Skip to main content
Back

Open-Source agent-skill-creator Turns Any Workflow Into AI Skills Across 17 Tools

FrancyJGLisboa's open-source repo turns any workflow description into a validated, cross-platform agent skill — no spec writing or prompt engineering needed

Repo, Full Access
  • What it is: An open-source Python repo that converts any workflow description into a validated, cross-platform agent skill — no spec writing or coding needed.
  • 17 platforms: Generated skills auto-install on Claude Code, Copilot, Cursor, Gemini CLI, Codex, Windsurf, Kiro, and 10 more via one SKILL.md file.
  • Built-in quality gates: Every skill is spec-validated and security-scanned before delivery; skills that fail are blocked.
  • Evals included: Each generated skill ships with a regression test suite (run_evals.py) that exits non-zero on failure and drops into CI.
  • Team sharing: A git-based skill registry lets teams publish, browse, and install skills with no servers required.
  • Free and open-source: MIT license, ~1,400 GitHub stars — github.com/FrancyJGLisboa/agent-skill-creator

agent-skill-creator is an open-source Python repo that automates the hardest part of building agent skills: going from a messy workflow description to a validated, installable skill that works across 17 AI coding tools. You hand it a plain-English description, a PDF, a URL, or an existing script , and it produces a complete SKILL.md-based skill package, security-scanned and ready to install.

What are agent skills, and why do they matter?

Skills are reusable, filesystem-based resources that give agents domain-specific expertise , workflows, context, and best practices that transform general-purpose agents into specialists. Unlike prompts, skills load on-demand and eliminate the need to repeatedly provide the same guidance across multiple conversations.

Agents load skills through progressive disclosure: at startup they load only the name and description of each skill (just enough to know when it's relevant), then read the full SKILL.md when a task matches, and finally execute bundled code or load referenced files as needed. Full instructions load only when a task calls for them, so agents can keep many skills on hand with a small context footprint.

Agent Skills is an open standard that works across multiple AI agents, including GitHub Copilot in VS Code, Copilot CLI, and the Copilot cloud agent. Unlike custom instructions that primarily define coding guidelines, skills enable specialized capabilities and workflows that can include scripts, examples, and other resources. Skills you create are portable and work across any skills-compatible agent.

The problem this repo solves

Every AI coding tool starts from zero. It doesn't know your company's processes, data sources, or compliance requirements , so every person re-explains the same workflows in every conversation. Knowledge stays in individual chat histories, and new team members start from scratch.