evm

Read-only EVM client: wallets, tokens, gas across 8 chains.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

93%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a concise, highly actionable command catalog with excellent progressive disclosure offloading implementation to a verified bundle script; only workflow validation is slightly light, appropriate for a read-only skill.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no concept padding; assumes Claude's blockchain knowledge and every section (Quick Reference, Procedure, Pitfalls, Verification) earns its tokens with non-obvious, actionable content.	5 / 5
Actionability	Fully executable, copy-paste-ready commands for all 14 subcommands with real addresses/hashes and flag examples like '--chain bsc --no-prices' and '--blocks 50 --min-usd 100000', covering the common cases.	5 / 5
Workflow Clarity	Clearly organized command catalog with a Setup Check and Verification section providing checkpoints; as a read-only query skill it needs no destructive-operation feedback loops, but validation is relatively light.	4 / 5
Progressive Disclosure	Well-structured overview pointing one level deep to the single bundle file scripts/evm_client.py (verified present), with implementation bulk correctly offloaded to the script and clear section navigation.	5 / 5
	Total	19 / 20 Passed

Description

70%Weight 40%Scale 1-5

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 specific and distinct with good natural keywords, but lacks an explicit 'when to use' trigger clause, which caps its completeness score.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when checking wallet balances, token prices, gas fees, or ENS names on EVM chains.'

Broaden capability coverage in the description to hint at the other commands (ENS, whale detection, contract inspection, tx decoding) rather than only wallets/tokens/gas.

Include a few user-facing synonyms ('balance', 'portfolio', 'Ethereum') to improve trigger-term recall.

Dimension	Reasoning	Score
Specificity	Names the domain and three concrete capability areas ('wallets, tokens, gas') plus an 8-chain scope, but omits other covered actions (ENS, whale detection, contract inspection, tx decoding), leaving minor gaps.	4 / 5
Completeness	Gives a clear 'what' (read-only EVM client) but has no explicit 'Use when...' trigger clause, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Includes natural keywords a user would say ('wallet', 'tokens', 'gas', 'EVM', 'chains') but misses common synonyms like 'balance', 'portfolio', 'Ethereum', or 'blockchain'.	4 / 5
Distinctiveness Conflict Risk	'EVM client across 8 chains' carves a clear niche with minimal overlap risk against non-blockchain skills; triggers are distinct.	5 / 5
	Total	16 / 20 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 — 13 / 16 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/blockchain/evm/SKILL.md
Commit: 6680afb

Reviewed: about 3 hours 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.