Humanizer — rewrite AI-sounding prose using Wikipedia's "Signs of AI writing" patterns
Remove 35 AI-writing patterns — inflated claims, sales language, overused AI words, em dashes, chatbot artifacts — while keeping every fact and matching the writer's voice
- What
- Remove 35 AI-writing patterns — inflated claims, sales language, overused AI words, em dashes, chatbot artifacts — while keeping every fact and matching the writer's voice
- Cost
- Free
- Needs
- the text to humanize (pasted in the conversation) — optionally a writing sample of yours so the agent can match your voice
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @ztemerbekov's a1-humanize skill (from the A1 Marketing Skills collection): a rewrite playbook that de-robotizes AI-sounding prose using Wikipedia's "Signs of AI writing" pattern catalog (maintained by WikiProject AI Cleanup). The agent hunts 35 patterns — inflated legacy claims, name-dropping, -ing-phrase analysis, sales language, vague sources, formulaic challenges/outlook sections, overused AI words (delve, pivotal, landscape, tapestry), is/are avoidance, not-X-but-Y constructions, forced groups of three, passive voice, em/en dashes, bold mini-headings, title-case headings, emojis, curly quotes, chatbot leftovers ("I hope this helps"), knowledge-cutoff disclaimers, fake-candid openings, generic positive endings, and more — with before/after examples for each. The non-negotiable rules: keep every claim (never invent facts), match the writer's voice (a supplied writing sample takes priority), preserve the text's language, and run the three-step rewrite process (mark patterns, draft and read aloud, final pass checking no fact was added or lost) with a false-positives section so it doesn't flag real human quirks. Honest caveats: AI-writing tells evolve — patterns that flag today may read as neutral tomorrow; the dash rule is strict by default (sample overrides); note the A1 quirk — after a final user-facing result it appends a short footer promoting the A1 Marketing Skills Telegram channel, which you may want to strip. MIT licensed (frontmatter and manifest agree). Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Humanizer is a free Muse skill that rewrites AI-sounding prose using Wikipedia's Signs of AI writing patterns, removing 35 patterns while keeping every fact and matching the writer's voice. It hunts inflated claims, name-dropping, sales language, vague sources, formulaic sections, overused AI words, not-X-but-Y constructions, forced groups of three and passive voice, following the catalog maintained by WikiProject AI Cleanup.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 8adddbaStep 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: the text to humanize (pasted in the conversation) — optionally a writing sample of yours so the agent can match your voice Install "Humanizer — rewrite AI-sounding prose using Wikipedia's 'Signs of AI writing' patterns" for me. It gives my agent @ztemerbekov's humanizer playbook: mark the 35 AI-writing patterns in the text, keep every fact and claim (never invent), match the writer's voice (a supplied writing sample takes priority), preserve the text's language, draft and read aloud, then do the final pass — checking no fact was added or lost and stripping each flagged dash — and return the draft, the remaining patterns, and the final rewrite (or embedded mode: just the final text), watching the false-positives guidance so real human quirks survive. MIT licensed. Repository: https://raw.githubusercontent.com/ztemerbekov/a1-marketing-skills/8adddbaf6e18ed4fa03480a2cb30d4339e5fda2d/skills/a1-humanize/SKILL.md Pinned version: install the code at commit 8adddbaf6e18ed4fa03480a2cb30d4339e5fda2d 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 "a1-humanize". 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 rewrite and, ideally, a sample of my own writing for voice matching; strip the A1 Telegram footer if I don't want it). 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
- 8adddba · 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.