optimizing-defi-yields
Find and compare DeFi yield opportunities across protocols with APY calculations, risk assessment, and optimization recommendations. Use when searching for yield farming opportunities, comparing DeFi protocols, or analyzing APY/APR rates. Trigger with phrases like "find DeFi yields", "compare APY", "best yield farming", "optimize DeFi returns", "stablecoin yields", or "liquidity pool rates".
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 capabilities, provides explicit trigger guidance with natural user phrases, and occupies a distinct niche. It follows the recommended pattern of 'what it does' + 'Use when' + trigger phrases, uses third person voice, and includes domain-specific terms that minimize conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: find and compare yield opportunities, APY calculations, risk assessment, and optimization recommendations. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (find/compare DeFi yield opportunities with APY calculations, risk assessment, optimization) and 'when' (explicit 'Use when' clause plus a 'Trigger with phrases like' section providing concrete examples). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'find DeFi yields', 'compare APY', 'best yield farming', 'optimize DeFi returns', 'stablecoin yields', 'liquidity pool rates', plus domain terms like APY/APR, DeFi protocols. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on DeFi yield farming specifically. The domain-specific terminology (DeFi, APY/APR, yield farming, liquidity pools, stablecoin yields) 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 commands covering a wide range of DeFi yield search scenarios. However, it suffers from moderate verbosity (repeated inline comments, lengthy output examples, some redundant quick examples) and lacks validation/verification steps for a workflow that involves financial data analysis. The progressive disclosure structure is reasonable but undermined by the absence of actual bundle files.
Suggestions
Remove redundant inline comments (e.g., '# 10000000 = 10M limit' appears three times) and trim the Prerequisites section—Claude already understands DeFi concepts.
Add a validation step after querying yields, such as checking data freshness/cache age before making recommendations based on the results.
Move the detailed output examples into a referenced file (e.g., references/output_formats.md) to keep the main skill lean, and consolidate the Quick Examples with the Instructions section to avoid duplication.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary elements: the Prerequisites section explaining DeFi concepts Claude already knows, redundant inline comments like '# 10000000 = 10M limit' repeated multiple times, and the '# 2026 year' comment in the output example. The output examples are quite lengthy and could be trimmed. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready commands with specific flags and arguments for every use case. Each step has concrete bash commands with realistic parameters, covering filtering, risk assessment, comparison, and export workflows. | 3 / 3 |
Workflow Clarity | Steps are clearly listed and sequenced from broad search to specific analysis to export, but there are no validation checkpoints or feedback loops. For a tool that queries live financial data and makes recommendations, there should be verification steps (e.g., checking data freshness, validating output before acting on recommendations). | 2 / 3 |
Progressive Disclosure | References to external files (errors.md, examples.md, settings.yaml) are present and clearly signaled, but no bundle files were provided to support them. The main content also includes a lengthy output section and quick examples that partially duplicate the Instructions section, suggesting content that could be better organized into referenced files. | 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.