Content
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a broad API reference for MEV protection with typed code examples and useful summary tables, but it lacks executable completeness (undefined variables, fictional library) and has no workflow sequencing or validation steps for what are inherently risky financial operations. The content reads more like API documentation than an actionable skill that guides Claude through protecting trades safely.
Suggestions
Add a clear end-to-end workflow (e.g., 1. Simulate risk → 2. Choose protection level → 3. Execute protected trade → 4. Verify inclusion → 5. Analyze result) with explicit validation checkpoints and error recovery steps.
Make code examples truly executable by defining or explaining prerequisite variables (routerAddress, swapCalldata, swapInstructions) and adding error handling for common failure modes like bundle rejection or timeout.
Add explicit error handling guidance: what happens when Flashbots bundles aren't included, when Jito tips are too low, or when MEV Blocker rejects a transaction.
Consider splitting the detailed per-provider API reference into separate files and keeping SKILL.md as a concise overview with the core workflow and quick-start example.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably organized but includes some unnecessary verbosity—console.log examples for every field, redundant comments explaining obvious things, and tables that restate what's already shown in code. The attack types table and best practices are useful but could be tighter. | 2 / 3 |
Actionability | The code examples look concrete and typed, but they reference a fictional 'clodds/mev' library with no installation instructions or verification that it exists. Functions like `calculateMinOut`, `routerAddress`, and `swapCalldata` are used without definition, making the examples not truly copy-paste executable. | 2 / 3 |
Workflow Clarity | There is no clear multi-step workflow for protecting a trade end-to-end. The skill presents isolated API calls without sequencing them into a coherent process. For a task involving financial transactions where errors can be costly, there are no validation checkpoints, error handling, or feedback loops (e.g., what to do if a Flashbots bundle fails or times out). | 1 / 3 |
Progressive Disclosure | The content is structured with clear sections and headers, and the tables provide quick-reference summaries. However, it's a long monolithic document (~180 lines of API reference) with no references to external files for detailed topics like provider setup or advanced configuration. | 2 / 3 |
Total | 7 / 12 Passed |