query-token-audit
Query token security audit to detect scams, honeypots, and malicious contracts before trading. Returns comprehensive security analysis including contract risks, trading risks, and scam detection. Use when users ask "is this token safe?", "check token security", "audit token", or before any swap.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 skill description that clearly communicates its purpose, capabilities, and trigger conditions. It uses third person voice, lists specific actions, includes natural user phrases as trigger terms, and occupies a distinct niche in token security auditing. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'detect scams, honeypots, and malicious contracts', 'returns comprehensive security analysis including contract risks, trading risks, and scam detection'. These are concrete, domain-specific capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Query token security audit to detect scams, honeypots, and malicious contracts; returns comprehensive security analysis') and when ('Use when users ask "is this token safe?", "check token security", "audit token", or before any swap'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'is this token safe?', 'check token security', 'audit token', 'before any swap', 'scams', 'honeypots', 'malicious contracts'. Good coverage of natural language variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on token security auditing in a crypto/DeFi context. The specific triggers around token safety, honeypots, and pre-swap auditing are unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid API reference skill with excellent actionability — complete curl examples, detailed request/response schemas, and clear conditional response handling. The main weakness is mild verbosity in introductory sections (Use Cases, duplicated chain info) that don't add value for Claude. The workflow is well-structured with appropriate validation checkpoints for interpreting audit results.
Suggestions
Remove the 'Use Cases' section — Claude can infer when to use this skill from the description and context.
Consolidate the 'Supported Chains' table into the request parameters section to avoid duplication of chain IDs.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary sections like 'Use Cases' which describes things Claude can infer, and the 'Supported Chains' table is duplicated in the request parameters description. The response fields table and examples are well-structured but could be slightly tighter. | 2 / 3 |
Actionability | Provides a fully executable curl example, complete request/response JSON, detailed parameter tables, specific headers, and clear response handling logic with conditional branching. The guidance is copy-paste ready and leaves no ambiguity about how to make the API call. | 3 / 3 |
Workflow Clarity | The workflow is clear: make the API call, check hasResult/isSupported flags, then branch on risk level. The response handling section provides explicit conditional logic (if hasResult=false → do X, if true → do Y), and the risk level reference table gives clear action guidance. The notes section adds important validation constraints like tax thresholds and the mandatory disclaimer. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and tables, but it's a single monolithic file with no references to external files. For a skill of this length (~130 lines), the inline approach is acceptable but the 'Use Cases' and 'Supported Chains' sections could be trimmed or consolidated to improve structure. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- binance/binance-skills-hub
- Commit
68fcfa1
- 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.