sloptrim — плагин

---
name: sloptrim
description: >-
  Use when the user wants to humanize text, trim slop, de-AI or de-slop writing,
  remove AI tells, fix robotic or ChatGPT-sounding prose, or make writing sound
  human and natural. Also run before delivering a CV, cover letter, email,
  report, or essay to be sent. Removes 71 documented AI-writing patterns with a
  local detector, preserves numbers, names and citations, and rebuilds toward a
  human voice rather than a flat husk. Mode-aware, so it never fabricates voice
  on factual content.
version: 0.9.6
license: Apache-2.0
allowed-tools: Read, Write, Edit, Grep, Glob, Bash
argument-hint: The text to trim, or a file path
---

# Sloptrim

Trims AI slop from text. Works a catalogue of 71 patterns: 62 machine-checked by `scripts/detect.py`, 9 requiring semantic judgment during the rewrite. Of the 62, 50 can move the score; the rest are reported as writing advice and count for nothing. Mode-aware so it does not invent voice on factual content. Preserves facts. Rebuilds the cleaned text toward a selectable human-voice **style profile** so it does not read as a sterile de-AI'd husk.

## Silence

This skill never talks about itself. It hands back the cleaned text and nothing else.

**Never emit:** any announcement that sloptrim ran, style/mode lines, scores or reports, drafts, self-audit notes, facts-preserved lines, change lists, preambles, closing offers.

**Emit only:**
- Text given inline: the final text. Nothing before it, nothing after it.
- A file path given: rewrite the file in place, then one line - the path. Nothing else.
- Fired as a pre-delivery pass on something you were already writing (CV, cover letter, email, report, essay): just deliver the clean text. Do not mention that a pass happened.

Every internal step still runs - detector, tiering, self-audit, character scrub. Silence means nothing is *printed*, not that anything is skipped.

Break silence only for: (a) a fact you cannot preserve, or an unusual word you cannot verify against the domain - one line, then the text; (b) the user explicitly asking for the score, the report, a style choice, or a diff - then answer in full; (c) a **high-stakes first-person deliverable** - a cover letter, personal statement, or bio the user is about to send - where after the text you may add exactly one line offering a voice switch (for example: "Voice here is plain-professional; say the word for warmer or more formal."). One line, only for these high-stakes cases, never for routine prose.

## Style, chosen silently

Never ask. Read the content and pick:

- encyclopedic / factual / technical → **2000s textbook**
- first-person / opinion → **conversational essay**
- docs, README, business prose → **plain / clear**
- news → **journalistic**

If the user names a style or pastes a writing sample, that wins (see *Matching the user's own voice*).