Remove AI writing patterns and formatting artifacts from text. Preserves author voice. Use for articles, posts, content that must not look AI-generated.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Humanize — Remove AI Fingerprints from Text
You are a meticulous human editor whose job is to make text read as if a real person wrote it from scratch. You work with both English and Russian texts.
**Core principle**: Do not rewrite the text. Surgically remove AI patterns while keeping the author's message, structure, and intent intact. The result should feel like a polished draft by a skilled human writer, not a sanitised AI output.
## Input
The user provides `$ARGUMENTS` — path to the file. If no path is given, ask for it.
## Workflow
### Phase 0: Setup
1. Read the source file.
2. Detect the primary language (English, Russian, or mixed).
3. Save a backup next to the original: `{name}.backup-{timestamp}.{ext}`.
4. Create a working copy at `/tmp/humanize-{timestamp}/draft.{ext}`.
### Phase 1: AI Pattern Scan
Scan the text and produce a diagnostic report. Flag every instance of the patterns below.
Save the report to `/tmp/humanize-{timestamp}/scan-report.md` with counts per category.
---
#### A. Banned Vocabulary (ALWAYS replace)
**English Tier 1 — replace on sight:**
| AI word/phrase | Use instead |
|---|---|
| delve | explore, dig into, look at |
…
The line at the top of this page pins the label git:20261004.8dfccd1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_feto6gdlhr75goj5
GET https://markdownregistry.com/api/v1/resolve?ref=arcanada-one/datarim/humanize
GET https://markdownregistry.com/api/v1/blob/46b2b3b7360718108b1008a94e170fa43a016670f150fae01955e78dec9642d2
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
arcanada-one/datarim · plugins/product-discovery/skills/decision-record/SKILL.md · Record bounded product decisions with counterevidence, uncertainty, and explicit reversal conditions.
arcanada-one/datarim · plugins/product-discovery/skills/hypothesis-validation/SKILL.md · Use when a product decision depends on an uncertain claim and needs a bounded, falsifiable check.
arcanada-one/datarim · skills/adversarial-review/SKILL.md · Forces an adversarial mindset on a plan, PRD, design, or code change — break it rather than bless it. Loaded at the…
arcanada-one/datarim · skills/brainstorming/SKILL.md · MUST use this before any creative work — features, components, functionality, behavior changes. Explores user intent…
arcanada-one/datarim · skills/consilium/SKILL.md · Assemble a panel of Datarim agents for multi-perspective analysis of decisions. Use for /dr-design stage (L3-4) or…
epoko77-ai/im-not-ai · skills/humanize/SKILL.md · AI가 쓴 한글 텍스트를 자연스럽게 윤문하는 진입 명령. humanize-korean 파이프라인을 shim 의 route_hint 가 정한 경로(light 1콜 · standard 2콜 · heavy 3+콜)로…
pedrohcgs/claude-code-my-workflow · .claude/skills/humanize/SKILL.md · Read-only audit of `.tex`, `.qmd`, or `.md` text for AI-voice tells — boilerplate transitions ("Moreover"…
fcakyon/claude-codex-settings · plugins/humanize/skills/humanize/SKILL.md · This skill should be used when writing or revising text, including responses, documentation, comments, emails, posts…
aperivue/medsci-skills · skills/humanize/SKILL.md · Use when a manuscript or response-to-reviewers letter reads as AI-written. Scans for 27 AI writing patterns and…
mathews-tom/armory · skills/humanize/SKILL.md · Detects and removes AI-generated writing patterns while preserving meaning and facts, using a deterministic scan and…
uchicago-dsi/ai-sci-skills · skills/humanize/SKILL.md · Edit prose so it sounds like the author and reads plainly - stripping formulaic AI phrasing and replacing jargon with…
kalyvask/winning-writing · skills/humanize/SKILL.md · Makes a draft read like a real human typed it — adds asymmetry, light contractions, and (rarely) one safe typo. Use…
