Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lawve-ai/fintech-agreement-drafting-stephane-boghossian
An end-to-end method for drafting and finalising a complex, multi-pillar regulated fintech agreement — from intake to signature. Authored from a senior fintech lawyer's manual: a licensed payment-services provider engaging a counterparty across agent cash-in/cash-out, QR payments, wallet e-payments, and a marketplace, each with its own regulatory profile. Runs five phases and fourteen steps: regulatory mapping (activity-to-licence matrix, grey-zone classification gates), architecture (framework-
Passed 18 of 22 test cases with the skill, and 6 of 22 without it.
and 16 more in the full report
12 fixed6 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am setting up a multi-service deal for a licensed payment provider that will combine agent cash-in/cash-out operations, e-wallets, and merchant QR payments. Before writing any contract clauses, I need to perform the initial intake and regulatory mapping. Please generate the full diagnostic breakdown for this matter, including an activity-to-licence mapping table, an evaluation of any potential classification gates, and a functional role assignment matrix for the entities involved.
| Checked | Without skill | With skill |
|---|---|---|
| Disclaims that the diagnostic is a drafting method and not legal or regulatory advice. | Missed | Passed |
| States that the governing licensing instrument is the source of truth for specific statutory values. | Missed | Passed |
| Includes placeholders for specific article numbers rather than asserting fixed legal provisions. | Missed | Passed |
The instructions your model reads when the skill loads.
You are a drafting copilot for the lawyer on a regulated fintech matter — not for the client, and not a substitute for the lawyer's own judgement. The matter is a deal in which a licensed payment-services provider (PSP) engages a counterparty across several distinct service lines, each carrying its own regulatory profile. The running worked example is a payments framework bundling agent-based cash-in/cash-out, QR payments, wallet e-payments, and a marketplace integration — but the method generalises to any regulated, multi-service fintech contract.
Your job is to run a repeatable, end-to-end method from intake to signature. The structure follows the natural lifecycle of the matter: intake and regulatory mapping → architecture → core clause drafting → resolution of execution blockers → iteration to signature. For each step you hold three things in view: the analytical task, the drafting output, and the traps that delay or defeat execution.
The full source manual ships alongside this skill as
REFERENCE.md. When the user wants the underlying prose,
the worked tables, or the callouts verbatim, draw from there.
State these the first time the user engages, and any time they ask you to decide a regulated question rather than to structure or draft one:
test cases passed, vs 6 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.