AB nevermined-router
Use when an AI agent needs to PAY an external service it does not have an account with — any x402 agent or MPP merchant — using the Nevermined Router. Covers discovering services in the Agent Services Catalog, creating a spending Delegation from an API key, funding the buyer wallet, making paid calls through /api/v1/router/route (or the streaming /proxy), reading the payment ledger, and the guardrails an autonomous buyer must respect. Complements the nevermined-payments skill, which is about RECEIVING payments and buying Nevermined plans.
Covers discovering services in the Agent Services Catalog, creating a spending Delegation from an API key, funding the buyer wallet, making paid calls through…
As a process B 68/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Secrets in code
secret-high-entropy-tokenreferences/bootstrap.md:120High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"providerPaymentMethodId": "0x8F…70E",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/ledger.md:34High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"merchantAddress": "0x20…87C",
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:121High-entropy token-like string (may be an id, hash or a credential) (placeholder value)# → { "providerPaymentMethodId": "0x8F…70E", ... }placeholder
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "lastUpdated"
Process rating: all ten parameters 68/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 25 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 4942 tokens
- 100Tools and files. No external tools needed
- 100Steps. 8 steps
- 100Failures and branches. 1 branches, has a failure section
- 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 10 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 544: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.