mcpField
U
unslop

unslop

github.com/mshumerAgent workflows55345 installsUpdated 32w ago
Repository

About unslop

unslop is a skill for analyzing text or visual samples in a domain and generating a profile to reduce repetitive AI defaults. It produces an analysis and a reusable skill file, with visual runs also allowing before-and-after review.

Key features

  1. 01Domain-specific pattern analysis
  2. 02Text and visual modes
  3. 03Generated analysis.md and skill.md
  4. 04Visual before-and-after comparison

Use cases

  1. 01Identify repetitive phrasing in domain writing
  2. 02Review generic patterns in website samples
  3. 03Create guidance for avoiding recurring defaults

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/mshumer/unslop --skill unslop

After installing, type/unslopin Claude Code to confirm it loaded.

Details

From the project README

unslop

Use this repo to generate a domain-specific profile that removes repetitive AI defaults.

Workflow

  1. Clone https://github.com/mshumer/unslop if the repo is not already present.
  2. Enter the repo root and use a Python virtual environment.
  3. Decide whether the job is text or visual. Text: writing, emails, essays, tutorials, copy, code explanations. Visual: websites, landing pages, HTML pages, UI mockups.
  4. Install Playwright only for visual runs: pip install playwright && playwright install chromium
  5. Run the tool: python3 unslop.py --domain "<domain>" python3 unslop.py --domain "<domain>" --type visual --count 20 --concurrency 3

Output Review

Check unslop-output/analysis.md and unslop-output/skill.md.

  • analysis.md must be concrete, counted, and specific.
  • skill.md should mostly say what to avoid, not prescribe one new stock style.
  • For visual runs, compare unslop-output/before-after/before.html and unslop-output/before-after/after.html.
  • The after result should feel meaningfully less generic than before.

If the analysis is thin or obviously missed repeated patterns, rerun or rewrite the analysis from inside unslop-output after reviewing the screenshots and sample files directly.

Deliverable

Return:

  • The generated skill.md
  • The main repeated patterns the analysis found
  • Any caveats about sample quality, missing screenshots, or weak comparison output

Comments

Markdown supported