x402
Search for new services and make paid API requests using the x402 payment protocol. Use when you don't have a clear tool to choose, search the bazaar. You can also use this tool if you or the user want to call an x402 endpoint, discover payment requirements, browse the bazaar, or search for paid services.
62
73%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/x402/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has a clear 'Use when' clause with multiple trigger conditions, which is a strength. However, the catch-all trigger 'when you don't have a clear tool to choose' is problematic as it could cause this skill to be selected inappropriately over many other skills. The specific capabilities could be more concrete, and the trigger terms lean heavily on protocol-specific jargon that users may not naturally use.
Suggestions
Remove or narrow the overly broad fallback trigger 'Use when you don't have a clear tool to choose, search the bazaar' as it creates high conflict risk with other skills.
Add more natural language trigger terms that users might actually say, such as 'pay for an API call', 'find a paid service', 'micropayment', or 'HTTP 402'.
Make the capabilities more concrete by specifying what kinds of services can be discovered or what the bazaar contains (e.g., 'Search a marketplace of paid APIs for data, computation, or AI services').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (x402 payment protocol, paid API requests) and some actions (search, make paid API requests, discover payment requirements, browse the bazaar), but the actions are not very concrete—'search for new services' and 'browse the bazaar' are somewhat vague about what specific outcomes are produced. | 2 / 3 |
Completeness | The description clearly answers both 'what' (search for services, make paid API requests using x402) and 'when' (when you don't have a clear tool, when wanting to call an x402 endpoint, discover payment requirements, browse the bazaar, or search for paid services). The 'Use when' clause is explicit with multiple trigger conditions. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'x402', 'bazaar', 'paid services', 'paid API requests', and 'payment requirements', but these are fairly niche terms. A user might not naturally say 'x402' or 'bazaar' unless they already know the protocol. Missing broader natural language triggers like 'pay for API', 'find a service', or 'monetized endpoint'. | 2 / 3 |
Distinctiveness Conflict Risk | The x402 protocol and 'bazaar' references are distinctive, but the trigger 'Use when you don't have a clear tool to choose' is extremely broad and could conflict with any fallback or general-purpose skill. This catch-all clause significantly increases conflict risk. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with excellent actionability and conciseness—commands are concrete, examples are copy-paste ready, and no tokens are wasted on explanations Claude doesn't need. The main weakness is the workflow section, which outlines the happy path but lacks validation checkpoints for an operation that involves real financial transactions (USDC payments). Adding verification steps after payment and explicit error recovery guidance would strengthen the skill.
Suggestions
Add a validation/verification step after `x402 pay` calls—e.g., checking response status, confirming payment went through, and what to do if the response indicates failure.
Expand the workflow section with a feedback loop: after making a paid request, verify the response, and if it fails, check balance and retry or escalate to the user.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what USDC is, what APIs are, or how HTTP methods work. Every section serves a clear purpose—command syntax, options tables, examples, and error handling. The USDC conversion table is a useful quick reference that earns its place. | 3 / 3 |
Actionability | All commands are fully executable and copy-paste ready with concrete examples. The options tables provide specific flags, defaults, and value formats. The examples section covers common use cases with real command invocations including POST with body data and max payment limits. | 3 / 3 |
Workflow Clarity | The workflow section outlines a clear 3-step sequence (find → inspect → pay), but lacks validation checkpoints. There's no guidance on verifying payment success, checking response status, or handling partial failures. For operations involving real money (USDC payments), a feedback loop (verify payment → check response → retry if needed) would be important. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and logical ordering, but it's somewhat long for a single file (~100 lines of substantive content). The options tables for each command could potentially be in a reference file. However, given no bundle files exist, keeping everything inline is reasonable. The structure is good but not exemplary. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- coinbase/agentic-wallet-skills
- Commit
5cb01b5
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.