STE80 Humanizer
Writing skill that edits AI-sounding text in two passes: first it strips the common chatbot tells, then it rewrites sentences most of the way to Simplified Technical English (short, one idea, active voice), keeping the meaning. MIT.
Test results
Run with our skill harness: the skill alone in a throwaway project, invoked by name, and the real output file checked. Skills are tested in Claude Code and Cursor only so far.
| Client | Result | Last passed | What we checked |
|---|---|---|---|
| Claude Code 2.1.296 (Claude Code) | Passed Tested 2026-11-10 | 2026-11-10 | ste80-humanizer: {'facts kept (token, 4.2, 40, March 3)': True, 'AI tells removed': True, 'no semicolons (STE 80%)': True, 'short sentences (avg <=20 words, max <=30)': True, 'draft left unchanged': True}; missing=[]; te |
| Cursor 2026.11.10-731fb78 | Passed Tested 2026-11-10 | 2026-11-10 | ste80-humanizer: {'facts kept (token, 4.2, 40, March 3)': True, 'AI tells removed': True, 'no semicolons (STE 80%)': True, 'short sentences (avg <=20 words, max <=30)': True, 'draft left unchanged': True}; missing=[]; te |
Skill version: github.com/Dodaios/ste80-humanizer @ 99bc4684 (2026-11-10).
Tested on ToolPassed badge
Maker of STE80 Humanizer? It passed in Claude Code, Cursor on 2026-11-10. Add this free badge to your README; it links back to this listing. Free, no strings: the badge never changes a result.
[](https://toolpassed.com/skills/ste80-humanizer/)Get it
The skill’s files and install instructions are in its repository: github.com/Dodaios/ste80-humanizer.
Not working?
Fixes from our own test runs: Skill not working in Claude Code? · Skill not working in Cursor?