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

—

Does it follow best practices?

Impact

100%

1.56x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

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

Highly actionable with concrete, executable Monad configuration and deploy artifacts, but the body is too long and monolithic — it pads general Solidity knowledge and repeats key rules while keeping multiple separable topics inline with no progressive disclosure.

Suggestions

Trim or move general EVM/Solidity gotchas (ERC-20 approve, CEI, basis points, decimals) to a short reference and keep only Monad-specific deviations inline, reducing repetition of the --legacy/forge-script rule.

Split separable topics into one-level-deep reference files (e.g. DeFi patterns, SpeedRun curriculum, scaffold hooks) and link them from a concise overview so SKILL.md stays a lean entry point.

Add an explicit validate→fix→retry checkpoint after deployment (e.g. confirm contract code on chain and re-run verify on failure) so the irreversible deploy workflow has a feedback loop.

Dimension	Reasoning	Score
Conciseness	The ~560-line body re-explains general EVM/Solidity knowledge Claude already has (ERC-20 approve, CEI reentrancy, basis points, decimals, "contracts cannot execute themselves") and repeats the --legacy/forge-script rule many times, though much Monad-specific content earns its place.	2 / 3
Actionability	Provides fully executable, copy-paste-ready artifacts: complete foundry.toml, forge script deploy commands with --legacy, faucet/verify curl calls, a Solidity deploy script, and scaffold hooks.	3 / 3
Workflow Clarity	Workflows A and B are clearly numbered with a security checklist and DO-NOT guardrails, but the irreversible deployment flows lack explicit validate→fix→retry feedback loops, which caps clarity at 2.	2 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the single monolithic SKILL.md inlines distinct topics (SpeedRun curriculum, DeFi patterns, scaffold hook reference, security checklist) that belong in separate one-level-deep reference files, and no bundle files are provided.	2 / 3
	Total	9 / 12 Passed

Description

92%

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

A strong, specific description with explicit trigger guidance and concrete tool references. Its main weakness is broad fallback triggers ("build", "create", "any blockchain development task") that create overlap risk with generic blockchain skills.

Suggestions

Narrow the generic fallback "any blockchain development task" and drop standalone "build"/"create" triggers, which are too broad and would conflict with general web3 skills; lead with Monad-anchored triggers instead.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete capabilities and tooling — "Foundry-first workflow, Scaffold-Monad, parallel execution EVM, and Monad-specific deployment patterns" — beyond a vague domain label.	3 / 3
Completeness	Explicitly states what ("Monad blockchain development tutor and builder") and when via an explicit "Triggers on ..." clause, answering both clearly.	3 / 3
Trigger Term Quality	Lists natural terms users actually say ("dApp", "smart contract", "Solidity", "DeFi", "web3", "Monad"), giving good coverage with common variations.	3 / 3
Distinctiveness Conflict Risk	Monad-specific terms are distinctive, but the generic triggers "build", "create", and "any blockchain development task" could overlap with general Solidity/web3 skills and fire for non-Monad work.	2 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 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	15 / 16 Passed

Repository: NeverSight/skills_feed
Commit: ff6a653

Reviewed: 5 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.