analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
55
45%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/analyzing-ethereum-smart-contract-vulnerabilities/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, highly specific description that clearly identifies the domain (Solidity smart contract security), the tools (Slither, Mythril), and the types of vulnerabilities detected. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The technical specificity and natural keyword coverage are excellent.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to audit, scan, or analyze Solidity smart contracts for security vulnerabilities, or mentions Slither, Mythril, or pre-deployment security checks.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'static and symbolic analysis', 'detect reentrancy, integer overflow, access control, and other vulnerability classes', and names specific tools (Slither, Mythril). Very concrete about what it does. | 3 / 3 |
Completeness | The 'what' is very well covered (static/symbolic analysis of Solidity contracts using specific tools to detect specific vulnerability classes). However, there is no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a user would say: 'Solidity', 'smart contracts', 'Slither', 'Mythril', 'reentrancy', 'integer overflow', 'access control', 'vulnerability', 'Ethereum mainnet', 'deployment'. These are all terms a developer working in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: Solidity smart contract security analysis with specific tools (Slither, Mythril) targeting Ethereum. Very unlikely to conflict with other skills given the narrow domain and specific tooling mentioned. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a table of contents with no actual content. It describes what should be done at a very high level but provides zero executable commands (e.g., `slither .` or `myth analyze contract.sol`), no example output, no triage criteria, and no report templates. It fails to leverage the tools it names and would not enable Claude to perform any of the described tasks.
Suggestions
Add actual CLI commands for each step, e.g., `slither . --json report.json`, `myth analyze contracts/Vault.sol --solv 0.8.19 -o json` with key flags explained.
Include a concrete example showing sample Slither/Mythril output and how to interpret and triage specific findings (e.g., a reentrancy detection with SWC-107).
Add validation checkpoints: how to verify solc version matches pragma, how to confirm tool output is complete, and what to do when false positives are detected.
Remove the verbose overview paragraph and generic 'When to Use' section; replace with a concise purpose statement and jump straight into actionable steps.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The overview paragraph explains concepts Claude already knows (smart contract immutability, what Slither and Mythril do at a high level, why security matters). The 'When to Use' section is generic boilerplate. Much of the content is padding that adds no actionable value. | 1 / 3 |
Actionability | No concrete commands, code examples, or executable guidance anywhere. Steps are entirely abstract descriptions ('Run Slither against the contract codebase') with zero actual CLI commands, flags, configuration, or code snippets. This describes rather than instructs. | 1 / 3 |
Workflow Clarity | Steps are listed but contain no actual procedures, no validation checkpoints, no error handling, and no feedback loops. Each step is a single vague sentence with no substeps, no specific commands, and no guidance on what to do when tools produce unexpected results. | 1 / 3 |
Progressive Disclosure | The content has some structural organization with headers and numbered steps, but there are no references to external files for detailed content. The skill is neither a concise overview pointing to details elsewhere nor does it contain the details itself—it's a hollow outline. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- mukul975/Anthropic-Cybersecurity-Skills
- Commit
888bbe4
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.