skill-forge

<div align="center">

  <picture>
    <source media="(prefers-color-scheme: dark)" srcset=".github/logo-dark.svg">
    <source media="(prefers-color-scheme: light)" srcset=".github/logo-light.svg">
    <img alt="Skill Forge" src=".github/logo-light.svg" width="480">
  </picture>

  <p>From local experiment to installable, trustworthy skill — in one command.</p>
</div>

> **Skills are code. Engineer them like it.**

<div align="center">

[![License: MIT][license-shield]][license-url]
[![Version][version-shield]][version-url]
[![Agent Skills][skills-shield]][skills-url]

</div>

<div align="center">
  <a href="#quick-start">Quick Start</a> &middot;
  <a href="#usage">Usage</a> &middot;
  <a href="#install">Install</a> &middot;
  <a href="https://agentskills.io">Agent Skills</a>
</div>

---

## The Problem

The Agent Skills ecosystem has grown to 88K+ published skills ([SkillsMP](https://skillsmp.com), [skills.sh](https://skills.sh)). Community audits estimate ~26% have security vulnerabilities. Most have descriptions that don't cover their actual trigger scenarios. There is no standard for what a "well-engineered skill" looks like.

**If you haven't published yet** — your skill is trapped in one project, can't be shared, and doesn't meet any platform's install standard. No README, no LICENSE, no proper structure, no discoverability.

**If you already published** — your repo might have issues you haven't noticed: leaked API keys in config files, missing .gitignore entries, structure that doesn't match the [Agent Skills](https://agentskills.io) standard, or claims in the README that don't match what the skill actually does.

The gap is not in authoring — AI agents can already help write skill content. The gap is in engineering: validating structure, scanning for security issues, checking description coverage, catching README claims that don't match actual capabilities, and publishing correctly.

## What Skill Forge Does

- **Audits entire projects** — point forge at any