Automation Advisor

glebis/automation-advisor

Interactive automation decision advisor using the Automation Decision Matrix framework. Use when the user asks "should I automate this?", wants to evaluate an automation opportunity, calculate automation ROI or break-even, or requests an automation decision analysis. Guides a structured questionnaire, scores four dimensions, applies override checks, and generates an Obsidian-formatted report with a visual decision diagram.

43k tokens

context cost

the whole folder, loaded on every use

files

ships runnable scripts

copies elsewhere

how many repositories repackaged it

337

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/glebis/claude-skills --skill automation-advisor

What comes with it

170 731 bytes besides the instruction

CLAUDE.md

README.md

docs/DESIGN_SYSTEM.md

docs/LLM_CONTEXTUAL_UX_DESIGN.md

docs/QUICKSTART.md

docs/WEB_SERVER_GUIDE.md

prompt.md

requirements.txt

server.py

server_web.py

skill.yaml

start_server.sh

templates/index.html

test_demo.py

test_groq_tts.py

visualize.py

The instruction itself

3 sections, as written by the author

Automation Advisor

Help the user decide whether to automate a task using data, not gut feeling.

Process

Gather task context through freeform conversation
Score four dimensions using AskUserQuestion
Calculate the automation score
Apply override checks
Recommend validation patterns for high-stakes automation
Calculate break-even analysis
Generate a markdown report + visualization (visualize.py)

Follow the full interactive flow in prompt.md.

Output location: /Users/glebkalinin/Brains/brain/automation-decisions/

Optional web/voice interface

A voice-enabled (Groq TTS) web interface lives in server_web.py / server.py — see docs/WEB_SERVER_GUIDE.md and docs/QUICKSTART.md.

How to use it

Copy the folder

Take glebis/automation-advisor from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.