Edessa

Run your SOP inside Gemini CLI

Last updated: October 3, 2026

Gemini CLI runs in the terminal, so there is no interface to upload into, just files it reads. That turns out to be an advantage when the thing you want it to read is a process.

What can Gemini CLI read?

Gemini CLI reads context files, GEMINI.md by default, as playbooks telling the model how to work. It also supports extensions, which bundle a context file, prompts and commands together and install from a Git repository, so a process your whole team uses can be shared rather than copied.

Start with the context file. Reach for an extension only when more than one person needs the same process and copying the file has already gone wrong once.

The details move, so check the Gemini CLI docs on GEMINI.md rather than a blog post. The install steps were checked against the vendor docs on October 3, 2026.

Where does the file go?

  1. Export the workflow as Markdown.
  2. Save it as the context file in the directory you run Gemini CLI from: GEMINI.md
  3. Run Gemini CLI there and ask for the task. To share it with a team later, the extensions docs cover bundling the same file so it installs from a repository.
  4. Or export it as a Skill and unzip it into ~/.gemini/skills. Gemini CLI asks before it activates a skill, then follows it.
Try Edessa free

Three asks worth trying

Once the process is loaded, the useful prompts are not “summarise this.” They are the ones that use the fact that Gemini CLI can now see how your business actually works.

  • "Follow this process and print each step before you run it." In a terminal you cannot undo a step you did not see coming.
  • "Which steps here are just moving or renaming files?" Those are the steps a shell script does better than any agent, and the ones worth taking out of the process entirely.
  • "What does this process assume is already installed?" Every written process has an invisible prerequisite. This is the fastest way to find yours.

How do you keep it current?

This is where documentation goes stale. The process changes, the file does not, and six months later the skill is confidently wrong. Keeping it right by hand means editing a Markdown file every time a step changes.

The alternative is re-recording. Do the task once the new way, replace the file with the new export, and the thing your AI tool reads matches what you actually do. That takes about as long as the task does.

The recording method is here, including the manual version if you would rather not use a tool for it.

Who wrote this. Thaddeus Demeke, Founder of Elevaite and the founder of Edessa. Five years at Genentech, most recently as a Senior Data Scientist, then building AI systems inside small businesses across agencies, home services, real estate and ecommerce. I run my own processes this way.

See how the AI SOP generator works

Related reading

© 2026 ElevaiteWorks LLC. A product of Elevaite.