Content
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 strong, actionable security skill that provides concrete vulnerable/safe code pairs for critical AMM vulnerability patterns. Its main strengths are executable examples with real library imports and a comprehensive checklist. The main weaknesses are the lack of a clear audit workflow with validation checkpoints and the somewhat monolithic structure that could benefit from progressive disclosure into separate reference files.
Suggestions
Add a sequenced audit workflow section (e.g., '1. Run slither → 2. Review each entrypoint against checklist → 3. Fuzz critical paths → 4. Verify fixes') with explicit validation checkpoints and error recovery guidance.
Consider splitting detailed code examples for each vulnerability category into a referenced file (e.g., PATTERNS.md) and keeping only the checklist and one representative example in the main SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient throughout. It avoids explaining what AMMs are, what Solidity is, or how ERC-20 tokens work. Every section delivers specific patterns without unnecessary preamble, and the one-line explanations between code blocks add context without bloat. | 3 / 3 |
Actionability | Every vulnerability pattern includes executable Solidity code showing both the vulnerable and hardened versions. The audit tools section provides copy-paste-ready CLI commands. Import paths reference real libraries (OpenZeppelin, Uniswap v3) making the code directly usable. | 3 / 3 |
Workflow Clarity | The skill is structured as a checklist-plus-pattern library rather than a sequential workflow, which is appropriate for its purpose. However, the security checklist at the end lacks explicit validation/verification steps—there's no feedback loop for what to do when a check fails, and the audit tools section is disconnected from the checklist without guidance on sequencing (e.g., run slither first, then fuzz, then manual review). | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and a logical flow from patterns to checklist to tools. However, at ~120 lines with 7 distinct vulnerability categories each containing code examples, some content (like the full oracle manipulation or admin controls examples) could be split into referenced files to keep the main skill leaner. | 2 / 3 |
Total | 10 / 12 Passed |