SkillAgentSearch skills...

setup

30-second auto-detection tour, then optional configuration of notifications, CLI allowlist, research CLAUDE.md rules, and LaTeX environment

Install / Use

npx skills add fcakyon/phd-skills --skill setup

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

87/100

Supported Platforms

Claude Code

Tags

Our assessment of setup

setup scores 87/100 on our quality scale, 268th of 394 Communication skills we index.

Its SKILL.md is 5.1 KB long, well organised into 12 sections with 6 code examples: a solid amount of guidance for an agent.

It has 406 GitHub stars, a meaningful sign that others use it.

Substance
26/30
Structure
20/20
Description
15/15
Adoption
11/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so setup is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

Review

Our scan of the whole file found 1 pattern worth reviewing before you install setup. An AI review judged it risky: Step 3 instructs the agent to merge an `allowedTools` list into `.claude/settings.json`, adding Bash command patterns to the permission allow-list and weakening safeguard prompts.

  • mediumSends the output of a local command to a remote serverline 80
    - **ntfy.sh**: ask for topic name, write to `.env` as `NTFY_TOPIC=<topic>`. Test with `curl -d "labrat test" ntfy.sh/<topic>`

AI review: risky

  • Step 3 instructs the agent to merge an `allowedTools` list into `.claude/settings.json`, adding Bash command patterns to the permission allow-list and weakening safeguard prompts.
  • Step 2 has the agent send test notifications to user-supplied remote endpoints (ntfy.sh, Slack webhook, email); this is user-configured and legitimate, but matches the flagged remote-transmission pattern.
  • The Step 0 shell-history probe reads local `history` but only displays results to the user and does not exfiltrate them.

AI review by kimi-k2.7-code on 2026-11-12. Automated pattern scan on 2026-11-12. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

setup compared with similar skills

All 4 of these similar skills score higher than setup; compare them before choosing.

SkillScoreStarsUpdatedFormat
setup (this skill)by fcakyon874062mo agoSKILL.md
x402by browser-use100121.0k3d agoSKILL.md
algorithmic-artby anthropics100177.9k55d agoSKILL.md
pptxby anthropics100177.9k55d agoSKILL.md
designby nextlevelbuilder100149.0k6d agoSKILL.md

Frequently asked questions

How do I install setup?
Run npx skills add fcakyon/phd-skills --skill setup. The install tabs above show the steps for each supported agent.
Which AI agents does setup work with?
It is written for Claude Code, as a SKILL.md file. Other agents that read the same format can often use it too.
Is setup safe to use?
Our scan of the whole file found 1 pattern worth reviewing before you install setup. An AI review judged it risky: Step 3 instructs the agent to merge an allowedTools list into .claude/settings.json, adding Bash command patterns to the permission allow-list and weakening safeguard prompts. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is setup still maintained?
The repository was last updated about 2 months ago, so setup is actively maintained.

name: setup description: > 30-second auto-detection tour, then optional configuration of notifications, CLI allowlist, research CLAUDE.md rules, and LaTeX environment. Use when the user runs /labrat:setup. disable-model-invocation: true allowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion

Lab Rat Setup

The plugin works correctly the moment it is installed. Most users never need to run setup. This skill 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:

# 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)

# 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:

Lab Rat auto-detected the following:

Recent launches:    <count> training-job patterns in shell history
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 prompt. 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.

Step 1: Feature Selection (optional, only if user opted in)

Use AskUserQuestion:

Which extras would you like to set up?

1. Notifications: get alerts when long tasks complete (ntfy / slack / email)
2. CLI Allowlist: auto-approve safe commands used in research workflows
3. Research CLAUDE.md: add research integrity rules to your project
4. LaTeX Environment: detect and configure LaTeX / BibTeX toolchain

Enter numbers separated by commas (e.g., 1,3,4), or "all":

Step 2: Notifications (if selected)

Ask which notification method:

How would you like to receive notifications?

1. ntfy.sh: free, works over SSH, no account needed
2. Slack: webhook to a channel
3. Email: via sendmail / msmtp

Enter number:

Based on selection:

  • ntfy.sh: ask for topic name, write to .env as NTFY_TOPIC=<topic>. Test with curl -d "labrat test" ntfy.sh/<topic>
  • Slack: ask for webhook URL, write to .env as SLACK_WEBHOOK_URL=<url>. Test with curl POST
  • Email: ask for recipient, write to .env as NOTIFICATION_EMAIL=<email>. Test with sendmail

Step 3: CLI Allowlist (if selected)

Show the user a list of safe, non-destructive commands commonly used in research:

{
  "allowedTools": [
    "Read",
    "Glob",
    "Grep",
    "Bash(pdflatex *)",
    "Bash(biber *)",
    "Bash(bibtex *)",
    "Bash(python -c *)",
    "Bash(uv run *)",
    "Bash(git status)",
    "Bash(git diff *)",
    "Bash(git log *)",
    "Bash(nvidia-smi)",
    "Bash(htop)",
    "Bash(df -h)",
    "Bash(wc -l *)",
    "Bash(du -sh *)"
  ]
}

Ask for confirmation, then merge into .claude/settings.json.

Step 4: Research CLAUDE.md (if selected)

Present the following research integrity rules to add to the project's CLAUDE.md:

## Research Integrity Rules

- Code is the source of truth. When paper text and code disagree, the code is correct
  unless the user explicitly states otherwise.
- Never state a numerical result without tracing it to a specific file, log, or code output.
  If you cannot find the source, say so explicitly.
- Never assume domain-specific technical behavior. Verify against code before making claims
  about how methods, losses, architectures, or training procedures work.
- When editing paper text, change ONLY what was requested. Do not remove existing content,
  add unrequested sections, or "improve" surrounding text unless asked.
- Citation integrity: verify author names, venue, and year against DBLP before adding or
  modifying any BibTeX entry. Flag any citation detail you cannot verify.
- Edit code locally, commit, push, then `git pull` on the GPU host. Never edit tracked code
  in place over SSH.

Ask the user to confirm, then:

  • Read existing CLAUDE.md (if any)
  • Append the research rules section (avoiding duplicates)

Step 5: LaTeX Environment (if selected)

Follow the LaTeX setup.

Paper search (when needed)

See paper search setup.

Escape hatches (mention only if asked)

The plugin avoids configuration on purpose. If a user really wants to override:

  • Suppress a hook: edit ~/.claude/settings.json and set "hooks.<event>.<matcher>.disabled": true (Claude Code's standard mechanism)

Related Skills

View on GitHub
GitHub Stars406
CategoryCommunication
Updated2mo ago
Forks34

Languages

Shell

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions