Content
80%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is concise and well-structured with concrete, copy-paste-ready command examples, but it lacks any confirmation or validation step before executing irreversible swaps, which caps its workflow clarity. Token/output details are also thin.
Suggestions
Add a confirmation/validation checkpoint before destructive swaps, e.g. require a quote first and confirm the amount and route with the user before executing.
Document command output format and valid token identifiers so results are interpretable.
Note expected error cases (insufficient liquidity, slippage, invalid token) and how to handle them.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean: one brief context line, a tight command table, and two examples, with every token earning its place and no over-explanation of concepts Claude already knows. | 5 / 5 |
Actionability | Commands are concrete with explicit syntax and copy-paste-ready examples ("/met swap 1 SOL to USDC"), but output format, valid token identifiers, and error handling are not covered, leaving minor gaps. | 4 / 5 |
Workflow Clarity | Although this is a simple skill that might otherwise score higher, swap executes an irreversible on-chain transaction with real funds and the body includes no validation or confirmation checkpoint, which caps workflow clarity at 3 per the destructive-operation rule. | 3 / 5 |
Progressive Disclosure | At well under 50 lines with no need for external references, the clearly organized Commands and Examples sections satisfy the simple-skill exception for progressive disclosure; no bundle files exist to verify. | 5 / 5 |
Total | 17 / 20 Passed |