BB 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-plus-sub-agreement structure, ring-fenced marketplace), the regulatory–commercial balance (what flexes vs what cannot), core drafting (authority, float mechanics, hard-coded regulator caps, liability — all tracking control), execution-blocker triage, and a pre-signature check closing open blockers as conditions precedent. It refuses to invent licence-specific values or draft a representation as true without executed evidence. Use it to structure, draft, negotiate, or review any regulated payments contract.
An end-to-end method for drafting and finalising a complex, multi-pillar regulated fintech agreement — from intake to signature.
As a process B 72/100 · Nearly there — weak spots: inputs and preconditions, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7249 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 72/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 3 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 7249 tokens
- 85Steps. 31 steps, 1 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 23 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1011: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 31 headings
- +3Step-by-step instructions: 31 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.