DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to remove AI tone from a work email without changing its commitments with Work Humanizer

Rewrite an AI-drafted sales, support or HR message in a plain voice with every fact kept.

Who it is forA 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 problemCommon AI rewrites apologize where you only acknowledged, add conditions to offers and blame the customer, which changes what you commit to.

The outcomeA rewritten message in a plain human voice, with a sentence-by-sentence fact audit that lists what stayed the same.

What you need first

  • An agent that loads SKILL.md, such as Claude Code, Codex or Cursor
  • The skills/work-humanizer folder copied into the agent's skills folder
  • Your draft or notes as text
  • Python, only if you want to run check.py

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 for your agent

Using the work-humanizer skill from the phuryn/work-humanizer repo, rewrite the AI-drafted email in <draft-file> 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.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page