fuck-slop
Fuck Slop detects and removes the statistical fingerprints of AI writing—negative parallelism, em-dash abuse, false ranges, puffery, and metronomic cadence—then rewrites the text to sound like a real person with a real point. It scans, diagnoses, rewrites by meaning rather than pattern, and re-scans until clean, ensuring the result reads naturally in its target register.
Fuck Slop removes AI writing tells and rewrites text to sound authentically human in any genre.
AI-generated summary based on this skill's SKILL.md
Install
JuliusBrussee/skills/fuck-slop · repository language: JavaScript
git clone https://github.com/JuliusBrussee/skills
cp -r skills/skills/fuck-slop ~/.claude/skills/fuck-slopnpx skillfed install JuliusBrussee/skills/fuck-slopFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does Fuck Slop remove AI writing patterns from text?
Fuck Slop detects and removes the statistical fingerprints of AI writing—negative parallelism, em-dash abuse, false ranges, puffery, and metronomic cadence—then rewrites the text to sound like a real person with a real point. It scans, diagnoses, rewrites by meaning rather than pattern, and re-scans until clean, ensuring the result reads naturally in its target register.
What specific AI tells does Fuck Slop fix in my writing?
Fuck Slop targets overused AI phrases like negative parallelism (not X but Y constructions), em-dash abuse, rule-of-three lists, hedging language, balanced contrasts, false ranges, and puffery vocabulary. It also eliminates metronomic cadence and other statistical markers that flag text as LLM-generated rather than authentically human.
Can Fuck Slop make text not sound like ChatGPT?
Yes. Fuck Slop is designed to humanize AI-written content by stripping AI detector red flags and rewriting prose to match your target genre and audience register. It rewrites by meaning rather than surface pattern, so the output reads like a real person with a real point, not a statistical artifact.
How does Fuck Slop verify that AI markers are actually gone?
Fuck Slop scans, diagnoses the AI fingerprints present, rewrites the text, and then re-scans iteratively until clean. This multi-pass approach ensures that statistical markers of LLM output are genuinely eliminated before you publish, rather than just masked or shuffled.
What makes Fuck Slop different from just rewriting manually?
Fuck Slop automates detection of subtle AI tells that humans often miss—statistical patterns, cadence, false ranges, and puffery that accumulate across a piece. It diagnoses what's wrong, rewrites by meaning, and verifies the fix, saving you the tedious work of hunting down every AI fingerprint yourself.
Can I use Fuck Slop to deslop my writing before posting?
Yes. Fuck Slop is built for cleaning up AI writing before publishing. Feed it your draft, and it will strip AI tells, rewrite for authenticity and genre fit, and re-scan until the text reads like a real person wrote it—ready to post without AI detector flags or statistical giveaways.
SKILL.md
rendered from the published skill — quoted content, verbatim
F*ck Slop
Strip every mark of AI writing from a text and make it good in its genre. Not "make it pass a detector" — make it read like a specific person with a specific point wrote it for a specific audience.
Why this is a loop, not a style guide
The worst tells — above all the "not X but Y" family — are not vocabulary mistakes. They are emergent properties of how LLMs generate text: preference tuning rewards balanced, contrastive, comprehensive-sounding framing, so the contrast move is baked into the model's priors. Two consequences drive this skill's
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 3 files
skills/fuck-slop/SKILL.md
skills/fuck-slop/references/tells.md
skills/fuck-slop/references/voices.md