setup

PHD-Skills Setup

The plugin works correctly the moment it is installed. Most users never need to run setup. This command exists to (1) show what was auto-detected on the user's system, and (2) let users opt into a few extras (notifications, allowlist, project CLAUDE.md, LaTeX).

Step 0: Auto-detection tour (always run first)

Before asking any questions, print what the plugin already knows. No prompts, no decisions, just visibility.

Run these probes silently and present the results:

# System timezone
sys_tz=$(date +%Z)
sys_tz_long=$(readlink /etc/localtime 2> /dev/null | sed 's|.*zoneinfo/||')

# Last few long-job launches the plugin would have flagged
recent_launches=$(history 200 2> /dev/null | grep -E '(python.*train|accelerate launch|torchrun|deepspeed|sbatch|tmux.*python)' | tail -5)

# Sample jargon-shape hits in user's recent commits (if in a git repo)
jargon_hits=$(git log -50 --pretty=format:%s 2> /dev/null | grep -E '\bwave-[0-9]+\b|\bphase-internal\b|\binternal-only\b' | head -3)

# What the agentic Stop hook would orient on for this project
project_orientation=""
[ -f README.md ] && project_orientation+="README.md found  "
[ -f CLAUDE.md ] && project_orientation+="CLAUDE.md found  "
[ -f .claude/CLAUDE.md ] && project_orientation+=".claude/CLAUDE.md found  "
[ -f AGENTS.md ] && project_orientation+="AGENTS.md found  "

Then present:

phd-skills auto-detected the following:

Timezone:           ${sys_tz} (${sys_tz_long})
Recent launches:    <count> training-job patterns in shell history
Jargon hits:        <count> commits with internal-jargon shapes
Project orientation: ${project_orientation:-no README / CLAUDE.md / AGENTS.md found at project root}

This is what the hooks and agentic Stop hook will use. No configuration needed.
The plugin works on the first command. Hooks fire silently when there is nothing to flag.

Want to configure any extras? (notifications, allowlist, CLAUDE.md, LaTeX) [y/N]

If the user says no, you are done. If yes, walk them through the optional steps below.