ste80-humanizer Rewrites AI Text Toward Controlled English
A developer released ste80-humanizer, a free MIT-licensed skill for Claude Code that rewrites text in two passes: removing common AI-writing tells and rebuilding it with short sentences, one idea per sentence, and active voice. The author says it also works with Codex and Cursor, based on Andrej Karpathy's “80% of the way to ASD-STE100” approach. Installation involves cloning the Dodaios/ste80-humanizer repository and adding its skill folder to the Claude Code skills directory.
The release provides a reusable open-source workflow for making AI-assisted technical writing clearer and more consistent, although its output quality and cross-tool compatibility remain self-reported.
I built a free, open-source skill for Claude Code (also works with Codex and Cursor) based on Karpathy's tip: ask LLMs to write "80% of the way to ASD-STE100", the controlled English used in aircraft maintenance manuals.
**What it does**
It rewrites text in two passes:
- Remove the 26 AI tells from Wikipedia's "Signs of AI writing"
- Rebuild the text in STE style: short sentences, one idea each, active voice
**Before:** "Great question! Kubernetes liveness probes are a powerful mechanism that enables the kubelet to determine whether a container is healthy — and it's not just a health check, it's your first line of defense…"
**After:** "A liveness probe tells the kubelet if a container is healthy. If the probe fails, the kubelet restarts the container."