# hardikpandya/stop-slop

A skill file for removing AI tells from prose

Repository: https://github.com/hardikpandya/stop-slop
Canonical: https://ross.abutalabs.com/products/stop-slop
License: MIT
License Family: permissive
Last push: 2026-03-17T18:50:39+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 72, release rhythm 35, longevity 16
- inputs: {"age_days": 234, "days_push": 169, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 16437, forks 1174 (observed 2026-08-28T04:11:16.309093+00:00)

## What it is
A skill file (SKILL.md plus reference documents) that teaches Claude or any LLM to detect and remove AI writing patterns from prose. It includes banned phrase lists, structural cliché rules, sentence-level rules, and a scoring rubric for revision.

## Use cases
- remove AI tells from my writing
- make LLM-generated text sound more human
- set up a Claude skill for editing prose
- check if my article reads like AI slop
- add style rules to my system prompt for writing tasks
- score and revise text for directness and rhythm

## When to choose
- you use Claude Code, Claude Projects, or the Claude API and want AI-sounding prose cleaned up
- you want a ready-made prompt/skill for editing AI-generated writing
- you need a concrete checklist of AI writing patterns and a scoring rubric

## When to avoid
- you need a standalone text-processing tool or library with programmatic APIs
- you want automated grammar or spell checking
- you don't use LLMs and need deterministic style linting

## Facets
- artifact type: learning-resource
- maturity: active
- function: nlp, prompt-engineering, llm-inference
- domain: large-language-models, developer-tools, tutorials
- platform: cross-platform
- tags: skill-file, ai-writing, prose-editing, claude, writing-style, prompting, natural-language-processing

## Member repositories
- hardikpandya/stop-slop (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:16.309093+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:05:06.486908+00:00, confidence not recorded.
  - readme: https://github.com/hardikpandya/stop-slop (fetched 2026-08-28T04:11:16.309093+00:00, sha d5c699e712e6)
- Data as of 2026-08-30T08:39:29.467469+00:00.