Turn a screen recording into a Gemini agent skill

Skills for Gemini-powered agents

Agents built on Google Gemini reason well but drift on multi-step UI tasks. A SKILL.md pins the exact steps — the clicks, typing, and navigation — so the Gemini agent stays on rails instead of improvising.

How it works

1. Record the workflow at skillforge.expert/app (10–60 seconds).
2. SkillForge extracts the actions into a SKILL.md.
3. Provide the SKILL.md to your Gemini agent as a structured plan; it replays the steps.

Portable across frameworks

The same SKILL.md also works with autogen, crewAI, langchain, browser-use, and Claude Skills — record once, reuse everywhere.

FAQ

Does this work with Google Gemini agents?
Yes. SkillForge outputs a plain SKILL.md that any agent runtime, including Gemini-based ones, can read and follow.

Do I need Google Cloud or Vertex AI to use the SKILL.md?
No. The SKILL.md is provider-agnostic; you attach it to whatever Gemini agent setup you already use.

Is it free?
Recording and AI extraction are free; new accounts get 15 credits and downloads cost 5 credits.