Humanizer by blader
Hacker ApprovedRanked 15 of 23 agent skills by recommenders
People recommend it for stripping common AI writing tells like 'not x, but y' and bolded bullets. Critics say the output still reads as AI-written.
People recommend it for stripping common AI writing tells like 'not x, but y' and bolded bullets. Critics say the output still reads as AI-written.
19 people gave an opinion
- recommend it
- 13
- criticize it
- 6
- approval share
- 68%
Recommended in 7 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 13 people recommend itNeeds 10 or more, met.
- 2.2 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 7 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Removes common LLM writing tells
“it's relatively easy to screen out "it's not x it's y" kind of things and the bolded bullet points”
Comment from 21 May 2026 in “Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)” “Skills like Humanizer and avoid-ai-writing help get rid of some of the worst memes”
Comment from 11 Oct 2026 in “Sorry, I'm in a meeting” “a skill that helps avoid some of the common LLM tells”
Comment from 24 Feb 2026 in “The Engine Behind the Hype” - Comment from 17 Jun 2026 in “Skill to Ensure Claude Code Uses No Em Dashes”
Useful for cleaning up writing
“I use the humanize skill to clean up AI written work before handing it over to colleagues.”
Comment from 14 Jul 2026 in “How to stop Claude from saying load-bearing” “It's also very useful in writing skills to help avoid these kinds of issues.”
Comment from 19 Jan 2026 in “Wikipedia: WikiProject AI Cleanup” Fits existing Claude Code setups
“I also incorporated the humanizer[2] skill into it.”
Comment from 19 Oct 2026 in “Show HN: Qwen3-4B with the AI writing tics trained out” “Here's a Claude code skill for that”
Comment from 18 May 2026 in “Don't Outsource the Learning”
What people warn about
Each mark is one comment
Output still sounds like AI
“When you read the full output example in that repo, it seems obvious to me that it's AI”
Comment from 21 Aug 2026 in “I'm Becoming AI-Blind” “This is what I got first time with a humanizer I built, still sounds terrible”
Comment from 23 Jul 2026 in “Launch HN: Unlayer (YC W22) – Add email and document builders to your app” “How to make your LLM slop sound like slightly different LLM slop.”
Comment from 22 Oct 2026 in “39-humanizer, for anyone under 40 who would rather not sound like a bot” Extra AI pass doesn't solve it
“Hiding these clues by another AI pass doesn't solve the core problem.”
Comment from 21 May 2026 in “Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)” “making it use random out of band non thinking tokens”
Comment from 22 May 2026 in “Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)”
Other agent skills people recommend
The four most recommended other agent skills, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Superpowers | 138 | 72 | 66% | 12 | 4 mo7 owners | — |
| Claude Skills | 59 | 26 | 69% | 11 | — | Approved |
| grill-me skill by Matt Pocock | 39 | 2 | 95% | 8 | — | Approved |
| Get Shit Done | 31 | 32 | 49% | 7 | — | — |
| Humanizer by bladerThis page | 13 | 6 | 68% | 7 | — | Approved |
What people said
17 of the 21 comments that mention it, newest first. Each links to the original comment.
“How to make your LLM slop sound like slightly different LLM slop.”
“I also incorporated the humanizer[2] skill into it.”
“Skills like Humanizer and avoid-ai-writing help get rid of some of the worst memes”
“When you read the full output example in that repo, it seems obvious to me that it's AI”
“This is what I got first time with a humanizer I built, still sounds terrible”
“I use the humanize skill to clean up AI written work before handing it over to colleagues.”
“Just says "Oops something went wrong!"”
“it removes many "claude-isms"”
“making it use random out of band non thinking tokens”
“Someone else shared this project which would be really helpful”
“Hiding these clues by another AI pass doesn't solve the core problem.”
“Thanks for this! This is exactly what I was looking for.”
“it's relatively easy to screen out "it's not x it's y" kind of things and the bolded bullet points”
“Here's a Claude code skill for that”
“a skill that helps avoid some of the common LLM tells”
“technically impressive but socially a bit tricky”
“It's also very useful in writing skills to help avoid these kinds of issues.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.