unslop
Original：🇺🇸 English
Translated
Use this skill when you need to run the unslop repo, analyze a domain for repetitive AI defaults, generate a reusable skill file, and verify that the output is specific and materially different from the baseline.
1installs
Sourcemshumer/unslop
Added on
NPX Install
npx skill4agent add mshumer/unslop unslopTags
Translated version includes tags in frontmatterSKILL.md Content
View Translation Comparison →unslop
Use this repo to generate a domain-specific profile that removes repetitive AI defaults.
Workflow
- Clone if the repo is not already present.
https://github.com/mshumer/unslop - Enter the repo root and use a Python virtual environment.
- Decide whether the job is or
text. Text: writing, emails, essays, tutorials, copy, code explanations. Visual: websites, landing pages, HTML pages, UI mockups.visual - Install Playwright only for visual runs:
pip install playwright && playwright install chromium - Run the tool:
python3 unslop.py --domain "<domain>"python3 unslop.py --domain "<domain>" --type visual --count 20 --concurrency 3
Output Review
Check and .
unslop-output/analysis.mdunslop-output/skill.md- must be concrete, counted, and specific.
analysis.md - should mostly say what to avoid, not prescribe one new stock style.
skill.md - For visual runs, compare and
unslop-output/before-after/before.html.unslop-output/before-after/after.html - The result should feel meaningfully less generic than
after.before
If the analysis is thin or obviously missed repeated patterns, rerun or rewrite the analysis from inside after reviewing the screenshots and sample files directly.
unslop-outputDeliverable
Return:
- The generated
skill.md - The main repeated patterns the analysis found
- Any caveats about sample quality, missing screenshots, or weak comparison output