# AI use cases for Work Humanizer (phuryn/work-humanizer) Repo: [phuryn/work-humanizer](https://github.com/phuryn/work-humanizer) | Use cases: 3 | Page: https://dedupedai.com/use-cases/phuryn-work-humanizer/ work-humanizer is an Agent Skill that removes AI tone from work writing while keeping every fact, commitment and caveat at the same strength. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Remove AI tone from a work email without changing its commitments: https://dedupedai.com/use-cases/phuryn-work-humanizer/humanize-ai-work-email/ - Get a specific work draft built from your answers, not guesses: https://dedupedai.com/use-cases/phuryn-work-humanizer/interview-before-rewriting-generic-draft/ - Turn your notes or transcript into a human-sounding work piece: https://dedupedai.com/use-cases/phuryn-work-humanizer/turn-own-notes-into-human-piece/ ## How to remove AI tone from a work email without changing its commitments with Work Humanizer Repo: [phuryn/work-humanizer](https://github.com/phuryn/work-humanizer) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Rewrite an AI-drafted sales, support or HR message in a plain voice with every fact kept. **Who it is for:** A sales rep or support agent who has an AI draft of a customer email that reads as machine-written and contains offers, dates or promises that must not change. **The problem:** Common AI rewrites apologize where you only acknowledged, add conditions to offers and blame the customer, which changes what you commit to. **The outcome:** A rewritten message in a plain human voice, with a sentence-by-sentence fact audit that lists what stayed the same. ### Steps 1. Copy the skills/work-humanizer folder into your agent's skills folder, for example ~/.claude/skills/work-humanizer for Claude Code. 2. Start a session in your agent and send: Use Work Humanizer on this: followed by the pasted draft. 3. Read the rewrite and the fact audit side by side with the original. 4. Confirm every price, date, offer, condition and caveat has the same strength as in the original. 5. Optionally run `python skills/work-humanizer/check.py draft.md` on the saved rewrite as a last mechanical check. ### Prompt to paste into your agent ```text Using the work-humanizer skill from the phuryn/work-humanizer repo, rewrite the AI-drafted email in in a plain human voice. Output the rewrite and the sentence-by-sentence fact audit. Verify that every price, date, offer, condition and caveat in the rewrite matches the original in meaning and strength. ``` ### Caveat The README reports small test samples and AI judges, so the fact audit is the step to rely on, not the reported win rates. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/phuryn-work-humanizer/humanize-ai-work-email/ ## How to get a specific work draft built from your answers, not guesses with Work Humanizer Repo: [phuryn/work-humanizer](https://github.com/phuryn/work-humanizer) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Answer a few questions so the rewrite contains your real example, number or outcome. **Who it is for:** A manager or account lead with a generic AI draft that could have been written from any one-line request and lacks the facts only they know. **The problem:** No edit can add a real example, a number or what the writer actually thinks, so a rewrite alone often papers over the gap or invents details. **The outcome:** A piece built from your answers, with gaps left to you rather than filled with made-up facts. ### Steps 1. Copy the skills/work-humanizer folder into your agent's skills folder if you have not already. 2. Send: Use Work Humanizer on this and interview me first: followed by the draft. 3. Answer up to five short questions, phrased as you would say them out loud. 4. Review the finished piece and confirm each fact it uses came from your answers or the original draft. ### Prompt to paste into your agent ```text Use the work-humanizer skill from the phuryn/work-humanizer repo in interview mode on . Ask up to five questions, then output the rewritten piece built only from my answers and the draft. Verify that the output contains no facts that appear in neither my answers nor the draft. ``` ### Caveat The interview was tested only with a simulated writer, so how well it works with real people is untested according to the README. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/phuryn-work-humanizer/interview-before-rewriting-generic-draft/ ## How to turn your notes or transcript into a human-sounding work piece with Work Humanizer Repo: [phuryn/work-humanizer](https://github.com/phuryn/work-humanizer) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Build a post or memo on your own argument, order and examples instead of an AI draft. **Who it is for:** A team lead or founder with rough notes or a voice-memo transcript who needs a launch post, update or internal memo that sounds like them. **The problem:** AI drafts flatten a person's reasoning, and the test found the most human results came from the writer's own notes. **The outcome:** A piece that keeps your claims, their order and your examples, with questions only where your notes leave gaps. ### Steps 1. Copy the skills/work-humanizer folder into your agent's skills folder if you have not already. 2. Send: Use Work Humanizer on this: followed by your notes or transcript pasted in. 3. Check the skeleton it builds from your claims and examples, and answer any questions about gaps. 4. If it offers a shorter option, decide whether to use it, since it never cuts on its own. 5. Read the final fact audit and confirm nothing from your notes was dropped or strengthened. ### Prompt to paste into your agent ```text Use the work-humanizer skill from the phuryn/work-humanizer repo on my notes in . Build the piece on my claims, in my order, with my examples, and ask only about gaps. Output the piece and the fact audit. Verify that each claim in the piece matches a claim in my notes at the same strength. ``` ### Caveat The README says that rewriting an AI draft on its own still lands near the same AI detector scores, so the gain comes from your own reasoning, and the detector results rest on 4 texts for the notes case. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/phuryn-work-humanizer/turn-own-notes-into-human-piece/