pashov/skills

Pashov Audit Group Skills

What it solves

This project provides a set of AI-powered tools designed to automate and enhance the security auditing of Solidity smart contracts, helping developers and auditors find vulnerabilities and create testing suites more efficiently.

How it works

It functions as a collection of "skills" or prompt-based tools that integrate with AI coding platforms like Claude Code, Cursor, Codex, GitHub Copilot, and Windsurf. Users can trigger specific security workflows by running commands such as "x-ray" for pre-audit scans or "solidity auditor" for vulnerability detection.

Who it’s for

Smart contract developers and security auditors who need to secure Foundry or Hardhat projects written in Solidity.

Highlights

  • Solidity Auditor: An AI security audit tool that has identified hundreds of Critical and High severity vulnerabilities.
  • X-Ray: A pre-audit tool that performs threat modeling, identifies invariants, maps entry points, and analyzes git history.
  • Fizz: A tool that automatically generates comprehensive Echidna or Medusa fuzzing suites for smart contract projects.

Related

  • Project
    kharmanskyi/open-steps

    Open Steps is a MIT‑licensed pack of prompt‑templates (“skills”) and two shell hooks that make Claude Code, Codex CLI, Cursor CLI and Gemini CLI speak plain language. It provides one‑screen “done‑or‑not” reports, step‑by‑step user instructions, simple question/answer prompts, premortem risk analysis, backlog tracking, and even autonomous PR merges. Install via a Claude plugin or by copying the skill folders and adding a tiny routing block to each agent’s config.

  • Project
    ChesterRa/cccc

    A coordination layer for coding agents that organizes multiple AI agents from different runtimes into durable, tracked groups with a unified web dashboard.

  • Project
    Miaotofu01/Study-Mate

    StudyMate is a Node.js‑based AI tutoring system for math and CS, delivered as a DeepSeek Harness plugin (and also as Antigravity, Codex, or ChatGPT plugins). It builds curriculum roadmaps, renders markdown lessons, saves progress in a local workspace, and can export offline HTML. Install via `npx @yunmiao/studymate@latest install`, then converse with the AI to pick subjects, get lessons, practice, and assess.

  • Project
    SaladDay/pi-from-scratch

    A TypeScript-based coding agent implementation and interactive tutorial that teaches how to build an agent capable of reading files, editing code, and executing commands.