Humanizer — detect and rewrite AI writing tells in five voice profiles
Detect 55 AI writing patterns, score 0–100, rewrite in casual/professional/technical/warm/blunt voices — pure Markdown, zero dependencies, no network calls
- What
- Detect 55 AI writing patterns, score 0–100, rewrite in casual/professional/technical/warm/blunt voices — pure Markdown, zero dependencies, no network calls
- Cost
- Free
- Needs
- prose (text, Markdown, blog post, email) to detect or rewrite — the skill is an editing methodology, not software
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @aboudjem's humanizer: an editing skill that hunts 55 documented AI writing patterns (significance inflation, superficial -ing phrases, vocabulary tells like "delve" and "tapestry", em-dash overuse, uniform sentence length, and more), scores the text 0–100, and rewrites it in one of five voice profiles — casual, professional, technical, warm, blunt. Three modes: detect (report only), rewrite (full transform with a before/after change summary), and edit (in-place Markdown editing). The guardrails are the real craft: flag pattern clusters, never isolated tells; never rewrite quoted, code, or cited content; protect non-native-English and neurodivergent prose styles; never fabricate facts. Honest caveats: it's an editor, not a verdict — the score is a signal, not proof of authorship; pure Markdown, zero dependencies, no network calls; prose only, not code. MIT licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Humanizer is an editing skill that hunts 55 AI writing patterns, inflation, -ing phrases, tells like delve and tapestry, em-dash overuse and sentence length, scores the text 0-100, and rewrites it in one of five voice profiles: casual, professional, technical, warm or blunt. Three modes: detect for report only, rewrite for transform with a change summary, and edit for fixes.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit a58df06Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: prose (text, Markdown, blog post, email) to detect or rewrite — the skill is an editing methodology, not software Install "Humanizer — detect and rewrite AI writing tells in five voice profiles" for me. It gives my agent @aboudjem's editing workflow: detect 55 AI writing patterns across content, style, communication, filler and forensic categories, score the text 0-100, rewrite it in a chosen voice (casual, professional, technical, warm, blunt) in detect/rewrite/edit modes, and apply guardrails (flag clusters not isolated tells, never rewrite quoted or code content, protect non-native and neurodivergent prose styles, never fabricate facts). Pure Markdown, zero dependencies, no network calls. MIT-licensed. Repository: https://raw.githubusercontent.com/aboudjem/humanizer-skill/a58df065367550b6ce40ff3f648335018d8e0589/skills/humanizer/SKILL.md Pinned version: install the code at commit a58df065367550b6ce40ff3f648335018d8e0589 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "humanizer". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. paste the text to detect or rewrite, or pass --file path/to/file.md with --mode edit; nothing else — it's a methodology). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- a58df06 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.