human-voice
Use when generating or rewriting reports, documentation, or any prose so it does not read as AI-written. Removes hedging, em-dash overuse, filler ("delve", "leverage", "seamless"), rule-of-three padding, bold-bullet listicles, meta-commentary, sycophancy, and vacuity, without altering facts, numbers, code, or citations. Accepts a file path or pasted text. Trigger when prose "sounds like AI" or "sounds like ChatGPT", when humanizing or de-slopping a draft, when a report, email, README or landing page reads robotic, or when drafting copy that should read human from the start. Not for translation
Why this score
Popularity score: 60/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 21, 2026 at commit 8303c479682c, with Cisco's open-source skill-scanner.
What its code does:
- Makes network requestsscripts/human_voice_linter/detector.py:133, scripts/human_voice_llm/providers.py:289 and 2 more
Web addresses in its code:
- api.anthropic.comscripts/human_voice_llm/providers.py:47
- api.cohere.aiscripts/human_voice_llm/providers.py:131
- api.deepseek.comscripts/human_voice_llm/providers.py:98
- api.fireworks.aiscripts/human_voice_llm/providers.py:124
- api.gowinston.aiscripts/human_voice_linter/detector.py:56
- api.gptzero.mescripts/human_voice_linter/detector.py:34
- api.groq.comscripts/human_voice_llm/providers.py:92
- api.mistral.aiscripts/human_voice_llm/providers.py:86
- api.openai.comscripts/human_voice_llm/providers.py:53
- api.originality.aiscripts/human_voice_linter/detector.py:41
- api.sapling.aiscripts/human_voice_linter/detector.py:48
- api.together.xyzscripts/human_voice_llm/providers.py:118
- api.x.aiscripts/human_voice_llm/providers.py:104
- generativelanguage.googleapis.comscripts/human_voice_llm/providers.py:66
- json.schemastore.orgscripts/human_voice_linter/reporting/sarif.py:33
And 1 more.
These are the sites named in the code, so it's where your data could go. It isn't a complete list: code can build addresses while it runs, and a few of these may be links rather than calls. Whatever you send also goes to the AI model you use.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This onehuman-voice stephenoffer/human-voice · Skill | 60 | ★ 41 | ≈153 always | 1mo ago |
| human-writing KKKKhazix/human-writing · Skill Both about human | 81 | ★ 4.1k | ≈85 always | 3mo ago |
| email-draft-in-voice yc-software/qm · Skill Both about voice and email | 82 | ★ 15k | ≈38 always | 16d ago |
| human-ai fabricioctelles/skills · Skill Both about human and prose | 59 | ★ 114 | ≈21 always | 16d ago |
| human-management agentscope-ai/AgentTeams · Skill Both about human | 77 | ★ 5.8k | ≈39 always | 19d ago |
| ig-human Jakeschincariol/instagram-agent-skill · Skill Both about human and em | 68 | ★ 2.0k | ≈21 always | 2mo ago |