Content
39%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a large dump of code examples covering Hardhat and Foundry testing patterns, but lacks a coherent workflow, validation steps, and efficient organization. The content is mostly actionable with real code, but it's far too verbose for a SKILL.md—most code blocks should live in the referenced resource files. The Instructions section is generic and unhelpful, providing no smart-contract-testing-specific guidance.
Suggestions
Move the large code blocks (full config, test suites, CI YAML) into the referenced resource files and keep only minimal illustrative snippets in SKILL.md, reducing it to an overview with clear pointers.
Add a clear sequential workflow: 1) Set up project → 2) Write tests → 3) Run tests → 4) Check coverage (validate ≥90%) → 5) Fix gaps → 6) Re-run → 7) Deploy/verify, with explicit validation checkpoints.
Replace the generic Instructions section ('Apply relevant best practices') with specific, actionable guidance unique to smart contract testing, such as 'Always test reentrancy by calling back into the contract from a malicious receiver' or 'Run fuzzing with at least 1000 iterations'.
Remove the 'Do not use this skill when' section and trim explanatory text that Claude already knows (e.g., what coverage reports look like, what CI/CD is).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is significantly verbose, inlining ~300+ lines of code examples that largely demonstrate patterns Claude already knows (basic Hardhat/Foundry test structure, CI/CD YAML, etherscan verification). The config file, full test suites, and CI workflow could be in referenced files. The 'Do not use this skill when' section adds no value. | 2 / 5 |
Actionability | The code examples are mostly executable and copy-paste ready (Hardhat config, unit tests, Foundry tests, coverage commands, verification). Minor gaps exist—some tests reference undefined variables (addr1 in gas optimization test without destructuring), and the Foundry fork test uses a placeholder URL—but overall the guidance is concrete and specific. | 4 / 5 |
Workflow Clarity | There is no clear sequenced workflow tying the pieces together. The skill presents isolated code blocks for different testing concerns but never defines a step-by-step process (e.g., setup → write tests → run → validate coverage → fix → verify). The Instructions section is extremely vague ('Apply relevant best practices and validate outcomes'). No validation checkpoints or feedback loops are present for what could be destructive deployment/verification operations. | 2 / 5 |
Progressive Disclosure | The skill references a 'resources/implementation-playbook.md' and lists 9 resource files in the Resources section, but no bundle files are provided, making these references unverifiable dead links. Meanwhile, massive amounts of code that should be in those referenced files are inlined, defeating the purpose of progressive disclosure. The structure is flat with no clear hierarchy. | 2 / 5 |
Total | 10 / 20 Passed |