monad-wingman

Monad blockchain development tutor and builder. Triggers on "build", "create", "dApp", "smart contract", "Solidity", "DeFi", "Monad", "web3", "MON", or any blockchain development task. Covers Foundry-first workflow, Scaffold-Monad, parallel execution EVM, and Monad-specific deployment patterns.

1.56x

Quality

79%

Does it follow best practices?

Impact

100%

1.56x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./data/skills-md/0x70626a/monad-wingman/monad-wingman/SKILL.md

Quality

Discovery

82%

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 does well at listing explicit trigger terms and covering both what and when, making it functional for skill selection. However, it lacks concrete action verbs describing specific capabilities (it says what it 'covers' rather than what it 'does'), and several trigger terms are too broad, creating potential conflicts with general blockchain development skills. The Monad-specific elements provide some distinctiveness but the generic web3/Solidity triggers weaken it.

Suggestions

Replace 'Covers Foundry-first workflow...' with specific actions like 'Scaffolds Monad dApps using Scaffold-Monad, deploys smart contracts via Foundry, optimizes for parallel execution EVM'

Narrow broad triggers by qualifying them with 'Monad' context, e.g., 'Triggers when user mentions Monad alongside build, create, dApp, smart contract, or DeFi tasks' to reduce conflict with general blockchain skills

Dimension	Reasoning	Score
Specificity	Names the domain (Monad blockchain development) and mentions some specific tools/concepts like Foundry-first workflow, Scaffold-Monad, parallel execution EVM, and deployment patterns, but doesn't list concrete actions (e.g., 'deploy contracts', 'scaffold projects', 'write Solidity code'). The description is more about coverage areas than specific actions.	2 / 3
Completeness	Clearly answers both 'what' (Monad blockchain development tutor and builder covering Foundry workflow, Scaffold-Monad, parallel execution EVM, deployment patterns) and 'when' (explicit trigger terms listed with 'Triggers on...'). The trigger guidance is explicit and well-defined.	3 / 3
Trigger Term Quality	Explicitly lists natural trigger terms users would say: 'build', 'create', 'dApp', 'smart contract', 'Solidity', 'DeFi', 'Monad', 'web3', 'MON', plus 'blockchain development task'. Good coverage of terms a developer would naturally use.	3 / 3
Distinctiveness Conflict Risk	While 'Monad' is distinctive, many trigger terms like 'build', 'create', 'smart contract', 'Solidity', 'DeFi', 'web3' are very broad and would overlap with any general blockchain/Solidity development skill. Only 'Monad', 'MON', 'Scaffold-Monad', and 'parallel execution EVM' are truly distinctive.	2 / 3
	Total	10 / 12 Passed

Implementation

77%

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

This is a comprehensive and highly actionable Monad development guide with excellent workflow clarity and executable examples throughout. Its main weaknesses are verbosity — it includes substantial general Solidity/EVM knowledge that Claude already possesses (reentrancy, approve patterns, decimal handling) — and a monolithic structure that could benefit from splitting detailed reference material into separate files. The Monad-specific content (chain config, --legacy flag, gas limit billing, prague EVM version) is genuinely valuable and well-presented.

Suggestions

Move general Solidity gotchas (reentrancy, approve pattern, SafeERC20, floating point, vault inflation) to a separate GOTCHAS.md reference file, keeping only Monad-specific gotchas inline

Move the SpeedRun Ethereum challenges table and DeFi protocol patterns to separate reference files (e.g., SPEEDRUN.md, DEFI_PATTERNS.md) with one-line references from the main skill

Remove explanations of concepts Claude already knows (e.g., what ERC-20 approve does, what reentrancy is) and keep only the code patterns and Monad-specific notes

Dimension	Reasoning	Score
Conciseness	The skill is quite long (~400+ lines) and contains some content Claude already knows well (ERC-20 approve pattern, reentrancy attacks, no floating point in Solidity, SafeERC20 usage). The Monad-specific content is valuable and earns its place, but general Solidity gotchas and DeFi patterns inflate the token budget significantly. The SpeedRun Ethereum table and DeFi protocol descriptions add bulk without much actionable Monad-specific value.	2 / 3
Actionability	The skill provides fully executable code throughout: complete foundry.toml configs, deployment scripts with exact flags, curl commands for faucet/verification, Solidity contract examples, and TypeScript frontend hooks. Commands are copy-paste ready with correct Monad-specific parameters (chain IDs, RPC URLs, --legacy flag).	3 / 3
Workflow Clarity	Both Workflow A (Foundry) and Workflow B (Scaffold-Monad) are clearly sequenced with numbered steps. The deployment workflow includes explicit verification steps, the security checklist serves as a pre-deployment validation checkpoint, and the 'DO NOT' list provides clear guardrails. The mainnet vs testnet distinction with hardware wallet requirements adds safety validation.	3 / 3
Progressive Disclosure	The content is entirely monolithic — everything is in a single file with no references to external documents for detailed topics like DeFi patterns, security reviews, or SpeedRun challenges. The SpeedRun Ethereum table, DeFi protocol patterns, and general Solidity gotchas could be split into separate reference files to keep the main skill lean. However, the internal organization with clear headers and sections is good.	2 / 3
	Total	10 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (568 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: NeverSight/skills_feed
Commit: f772de4

Reviewed: 1 day 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.