Automate Me

Captures your working style from chat history and turns it into a personal mode skill that agents will follow. It mines recent transcripts for patterns (how you like responses, when you want subagents, your git workflow), asks you structured questions to fill gaps, then orchestrates create-skill and unslop to draft something like jay-mode or priya-mode. The mining stays scoped to your current workspace, cross-checks signals across time slices before codifying them, and defaults to updating your existing mode skill rather than starting fresh each time. Honest take: this is meta-automation done right. Instead of repeating preferences every conversation, you encode them once and let agents adapt to you.

skills.sh installs: 4.3K
GitHub stars: 15.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add cursor/plugins --skill automate-me --agent claude-code

Installs into .claude/skills of the current project.

Files

Automate me

A guided flow for turning the user's working conventions into a skill agents will follow. The output is one -mode skill tailored to them (e.g. jay-mode, priya-mode).

This skill orchestrates three others: an inline mining pass (see step 1), Cursor's built-in create-skill (authoring), and the unslop skill (prose discipline). It sequences them. It doesn't replace them.

Flow

0. Check for an existing skill

Look recursively for .cursor/skills/**/*-mode/SKILL.md and ~/.cursor/skills/*-mode/SKILL.md matching the user's handle. Mode skills can live in a personal category directory (.cursor/skills/<handle>/), not only at the top level. If one exists, confirm intent with AskQuestion (unless they already said "update my skill" or similar):