Edessa

Run your SOP inside GitHub Copilot

Last updated: October 3, 2026

Copilot is built around the repository: the instructions live there, so everybody working in it gets them without installing anything.

That makes it the right place for a process the whole team has to follow the same way.

What can GitHub Copilot read?

Copilot reads repository custom instructions from a Markdown file in your repository, and applies them to work in that repository for every person on it. The instructions are plain natural language, so a workflow write-up drops in with no reformatting.

The trade-off is scope. The instructions file is per repository, which is right for a shared process. For something only you do, Copilot also reads personal skills from ~/.copilot/skills.

The details move, so check GitHub’s custom instructions docs 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. Add it to the repository as custom instructions, at the path in GitHub’s docs: .github/copilot-instructions.md
  3. Commit it. From then on it applies for everyone working in that repository, which also means it goes through review like any other change.
  4. Or export it as a Skill and unzip it into the repository’s .github/skills folder, where Copilot’s agent mode, cloud agent and CLI pick it up when the work matches.
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 GitHub Copilot can now see how your business actually works.

  • "Follow the process in the instructions for this change, and tell me which step you are on." Naming the step makes it obvious when the agent has skipped one.
  • "Does this change follow our documented process? Where does it not?" Turns the write-up into a review checklist, which is the highest-value use of a process file on a team.
  • "Our process says to do X. Is that still what the code does?" Finds the gap between the written process and what was actually shipped, which is the gap a stale file hides.

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.