Turn live TrustMRR startup observations into a reproducible market, competitor, opportunity, or acquisition decision. Built for SaaS founders and indie developers who want revenue evidence without pretending one opt-in dataset represents the whole market.
Start with a market question. This skill builds a bounded TrustMRR cohort, checks pagination and money units, separates payment-provider-backed observations from marketplace and founder claims, and turns the evidence into a decision memo with a 1-7 day validation test.
It includes a deterministic Python validator for revenue pools, quartiles, medians, concentration, duplicate detection, page-clamp detection, and detail-coverage checks. If the data cannot support a monetary conclusion, the workflow says so instead of guessing.
TrustMRR access is separate. You need your own developer API key and an MCP client that can bind bearer authentication through a secret store or environment variable.
Input
Use $trustmrr-market-research to find a narrow mobile-app opportunity an indie developer could validate in seven days. Keep the research within the standard API limit.
Output
A bounded, explicitly stratified cohort; reproducible revenue statistics; direct and adjacent peers; one narrow opportunity hypothesis; key caveats; and a seven-day test with success and kill thresholds.
Input
Compare my B2B AI support product with relevant TrustMRR startups. Separate direct competitors from broad AI tools and show where my positioning is weak.
Output
A peer classification table with payment-backed metrics kept separate from founder claims, plus positioning gaps, reachable wedges, and evidence confidence.
Bring your own TrustMRR account and API key. TrustMRR plan limits and fees are separate from this skill.
The client must support Streamable HTTP and bind the API key through a secret store or environment variable. Literal keys in configuration are not supported by this workflow.
Used by the included deterministic cohort validator and calculator. No third-party Python packages are required.
No reviews yet.
Input
Screen on-sale SaaS businesses below $100,000. Prioritize simple operations and flag the diligence I still need before making an offer.
Output
A reproducible shortlist that separates asking price, reported margin, returned multiple, revenue, traffic, and founder claims, followed by explicit diligence gaps and no unsupported valuation verdict.
Input
Is there enough observed willingness to pay for a specialist analytics product for Shopify agencies, or should I park the idea?
Output
A pursue, reshape, monitor, park, reject, or insufficient-evidence recommendation with the observed-to-inference chain and the smallest next test.
gorven72
Updated Aug 7, 2026
Automated scan passed. It found 1 finding; highest severity info.
Scanned Jul 12, 2026.
Automated scanning reduces risk but cannot guarantee a package is safe for every environment.
Creator
TTrebuh
