SK
skills
>-
Install
mkdir -p .claude/skills/skills-0x-shashi && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15404" && unzip -o skill.zip -d .claude/skills/skills-0x-shashi && rm skill.zipInstalls to .claude/skills/skills-0x-shashi
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Root skill definition for the Web3 Audit Plugin providing AI-powered smart contract security auditing across EVM, Solana, Move, Cairo, CosmWasm, and TON platforms. Use as the top-level entry point for understanding plugin capabilities, supported chains, and skill routing.272 charsno explicit “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
About this skill
Web3 Audit Plugin - Core Skill Definition
Purpose
This plugin provides AI-powered smart contract security auditing capabilities across multiple blockchain platforms.
Capabilities
- Multi-chain smart contract analysis (EVM, Solana, Move, Cairo, CosmWasm, TON)
- Pattern-based vulnerability detection using 200+ known patterns
- Protocol-specific audit checklists (DeFi, NFT, Bridge, Governance)
- Attack chain analysis for multi-step exploit detection
- Automated severity classification
- Report generation with findings templates
Usage
- Load the target smart contract code
- Identify the chain and protocol type
- Run appropriate scanner skill
- Apply relevant checklist
- Check attack chain patterns
- Generate audit report
Skill Chain
Context Building → Scanner → Checklist → Attack Chains → Report
Available Scanners
- Solidity Scanner (EVM chains)
- Solana Scanner (Rust/Anchor)
- Cairo Scanner (Starknet)
- Move Scanner (Aptos/Sui)
- Cosmos Scanner (CosmWasm/SDK)
- TON Scanner (FunC/Tact)
- Aptos Scanner (Move/Aptos)
- Sui Scanner (Sui Move)
- Starknet Scanner (Cairo)
- Aztec Scanner (Noir)
- Fuel Scanner (Sway)
Prerequisites
The plugin requires an AI model with tool-use capabilities. Each scanner skill may have chain-specific prerequisites (e.g., Solana scanner requires familiarity with Anchor framework).
Validation
To verify installation and test skill loading:
# Validate all SKILL.md files pass quality threshold
python scripts/quality-check.py --all --min-score 8
# Example trigger routing
trigger: "audit solidity"
route_to: solidity-scanner/SKILL.md
load: [checklists, patterns, severity]
# Verify scanner availability
ls skills/*/SKILL.md | wc -l # Should show 29+ skills
Behavior Guidelines
- Scanner selection is required based on detected chain type
- Protocol template loading is optional but recommended
- Severity classification MUST follow the decision tree in
patterns/severity-scoring.md - Auditors may optionally skip gas optimization checks depending on engagement scope
References
- Core References - Architecture diagrams and skill routing maps