Install
openclaw skills install @itspremkumar/prompt-lintLint prompts/SKILL.md for quality (role, goal, output format, vague verbs, jailbreak phrases). Stdlib.
openclaw skills install @itspremkumar/prompt-lintLint AI prompts for clarity, safety, injection risk, and template validity — scored 0-100.
Keywords: lint, prompt, ai, cli, safety, quality, python, open-source, agent, automation, MIT
Part of the itsPremkumar Hermes / OpenClaw / Paperclip agent stack — 31 free, MIT-licensed, CI-tested agent-native tools.
Bad prompts produce bad outputs; quality isn't measurable. Prompt Linter solves this: Lint AI prompts for clarity, safety, injection risk, and template validity — scored 0-100.
Best for: Prompt engineers, agent builders, and AI product teams.
# Requires Python 3.8+. No pip install needed.
curl -O https://raw.githubusercontent.com/itsPremkumar/prompt-lint/main/prompt_lint.py
# Or copy the file anywhere — it's self-contained.
python prompt_lint.py self-test # prove it works end-to-end
python prompt_lint.py check --help # check subcommand
| Alternative | Why this skill is better |
|---|---|
| Eyeballing prompts | Measurable quality + safety. |
| Partial linters | Adds injection + template checks. |
| No gate | CI-ready scoring. |
Q: Score?
A: 0-100 quality score with reasons.
Q: Injection?
A: Flags prompt-injection patterns.
Q: CI?
A: Yes — --json, non-zero on failure.
Q: Offline?
A: Yes.
Built and maintained by @itsPremkumar (Chennai, India · serving developers worldwide). Free for individuals and teams everywhere. Documentation in English; tool output is locale-neutral.
# .github/workflows/verify.yml
name: Verify
on: [push]
jobs:
verify:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Self-test prompt-lint
run: python prompt_lint.py self-test
Free + MIT-0 (free, modifiable, no attribution required). Sponsor if useful:
⭐ Star on GitHub