cypherhq/agent-pay
Auto-provision a virtual Visa card to complete an online purchase. Use when user asks to buy something and needs payment, or explicitly mentions cypher-pay/agent-pay. Handles onboarding (email OTP + KYC — once ever), token generation (once per device), funding, card creation, 3DS, and card lifecycle.
90
90%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates what the skill does (auto-provisions virtual Visa cards with full lifecycle management) and when to use it (when users want to buy something or mention specific payment products). It provides excellent specificity by listing the concrete steps involved (onboarding, KYC, token generation, funding, 3DS) and occupies a very distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: auto-provision a virtual Visa card, onboarding (email OTP + KYC), token generation, funding, card creation, 3DS, and card lifecycle. These are detailed, concrete capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (auto-provision a virtual Visa card, handle onboarding, token generation, funding, card creation, 3DS, card lifecycle) and 'when' (explicit 'Use when user asks to buy something and needs payment, or explicitly mentions cypher-pay/agent-pay'). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'buy something', 'needs payment', 'cypher-pay', 'agent-pay', 'Visa card', 'online purchase'. Covers both natural language ('buy something') and product-specific terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — virtual Visa card provisioning and payment processing is a very specific domain. The mention of cypher-pay/agent-pay, 3DS, KYC, and card lifecycle makes it clearly distinguishable from other skills and unlikely to conflict. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with excellent workflow clarity for a complex multi-path process (onboarding, authentication, two card modes, 3DS handling). The main weakness is length — the operations reference and SDK sections add significant bulk that could be split into referenced files. Security rules and error handling are well-covered with explicit constraints.
Suggestions
Move the 'Operations reference' and 'SDK Reference' sections to separate files (e.g., COMMANDS.md, SDK.md) and link to them from the main skill to reduce token footprint.
Remove the SDK Reference section entirely — the skill explicitly states the agent runs CLI commands and should not show code to users, making SDK documentation unnecessary in this context.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~250 lines) and includes some sections that could be trimmed — the SDK reference section at the end is unnecessary for an agent that runs CLI commands, and some explanations are slightly verbose (e.g., the card mode selection dialogue). However, most content is genuinely needed given the complexity of the multi-path workflow. | 2 / 3 |
Actionability | Every step includes exact CLI commands with real flags and arguments, concrete examples, and clear expected outputs. Commands are copy-paste ready with specific flags like `--tag`, `--limit`, `--reveal`, and `--pretty`. The decision tables and branching logic are explicit and executable. | 3 / 3 |
Workflow Clarity | The multi-step workflows are clearly sequenced with numbered steps, explicit validation checkpoints (e.g., 'agent-pay agent' to verify token, 'wait-for-txn' before cancelling, polling kyc-status), and error recovery paths (stale token deletion, freeze instead of cancel on timeout). The branching logic via the enrolled/kycComplete table is well-structured with clear feedback loops. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and logical flow, but it's a monolithic document that could benefit from splitting the operations reference and SDK reference into separate files. The inline operations reference table (~30 lines of command listings) and SDK section add bulk that could be linked out. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents