{"slug": "humanizer", "name": "humanizer", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 4, "commenters": 4, "warners": 0, "score": 3.745, "rising": 0.02, "first": "2026-05-21", "latest": "2026-10-19", "why": "I use the humanize skill to clean up AI written work before handing it over to colleagues.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 0, "compare": 0, "warn": 0}, "spark": [0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 1], "listed": true, "loved": [], "caveat": "", "short_quote": "I use the humanize skill to clean up AI written work before handing it over to colleagues.", "icon": true, "domain": null, "github_repo": "github.com/blader/humanizer", "official_url": "https://github.com/blader/humanizer", "pricing": "", "aliases": ["humanizer"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 802450305, "item_id": 50153144, "url": "https://news.ycombinator.com/item?id=50153144", "by": "jamesponddotco", "date": "2026-10-19", "stance": "recommend", "quote": "I also incorporated the humanizer[2] skill into it.\n\nWorked like a charm.", "excerpt": "I gave Claude several pieces of writing from myself, from notes to code comments to iMessage messages with my wife[1], and asked it to write skills that match my voice. I also incorporated the humanizer[2] skill into it. Worked like a charm. This is the prompt I used[3] to write a version for the company I own with my wife, if it helps anyone. The personal version, which lead to the `jamenizer` skill, is very similar", "context": "", "use_case": "remove AI writing tics", "switched_from": "", "story": "Show HN: Qwen3-4B with the AI writing tics trained out"}, {"id": 782596944, "item_id": 48912309, "url": "https://news.ycombinator.com/item?id=48912309", "by": "3uler", "date": "2026-07-14", "stance": "recommend", "quote": "I use the humanize skill to clean up AI written work before handing it over to colleagues.", "excerpt": "Your tells, are just someone\u2019s good writing now in the training set. It\u2019ll be a moving target with each model. I use the humanize skill to clean up AI written work before handing it over to colleagues. https://github.com/blader/humanizer", "context": "", "use_case": "cleaning up AI-written text", "switched_from": "", "story": "How to stop Claude from saying load-bearing"}, {"id": 777118544, "item_id": 48569909, "url": "https://news.ycombinator.com/item?id=48569909", "by": "bearjaws", "date": "2026-06-17", "stance": "recommend", "quote": "this is probably the better solve as it removes many \"claude-isms\"", "excerpt": "https://github.com/blader/humanizer this is probably the better solve as it removes many \"claude-isms\"", "context": "", "use_case": "removing Claude-isms from output", "switched_from": "", "story": "Skill to Ensure Claude Code Uses No Em Dashes"}, {"id": 771625553, "item_id": 48226597, "url": "https://news.ycombinator.com/item?id=48226597", "by": "asenna", "date": "2026-05-21", "stance": "recommend", "quote": "Someone else shared this project which would be really helpful", "excerpt": "Tbh, I did spend a lot of time trying to ground it and de-slopify it - verified nothing was halucinated and went through 10 iterations to get to this. It's almost like wrestling with Claude and I knew it would be tough on HN. But because of the fear of non-perfection, I used to put away things like creating this article or even posting it anywhere. And I do think the article has real value that HN would appreciate (I", "context": "", "use_case": "de-slopifying writing", "switched_from": "", "story": "Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["remove ai writing tics", "cleaning up ai-written text", "removing claude-isms from output", "de-slopifying writing"], "compared": [{"slug": "claude", "name": "Claude", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=50151928", "title": "Show HN: Qwen3-4B with the AI writing tics trained out", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48905248", "title": "How to stop Claude from saying load-bearing", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48569781", "title": "Skill to Ensure Claude Code Uses No Em Dashes", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48222733", "title": "Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {"recommend": 1}, "2026-06": {"recommend": 1}, "2026-07": {"recommend": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {"recommend": 1}}, "quotes": [{"id": 802450305, "item_id": 50153144, "url": "https://news.ycombinator.com/item?id=50153144", "by": "jamesponddotco", "date": "2026-10-19", "stance": "recommend", "quote": "I also incorporated the humanizer[2] skill into it.\n\nWorked like a charm.", "excerpt": "I gave Claude several pieces of writing from myself, from notes to code comments to iMessage messages with my wife[1], and asked it to write skills that match my voice. I also incorporated the humanizer[2] skill into it. Worked like a charm. This is the prompt I used[3] to write a version for the company I own with my wife, if it helps anyone. The personal version, which lead to the `jamenizer` skill, is very similar", "context": "", "use_case": "remove AI writing tics", "switched_from": "", "story": "Show HN: Qwen3-4B with the AI writing tics trained out"}, {"id": 782596944, "item_id": 48912309, "url": "https://news.ycombinator.com/item?id=48912309", "by": "3uler", "date": "2026-07-14", "stance": "recommend", "quote": "I use the humanize skill to clean up AI written work before handing it over to colleagues.", "excerpt": "Your tells, are just someone\u2019s good writing now in the training set. It\u2019ll be a moving target with each model. I use the humanize skill to clean up AI written work before handing it over to colleagues. https://github.com/blader/humanizer", "context": "", "use_case": "cleaning up AI-written text", "switched_from": "", "story": "How to stop Claude from saying load-bearing"}, {"id": 777118544, "item_id": 48569909, "url": "https://news.ycombinator.com/item?id=48569909", "by": "bearjaws", "date": "2026-06-17", "stance": "recommend", "quote": "this is probably the better solve as it removes many \"claude-isms\"", "excerpt": "https://github.com/blader/humanizer this is probably the better solve as it removes many \"claude-isms\"", "context": "", "use_case": "removing Claude-isms from output", "switched_from": "", "story": "Skill to Ensure Claude Code Uses No Em Dashes"}, {"id": 771625553, "item_id": 48226597, "url": "https://news.ycombinator.com/item?id=48226597", "by": "asenna", "date": "2026-05-21", "stance": "recommend", "quote": "Someone else shared this project which would be really helpful", "excerpt": "Tbh, I did spend a lot of time trying to ground it and de-slopify it - verified nothing was halucinated and went through 10 iterations to get to this. It's almost like wrestling with Claude and I knew it would be tough on HN. But because of the fear of non-perfection, I used to put away things like creating this article or even posting it anywhere. And I do think the article has real value that HN would appreciate (I", "context": "", "use_case": "de-slopifying writing", "switched_from": "", "story": "Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)"}]}