Run your SOP inside Cursor

Last updated: October 3, 2026

Some small businesses use Cursor for work that is not code: a spreadsheet, a data file, a script somebody wrote once. The agent is good at the doing and has no idea how your business wants it done.

Handing it the written process closes that gap, and it takes one file.

What can Cursor read?

Cursor reads project rules from a .cursor/rules directory, and an AGENTS.md file at your project root as the simpler alternative. Cursor also reads Agent Skills, the same SKILL.md format Edessa exports, from a .cursor/skills or .agents/skills folder.

Which of the three you use matters less than picking one and keeping it the only copy.

The details move, so check Cursor’s skills docs rather than a blog post. The install steps were checked against the vendor docs on October 3, 2026.

Where does the file go?

Export the workflow as a Skill.
Unzip it into your project’s .cursor/skills folder, or into ~/.cursor/skills for every project. Cursor also reads ~/.claude/skills, so a skill already installed for Claude Code shows up here too: unzip -o ~/Downloads/<skill>.zip -d ~/.cursor/skills/
If you would rather use plain Markdown, paste the workflow into an AGENTS.md file at the project root. Rule files in .cursor/rules need the .mdc extension and frontmatter, so a plain .md there is ignored.

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 Cursor can now see how your business actually works.

"Follow this process on these files and show me the diff before you touch anything." Diff-first is the only safe default for an agent acting on real files.
"Which steps in this process could be one script instead?" Cursor can answer this well because it can see the files the steps operate on.
"What in this process would break if the input format changed?" The fragile step may not be the obvious one, and it is the one worth writing down.

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

Run your SOP inside Cursor

What can Cursor read?

Where does the file go?

Three asks worth trying

How do you keep it current?

Related reading