/deslop

name: deslop
description: "Detect and remove the telltale signs of AI-generated 'slop' from any written text - articles, reports, emails, essays, bios, marketing copy, documentation, encyclopedia entries, or anything meant to read as if a thoughtful human wrote it. Apply silently as a quality gate before finalizing substantial prose, and explicitly when asked to clean a draft. TRIGGER when the user says 'make this sound less like AI', 'remove the AI tells', 'de-slop this', 'check if this reads as AI-written', 'make it sound human', 'edit out the ChatGPT voice', or critiques a draft as generic, puffy, or robotic. Based on Wikipedia's 'Signs of AI writing' field guide."

Deslop: removing the signs of AI writing

LLMs have an identifiable writing style. Left unchecked, AI prose regresses toward the statistical mean: it smooths specific, unusual, verifiable facts into generic, positive, important-sounding filler. The result reads fluent but hollow - "slop." This skill is a field guide to catching and fixing those tells.

How to use this skill

There are two modes:

1. **Gate mode (default, silent).** When you are *writing* substantial prose, self-check the draft against the patterns below before presenting it. Don't announce that you're doing this; just produce clean output. 2. **Audit mode (explicit).** When the user gives you text and asks you to de-slop it, critique it, or check whether it sounds AI-written, scan against every category, then either (a) return an edited version, or (b) return a findings list with specific quoted offenders and fixes - match whatever the user asked for.

For a full audit of an external file, read `references/full-checklist.md` for the exhaustive pattern list with examples. The summary below covers the high-frequency offenders that catch ~90% of slop.

Critical mindset

• **The patterns are signals, not crimes.** Humans write some of these too (blogs, editorials, press releases). The presence of one phrase doesn't condemn a text; a *cluster* of them is the tell. Don't mechanically purge every "however."
• **Fixing the surface tic is not the goal - fixing the underlying emptiness is.** Deleting the word "underscores" while leaving a sentence that says nothing just makes the slop harder to detect. If a sentence only puffs up significance and carries no fact, cut the whole sentence, don't reword it.
• **Specificity is the antidote.** The core failure of slop is vagueness masquerading as importance. Replace "a revolutionary titan of industry" with "inventor of the first train-coupling device." When you can't add a real fact, delete the claim.
• **Leave the human markers alone.** The source records what is *more* common in human text than in AI text: plain "there is" / "it has" phrasing, plain verbs (*wrote, moved, used, tried, died* over *authored, relocated, utilized, attempted, passed away*), definite claims when true ("was the first," "is the only"), natural qualifiers (*very, perhaps, tends to*), and the odd wordy phrase ("in order to," "the fact that"). An edit pass that "tightens" these pushes prose toward the AI register. Don't strip them, and don't sprinkle them in either - they are byproducts of a person writing, not ingredients. A definite claim you can't verify stays as written and goes on the list of things for the author to confirm; softening it to "one of the first" is a guess in the other direction.

The high-frequency tells

1. Puffery: inflated significance and promotional tone

AI inflates importance by asserting that the subject represents some broader trend or leaves a lasting mark - even for mundane subjects. The same reflex produces advertisement or travel-guide prose where a neutral writer would just describe the thing.

> Watch words (significance): *stands/serves as, is a testament/reminder, plays a vital/significant/crucial/pivotal/key role, underscores/highlights its importance, reflects broader, symbolizing its enduring/lasting, contributing to the, setting the stage for, marking a shift, key turning point, evolving landscape, focal point, indelible mark, deeply rooted, rich cultural heritage.*

> Watch words (promotion): *boasts a, vibrant, rich, profound, nestled, in the heart of, groundbreaking, renowned, diverse array, commitment to, natural beauty, exemplifies, showcasing.*

Current models are subtler than older ones: they avoid "the best" and stay faintly positive throughout. Look for a tone no neutral writer would hold, not only for superlatives.

**Fix:** Delete the significance claim, or replace it with the specific fact that would justify it. "The 1989 founding marked a pivotal moment in the evolution of regional statistics" → "It was founded in 1989." "Nestled in the heart of the region, the town boasts a vibrant market" → "The town has a weekly market." If there's a real reason it mattered, state that reason concretely.

2. Superficial analysis tacked onto sentence ends

A trailing present-participle ("-ing") phrase that editorializes about significance, impact, or implication - often a synthesis the sources don't support.

> Watch words: *highlighting/underscoring/emphasizing…, ensuring…, reflecting/symbolizing…, contributing to…, fostering…, cultivating…, encompassing…, enhancing…, valuable insights, aligning/resonating with…*

> "Douera enjoys close proximity to the capital, **further enhancing its significance as a dynamic hub of activity and culture.**"

**Fix:** Amputate the trailing clause. The factual half of the sentence usually stands fine alone.

3. Indirection: dodging "is," "has," and the plain relationship

Two habits with one cause - reaching past the simple verb. **Copula avoidance:** *serves as / stands as / marks / represents / functions as / operates as* where "is" would do; *boasts / features / offers / maintains* where "has" would do; in newer output, longer forms such as "ventured into politics as a candidate" for "was a candidate." **Vague connection:** *associated with,