Content
78%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.
A tight, actionable audit playbook: concrete scan patterns, executable Foundry PoC commands, and explicit success criteria with a sensible scan-to-verify sequence. The only real gaps are the undefined provenance of the `solidity_scan_file`/`foundry_reentrancy_test` tools and the absence of an error-recovery loop after test execution.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes domain competence — variant taxonomy, audit checks, and commands appear with no padding or explanation of basics. Minor trimmable content exists (the Known exemplars list and CVSS boilerplate restate history Claude largely knows), so it fits anchor 4 rather than 5's "every token earns its place", and is far above the verbosity of anchor 3. | 4 / 5 |
Actionability | Concrete, executable guidance throughout: `solidity_scan_file` scan targets (".call{value:...}" and `delegatecall`), a parameterized PoC invocation (`foundry_reentrancy_test(target="Vault", function="withdraw", target_path="src/Vault.sol")`), and copy-paste bash (`forge test -vvv --match-contract Test_withdraw`). Minor gaps keep it at 4 rather than 5 — attacker-contract construction is delegated to a tool never defined in the skill, and no fallback is given if the tools are unavailable. | 4 / 5 |
Workflow Clarity | A clear sequence runs scan → per-hit checks (state-write ordering, nonReentrant, checks-effects-interactions) → call-graph trace → PoC → test execution, with the forge test plus success criteria ("attacker contract balance grows by more than its initial deposit") serving as a validation checkpoint. It stops short of anchor 5 because there is no explicit error-recovery loop (what to do when the test fails or no hit validates); the destructive/batch cap does not apply since this is analysis and test generation. | 4 / 5 |
Progressive Disclosure | The body is under 50 lines with no need for external references, and content is well-organized into clear sections (Variants, Audit steps, PoC, Success criteria, CVSS, Known exemplars). Per the simple-skill exception this scores 5; no bundle files exist to verify and no dangling file references appear in the body. | 5 / 5 |
Total | 17 / 20 Passed |