defi

DeFi protocol interactions. Swap tokens via DEX aggregators, check yields, track positions across Ethereum, Polygon, Arbitrum, and Solana.

Quality

66%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./public/skills/0xterrybit/defi/SKILL.md

Quality

Discovery

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong in specificity and distinctiveness, clearly naming concrete DeFi actions and supported blockchains. Its main weaknesses are the absence of an explicit 'Use when...' clause and incomplete coverage of natural trigger terms users might employ (e.g., 'liquidity', 'farming', 'staking').

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about swapping tokens, checking DeFi yields, or tracking on-chain positions.'

Expand trigger terms to include common user phrases like 'liquidity pools', 'farming', 'staking', 'AMM', 'token price', and 'DeFi portfolio'.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Swap tokens via DEX aggregators, check yields, track positions' across named chains (Ethereum, Polygon, Arbitrum, Solana).	3 / 3
Completeness	Clearly answers 'what does this do' with specific actions and chains, but lacks an explicit 'Use when...' clause or equivalent trigger guidance, capping this at 2 per the rubric.	2 / 3
Trigger Term Quality	Includes good domain terms like 'DeFi', 'swap tokens', 'DEX aggregators', 'yields', and specific chain names, but misses common user variations like 'liquidity pools', 'AMM', 'farming', 'staking', 'token price', or 'portfolio'.	2 / 3
Distinctiveness Conflict Risk	The combination of DeFi-specific actions (swap, yields, positions) with named chains and DEX aggregators creates a clear niche that is unlikely to conflict with other skills.	3 / 3
	Total	10 / 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 is a solid, highly actionable DeFi skill with real, executable curl commands covering multiple chains and protocols. Its main weaknesses are the monolithic structure that could benefit from splitting detailed references into separate files, and the lack of explicit validation/confirmation workflows inline with the swap and bridge operations despite dealing with irreversible financial transactions. The referral fee configuration is transparently documented, which is good practice.

Suggestions

Add explicit inline validation steps to swap/bridge workflows: check token allowance → get quote → display details → wait for user confirmation → return tx data, with error recovery loops

Split detailed content (chain reference tables, error handling, token address lists) into separate bundle files and reference them from the main SKILL.md to improve progressive disclosure

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient with concrete commands and tables, but includes some unnecessary content like the 'Supported Chains' and 'Free APIs' tables that partially duplicate information already shown in the commands, and the 'Example Interactions' section restates what the commands already demonstrate. The referral configuration table is domain-specific knowledge that earns its place.	2 / 3
Actionability	Excellent actionability with fully executable curl commands, specific token addresses, chain IDs, and jq filters that are copy-paste ready. Every major operation (price checks, yield queries, swaps, bridges, balance checks) has concrete, runnable examples with real API endpoints and parameters.	3 / 3
Workflow Clarity	The 'Example Interactions' section shows a clear sequence (quote → display → confirm → execute) and the Safety Rules establish important constraints, but the actual swap/bridge command sections only show the quote step without explicit validation checkpoints or feedback loops for error recovery. For financial operations involving real funds, the lack of inline validation steps (e.g., verify token contract, check allowance, confirm quote before proceeding) caps this at 2.	2 / 3
Progressive Disclosure	The content is well-organized with clear section headers and tables, but it's a long monolithic file (~180 lines of content) with no bundle files to offload detailed reference material. The chain reference tables, error handling, and detailed API examples for each chain could be split into separate files for better progressive disclosure.	2 / 3
	Total	9 / 12 Passed

Validation

81%

Warnings & errors only

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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	9 / 11 Passed

Repository: Demerzels-lab/elsamultiskillagent
Commit: f45fcb5

Reviewed: 23 days ago

Table of Contents

Discovery Implementation Validation

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.