Simulate flash loan strategies with profitability calculations and risk assessment across Aave, dYdX, and Balancer. Use when simulating flash loans, analyzing arbitrage profitability, evaluating liquidation opportunities, or comparing flash loan providers. Trigger with phrases like "simulate flash loan", "flash loan arbitrage", "liquidation profit", "compare Aave dYdX", "flash loan strategy", or "DeFi arbitrage simulation".
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 a specific DeFi niche with concrete capabilities, explicit trigger guidance, and natural user-facing keywords. It follows best practices by using third person voice, providing both 'Use when' and 'Trigger with' clauses, and naming specific platforms to reduce ambiguity. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: simulate flash loan strategies, profitability calculations, risk assessment, and names specific platforms (Aave, dYdX, Balancer). These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (simulate flash loan strategies with profitability calculations and risk assessment across specific platforms) and 'when' (explicit 'Use when...' clause plus a 'Trigger with phrases like...' section providing concrete trigger guidance). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'simulate flash loan', 'flash loan arbitrage', 'liquidation profit', 'compare Aave dYdX', 'DeFi arbitrage simulation'. These are terms users would naturally use when seeking this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche targeting flash loan simulation specifically across named DeFi protocols. The combination of flash loans, specific platforms (Aave, dYdX, Balancer), and arbitrage/liquidation focus 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.
The skill provides strong actionability with concrete, executable CLI commands covering multiple flash loan strategies. Its main weaknesses are the lack of validation/feedback loops in the workflow (important for financial simulations) and redundancy between the Instructions and Examples sections. The progressive disclosure structure is reasonable but undermined by missing bundle files and duplicated content.
Suggestions
Add validation checkpoints to the workflow, e.g., 'Verify RPC connectivity before running simulations' and 'Check output for stale price warnings before trusting profitability results'.
Remove the Examples section or replace it with distinct, more advanced examples that aren't duplicates of the Instructions commands.
Include a brief feedback loop for iterating on unprofitable results, e.g., 'If No Profitable Route: adjust amount with --amount, try --compare-providers, or scan alternative pairs'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some redundancy—the Examples section largely duplicates commands already shown in Instructions. The Overview and Prerequisites sections are reasonably tight, but the document could be trimmed by removing the duplicate examples. | 2 / 3 |
Actionability | Provides fully concrete, copy-paste-ready CLI commands for every strategy type (arbitrage, liquidation, triangular, risk analysis, full analysis). Each command includes specific flags, token pairs, and amounts—nothing is left vague. | 3 / 3 |
Workflow Clarity | Steps are clearly listed and sequenced, but there are no validation checkpoints or feedback loops. For financial simulations involving risk assessment and profitability calculations, there's no guidance on verifying results, checking for stale data before proceeding, or iterating on failed simulations beyond the error table. | 2 / 3 |
Progressive Disclosure | References to implementation.md, errors.md, and examples.md are well-signaled and one level deep, which is good. However, no bundle files are provided, so we cannot verify these references exist. The Examples section duplicates Instructions content rather than deferring to the referenced examples.md, suggesting suboptimal content splitting. | 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 | |
3a2d27d
Table of Contents
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.