# Automation decision advisor

A found skill.

Compares setup and maintenance time with estimated hours saved before automating a task.

Task: Planning and reviews
Works with: Claude, ChatGPT, Gemini
Tools: Any chat assistant
Difficulty: Intermediate
Country: Country unknown

Use this when you wonder whether a repeat task is worth automating.
Skip this if you want numbers, prices or facts filled in that you have not given.

Source: https://github.com/glebis/claude-skills/blob/main/automation-advisor/SKILL.md

## Skill text

Please turn the text below into a reusable skill. If you are Claude, save it as a skill. If you are ChatGPT or Gemini, save it as the instructions for a Project, custom GPT or Gem. If you cannot save skills, just follow these instructions now.

Name: Automate or not
Description: Use this when you wonder whether a repeat task is worth automating.
Ask me for: the task, how often it runs, minutes each time, what goes wrong if it errs, and how fixed the steps are.
Steps:
1. Record task frequency, current minutes per run and expected automated minutes, using my figures only.
2. Calculate monthly hours saved, less my estimated review and maintenance time.
3. If net saved time is positive, divide setup hours by monthly hours saved for break-even months. Otherwise report no time break-even.
4. List risks and require human review for consequential work.
5. Give a tentative yes, no or later with assumptions, not an automatic decision.
Output: A score, a break-even estimate and one recommendation.
Rules: Do not invent numbers. Use mine only. Do not set anything up.
Starter by me, inspired by automation-advisor by Gleb Kalinin. Original: https://github.com/glebis/claude-skills/blob/main/automation-advisor/SKILL.md . Check the licence before reusing the original.

## More

- [This skill as a web page](https://agentstories.org/skills/automation-break-even-check.html)
- [All skills, as a Markdown list](https://agentstories.org/skills.md)
- [Skills directory](https://agentstories.org/skills/)
