How do I install the Skill skill?

Run npx skillmds@latest add artvepa80/skill in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Skill skill do?

HefestoAI — Claude Code Skill Reference It is listed under Coding & Dev Tools on SkillMD.

Is Skill safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Skill?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Skill free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

artvepa80 (@artvepa80) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Skill by artvepa80 — Agent Skill

Name: Skill
Author: artvepa80

File contents

HefestoAI — Claude Code Skill Reference

HefestoAI is a pre-commit code quality guardian that detects semantic drift, security vulnerabilities, and reliability anti-patterns in AI-generated code.

Package: hefesto-ai (PyPI) | Version: 4.13.1 | License: MIT Requires: Python >= 3.10

When to Load These Docs

User asks about code quality analysis or pre-commit hooks
User wants to detect issues in AI-generated code
User needs to set up CI/CD quality gates
User mentions semantic drift, code smells, or security scanning
User wants to integrate HefestoAI with Claude Code or Cursor

Document Index

File	Contents
issue_types.md	All 73 issue types with severities and descriptions
commands.md	CLI commands, flags, workflows, and exit codes
semantic_drift.md	What semantic drift is and how HefestoAI detects it
reliability_drift.md	5 RELIABILITY_* rules for long-running services
integration.md	Pre-commit hooks, CI/CD, MCP server setup

Quick Start

pip install hefesto-ai
hefesto analyze .
hefesto install-hooks

Architecture Overview

HefestoAI runs a two-phase pipeline:

Phase 0 — Static Analysis (always enabled): 5 analyzers run deterministically on every file:

ComplexityAnalyzer — cyclomatic and cognitive complexity
CodeSmellAnalyzer — long functions, deep nesting, dead code, etc.
SecurityAnalyzer — hardcoded secrets, injection risks, eval/pickle
BestPracticesAnalyzer — naming, docstrings, style
ResourceSafetyAnalyzer — reliability drift (EPIC 4)

DevOps analyzers run on non-Python files: YAML, Shell, Dockerfile, Terraform, SQL — each with dedicated analyzer.

Phase 1 — ML Semantic Analysis (PRO/OMEGA only): Detects semantic duplication across functions using embeddings. Enabled when HEFESTO_TIER=professional or HEFESTO_TIER=omega.

Supported Languages

Python, JavaScript, TypeScript, Java, Go, Rust, C, C++, YAML, Shell/Bash, Dockerfile, Terraform/HCL, SQL, PowerShell.

MCP Server

Registry: io.github.artvepa80/hefestoai Protocol: JSON-RPC 2.0 (streamable-http) Endpoint: https://hefestoai.narapallc.com/api/mcp-protocol

npx @smithery/cli@latest mcp add artvepa80/hefestoai

---name: skilldescription: HefestoAI — Claude Code Skill Reference---# HefestoAI — Claude Code Skill ReferenceHefestoAI is a pre-commit code quality guardian that detects semantic drift,security vulnerabilities, and reliability anti-patterns in AI-generated code.Package: `hefesto-ai` (PyPI) | Version: 4.13.1 | License: MITRequires: Python >= 3.10## When to Load These Docs- User asks about code quality analysis or pre-commit hooks- User wants to detect issues in AI-generated code- User needs to set up CI/CD quality gates- User mentions semantic drift, code smells, or security scanning- User wants to integrate HefestoAI with Claude Code or Cursor## Document Index| File | Contents ||------|----------|| [issue_types.md](issue_types.md) | All 73 issue types with severities and descriptions || [commands.md](commands.md) | CLI commands, flags, workflows, and exit codes || [semantic_drift.md](semantic_drift.md) | What semantic drift is and how HefestoAI detects it || [reliability_drift.md](reliability_drift.md) | 5 RELIABILITY_* rules for long-running services || [integration.md](integration.md) | Pre-commit hooks, CI/CD, MCP server setup |## Quick Start```bashpip install hefesto-aihefesto analyze .hefesto install-hooks```## Architecture OverviewHefestoAI runs a two-phase pipeline:**Phase 0 — Static Analysis** (always enabled):5 analyzers run deterministically on every file:1. ComplexityAnalyzer — cyclomatic and cognitive complexity2. CodeSmellAnalyzer — long functions, deep nesting, dead code, etc.3. SecurityAnalyzer — hardcoded secrets, injection risks, eval/pickle4. BestPracticesAnalyzer — naming, docstrings, style5. ResourceSafetyAnalyzer — reliability drift (EPIC 4)DevOps analyzers run on non-Python files:YAML, Shell, Dockerfile, Terraform, SQL — each with dedicated analyzer.**Phase 1 — ML Semantic Analysis** (PRO/OMEGA only):Detects semantic duplication across functions using embeddings.Enabled when HEFESTO_TIER=professional or HEFESTO_TIER=omega.## Supported LanguagesPython, JavaScript, TypeScript, Java, Go, Rust, C, C++,YAML, Shell/Bash, Dockerfile, Terraform/HCL, SQL, PowerShell.## MCP ServerRegistry: `io.github.artvepa80/hefestoai`Protocol: JSON-RPC 2.0 (streamable-http)Endpoint: `https://hefestoai.narapallc.com/api/mcp-protocol````bashnpx @smithery/cli@latest mcp add artvepa80/hefestoai```

Frequently asked questions

Skill