user-test-splitsquad
Skill0 starsChanged 3 months agoNo licenceView on GitHub
SplitSquad-specialized user testing for a shared-expense app. A six-person group panel — the trip organizer, the cent-counting roommate, the international traveler, the group treasurer who actually chases the money, the stranger who arrives through an invite link with no account, and the housemate running recurring bills and subscriptions — plus a rotating bench of ten domain experts (bookkeeper/CPA, payments-ops, Splitwise power user, FX/treasury, receipt-OCR skeptic, offline/localStorage durability, privacy, accessibility, email deliverability, app-security). Scores TWO things: the product UX, and — unique to this skill — MONEY INTEGRITY: does every screen's number survive being re-derived by hand, does the app create or destroy money in rounding and FX, and would the settle-up plan it produced actually leave the group square? Includes conservation/rounding/FX auditing of `src/utils/balances.ts`, `currency.ts`, and `debtSimplification.ts` against the invariants in `references/domain-accuracy.md`, plus planted-defect calibration that measures what the panel MISSES. Each persona runs as an isolated Agent subprocess. Use when you want "would six friends trust this app with a real trip's money, and would anyone get shortchanged?" — not generic UX.
- Reads credentials
In this repository38 other files it gives its agents.
- aiml-dudeSkill
- back-end-dudeSkill
- be2-code-reviewSkill
- be-code-reviewSkill
- book-to-productSkill
- browseSkill
- bug-finder-dudeSkill
- bug-huntSkill
- checkerSkill
- code-qualitySkill
- contractor-dudeSkill
- cruise-plannerSkill
- debug-dudeSkill
- designer-dudeSkill
- fe-code-reviewSkill
- fleet-huntSkill
- flight-finderSkill
- front-end-dudeSkill
- general-code-reviewSkill
- h1-reportSkill
- helmSkill
- logo-designSkill
- nextjs-code-reviewSkill
- orchestrateSkill
- pick-programSkill
- plan-dudeSkill
- push-dudeSkill
- qa-dudeSkill
- retro-dudeSkill
- round-trip-stocksSkill
- security-dudeSkill
- seo-dudeSkill
- user-test-2Skill
- user-test-massiveSkill
- user-test-miskariSkill
- user-test-sheevookSkill
- user-testSkill
- vuln-researchSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. About 0 are common, 9 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.