1. Habit
  2. Skills
  3. Skill Vetter skill
UseAI-pro · 21K installs

Skill Vetter skill
Runs by itself, before every skill install or update.

No skill gets installed without a safety report.

Install the Skill Vetter skill and make it a habit: follow https://gethabit.dev/skills/useai-pro/skill-vetter.md

  1. 1Copy
  2. 2Paste into Claude Code, Codex or Cursor
  3. 3It runs by itself

21K installs73 starsMIT licenceSource on GitHub ↗

Skill Vetter

by UseAI-pro · 21K installs

The skill

Checks a skill for risks before you install it.

Only when you ask.

Safer agents

No skill gets installed without a safety report. Fewer nasty surprises.

↻ Runs by itselfbefore every skill install or update

How the habit works.
You don't have to.

Three questionsWhen does it start? How does it check its work? What does it remember?

01

It starts by itself

Skill install or update. Runs in Claude Code routine or GitHub Actions.

  • ↻ Skill install or update
  • new or changed SKILL.md before install

02

It checks its work

report with verdict. If a check fails, it stops.

  • ✓the report has a VERDICT of SAFE, WARNING, DANGER or BLOCK
  • ✓RED FLAGS count is stated
  • ✓a skill with network plus shell is flagged
  • ✓any critical red flag sets the verdict to BLOCK

03

It remembers

vetting reports. The next run reads it first: past verdicts and the version each was given for.

loops/skill-vetting-loop/reports.md

One run, step by step.
Then it stops.

Stop ruleStops after one skill per run.

  1. 01

    Check metadata

    The agent checks name, semver version, description and author in the frontmatter.

  2. 02

    Score permissions

    It rates fileRead, fileWrite, network and shell against what the skill needs.

  3. 03

    Scan content

    It looks for critical, warning and informational red flags in the body.

  4. 04

    Check typosquats

    It compares the name with known skills for small spelling tricks.

  5. 05

    Write the report

    It fills the vetting report format with a verdict and a recommendation.

What it may do.
Nothing more.

Safe by defaultIt writes only in its own folder and asks you before anything goes out.

Is it for you?
Use it when it fits.

Quick checkRead both lists. If the left one sounds like you, the Skill Vetter skill helps.

Use it when

  • ✓ You are about to install a new skill
  • ✓ You review a SKILL.md from GitHub
  • ✓ You audit skills you already have

Skip it when

  • – You only use skills you wrote
  • – You need a full code audit of scripts

Questions

Skill Vetter skill, answered.

Why vet a skill again after an update?

The skill notes that a version that was safe can change in the next release.

What if the verdict is unclear?

The skill recommends running the skill in a sandbox first.

Does it report bad skills anywhere?

The skill suggests telling the UseClawPro team. This loop only writes the report and leaves sending to you.

How do I install the Skill Vetter skill?

Copy the prompt at the top into your agent. It installs the skill from UseAI-pro/openclaw-skills-security and sets up the habit. Or run npx skills add UseAI-pro/openclaw-skills-security --skill skill-vetter.

Is the Skill Vetter skill free?

Yes. It is published under MIT. Habit is free too.

Skill Vetter. Now as a habit.

Install the Skill Vetter skill and make it a habit: follow https://gethabit.dev/skills/useai-pro/skill-vetter.md

  • Free
  • No account
  • Undo in one line

All UseAI-pro skills →More ops skills →

Works in

  • Claude Code
  • Codex
  • Cursor
  • ChatGPT
  • Claude app

Made by UseAI-pro, published under MIT. Habit links to the original and never changes it. Is this your skill?

Copying didn't work here. Select the line and copy it by hand.