finding-arbitrage-opportunities
Detect profitable arbitrage opportunities across CEX, DEX, and cross-chain markets in real-time. Use when scanning for price spreads, finding arbitrage paths, comparing exchange prices, or analyzing triangular arbitrage opportunities. Trigger with phrases like "find arbitrage", "scan for arb", "price spread", "exchange arbitrage", "triangular arb", "DEX price difference", or "cross-exchange opportunity".
84
82%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 defines its purpose, provides explicit trigger guidance with both a 'Use when' clause and a 'Trigger with phrases' section, and covers a well-defined niche. The description uses proper third-person voice, lists concrete actions, and includes natural keyword variations that users would actually say. It serves as a near-ideal example of a well-crafted skill description.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: detecting arbitrage opportunities across CEX, DEX, and cross-chain markets, scanning for price spreads, finding arbitrage paths, comparing exchange prices, and analyzing triangular arbitrage opportunities. | 3 / 3 |
Completeness | Clearly answers both 'what' (detect profitable arbitrage opportunities across CEX, DEX, and cross-chain markets in real-time) and 'when' (explicit 'Use when' clause with specific trigger scenarios, plus a 'Trigger with phrases' section). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'find arbitrage', 'scan for arb', 'price spread', 'exchange arbitrage', 'triangular arb', 'DEX price difference', 'cross-exchange opportunity'. These cover both formal and informal variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on crypto arbitrage detection across specific market types (CEX, DEX, cross-chain). The domain-specific terminology like 'triangular arb', 'DEX price difference', and 'cross-exchange opportunity' makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides strong actionability with concrete CLI commands and realistic sample output, making it easy for Claude to execute. However, it suffers from some redundancy between Instructions and Examples sections, and lacks validation/verification steps important for a financial tool where acting on stale or incorrect data could be costly. The progressive disclosure is reasonable but unverifiable without bundle files.
Suggestions
Add a validation step or feedback loop before acting on opportunities (e.g., 'verify spread still exists with --verify flag before recommending execution') — this is critical for a financial tool.
Remove the duplicated commands in the Examples section that already appear in Instructions, or consolidate into a single section to improve conciseness.
Remove the Resources section with external links (CoinGecko, CCXT, Uniswap) — Claude already knows these; move to implementation.md if needed for reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary content like the 'Understanding of arbitrage concepts and trading fees' prerequisite and the Resources section with external links Claude already knows about. The Examples section partially duplicates the Instructions section with repeated commands. | 2 / 3 |
Actionability | Every instruction includes a concrete, copy-paste-ready CLI command with specific flags and arguments. The sample output shows exactly what to expect, and the error handling table provides specific fixes for each error condition. | 3 / 3 |
Workflow Clarity | The instructions present a clear set of independent commands rather than a multi-step workflow, which is appropriate for a scanning tool. However, there are no validation checkpoints — no guidance on verifying that prices are fresh before acting, no feedback loop for confirming an opportunity is still valid before execution, which matters for a financial tool where stale data could lead to losses. | 2 / 3 |
Progressive Disclosure | References `${CLAUDE_SKILL_DIR}/references/implementation.md` for advanced details, which is good one-level-deep disclosure. However, no bundle files are provided to verify the reference exists, and the main file includes substantial inline content (error table, multiple examples, resources) that could be split out for better organization. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3a2d27d
- 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.