web3-audit

Smart contract security audit — 10 DeFi bug classes (accounting desync, access control, incomplete path, off-by-one, oracle, ERC4626, reentrancy, flash loan, signature replay, proxy), pre-dive kill signals (TVL < $500K etc), Foundry PoC template, grep patterns for each class, and real Immunefi paid examples. Use for any Solidity/Rust contract audit or when deciding whether a DeFi target is worth hunting.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/web3-audit/SKILL.md

Quality

Content

65%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.

An information-rich, highly actionable audit reference with concrete code and grep patterns throughout. Its weaknesses are conciseness (re-explains known concepts plus a verbose editorial section) and structure (a monolithic single file with no progressive disclosure or end-to-end sequenced audit workflow).

Suggestions

Move the per-bug-class detail, the grep-pattern catalog, and the Foundry PoC template into separate reference files (e.g. references/bug-classes.md, references/grep-patterns.md, references/foundry-poc.md), keeping SKILL.md as a concise overview that links one level deep.

Trim re-explanations of concepts Claude already knows (reentrancy CEI, basic oracle staleness, the ERC4626 first-depositor attack) down to the non-obvious operational details.

Add an explicit end-to-end audit workflow section (e.g. pre-dive gate -> grep sweep per class -> reproduce suspect finding in Foundry -> validate impact -> file report) with validation checkpoints between phases.

Dimension	Reasoning	Score
Conciseness	The body is dense with genuinely specialized knowledge (exact grep patterns, real paid-example payouts, Immunefi submission rules), but it also re-explains concepts Claude already knows (reentrancy CEI, oracle staleness basics, the ERC4626 first-depositor attack) and the Operator Notes section is verbose and editorial, so it is mostly efficient with some unnecessary explanation that could be trimmed.	3 / 5
Actionability	It provides copy-paste-ready bash grep patterns, vulnerable-plus-correct Solidity pairs for each bug class, and a complete executable Foundry PoC template with specific cheatcode references, fully covering the common audit cases.	5 / 5
Workflow Clarity	The pre-dive section is a clear sequenced decision flow with a go/no-go checkpoint ("go if >= 6/10") and the PoC template includes a verify assertion, but the core audit process is presented as a flat 10-class checklist with grep patterns rather than a sequenced workflow with explicit validation checkpoints between steps.	3 / 5
Progressive Disclosure	The ~600-line document has clear in-file section headers but no bundle files exist and all detail (bug-class write-ups, grep catalogs, PoC template, operator notes) is inlined in SKILL.md rather than split into one-level-deep reference materials, so it is structured internally but does not function as an overview pointing to detailed files.	3 / 5
	Total	14 / 20 Passed

Description

88%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.

A strong, highly specific description that clearly conveys both capabilities and trigger conditions in third-person imperative voice. Minor gaps in trigger-term synonyms and some breadth-related overlap risk keep it just below a perfect score.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete capabilities — "10 DeFi bug classes (accounting desync, access control, ...)", "pre-dive kill signals (TVL < $500K etc)", "Foundry PoC template", "grep patterns for each class", and "real Immunefi paid examples" — giving comprehensive, not just minimal, coverage.	5 / 5
Completeness	It explicitly states what the skill does (the listed bug classes, kill signals, PoC template, grep patterns, paid examples) and when to use it ("Use for any Solidity/Rust contract audit or when deciding whether a DeFi target is worth hunting"), matching the top anchor on both axes.	5 / 5
Trigger Term Quality	Natural terms a hunter would say are present ("smart contract security audit", "Solidity/Rust contract audit", "DeFi target", "Immunefi", "worth hunting"), but common variations like "bug bounty", "web3", and file extensions such as ".sol" are missing, so it falls just short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	The DeFi-specific niche and Immunefi framing make it mostly distinct with minimal conflict risk, but the broad trigger "any Solidity/Rust contract audit" leaves minor overlap risk with closely related on-chain audit skills.	4 / 5
	Total	18 / 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
skill_md_line_count	SKILL.md is long (607 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: elementalsouls/Claude-BugHunter
Path: skills/web3-audit/SKILL.md
Commit: d4b54e1

Reviewed: 3 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.