusting the report. Result: The founder gets real demand signal before building, using IdeaCheck's structure, not its verdict.

Example 2: Which IdeaCheck plan is actually cheapest for me?

User says: "IdeaCheck has a $2.99 single report, a 5-pack, and a monthly plan — which should I get?" Skill does: Explains all three deliver the identical full report — you're buying quantity and expiry, not features. Maps the choice to re-run count: one idea run once → Try Once; a few ideas over months with no deadline → the 5-pack whose credits never expire; validating many ideas inside one month → the monthly Starter (but its unused credits expire at period end). Warns that a founder who re-validates the same idea through several pivots can pay more with "cheap" single reports than one pack, and to confirm current prices on ideacheck.ai. Result: The user picks the model that matches their iteration cycle instead of the lowest sticker price.

Example 3: Can I export or automate IdeaCheck reports? (developer/automation)

User says: "I want to run 30 ideas through IdeaCheck and pull the reports into a database via API." Skill does: States plainly there's no documented public API, no webhooks, no Zapier/Make, no MCP — it's a UI tool whose only export is PDF/Word/Excel, so there's no supported way to batch or export programmatically. Suggests exporting to Excel/Word and parsing locally, or using a tool built for programmatic validation, and notes the thing worth automating is a real demand signal (landing-page conversions), not a generated report — pointing to /sales-idea-validation and /sales-funnel. Result: The user avoids building on a non-existent API and picks a workable path.

Troubleshooting

The report reads glowing / it never really tells me not to build

Symptom: Every module assumes the idea should proceed and the tone is encouraging. Cause: The report is a short-prompt LLM output — it pattern-matches to plausible-sounding encouragement and can invent supporting "facts" (market size, demand). Solution: Stop treating the report as the decision. Keep the structured outputs (competitors, risks, audience profiles, unit-economics scaffold) and run a real demand test — smoke test or pre-sale — via /sales-idea-validation.

I paid for a single report but want to validate more ideas / a pivot

Symptom: Expected ongoing access; a second idea (or a re-run after a pivot) asks for another credit. Cause: One credit = one full report. Try Once buys a single report; re-running spends another. Solution: If you'll re-validate repeatedly, switch model: the 5-pack (credits never expire) for a few ideas over time, or the monthly Starter for many ideas inside one month (its unused credits expire). Finalize each idea's framing before spending a credit. Confirm current prices on ideacheck.ai.

I want an API or a way to export/automate

Symptom: Want to script IdeaCheck or pull reports into another system. Cause: IdeaCheck has no documented public API, webhooks, or iPaaS connectors; it's a web tool that exports PDF/Word/Excel only. Solution: Export the report and parse it locally, or use a tool intended for programmatic use; automate a real demand signal (landing-page analytics) instead. See /sales-idea-validation.