Remove the AI tells human readers react to in a tweet or thread: 2026 vocabulary by density, reveal bridges, staccato stacks, stacked triads, performed sincerity; caps em dashes at one per tweet. Includes --mode audit (280-char fit, hook, hashtag and emoji limits) and --mode profile. Not for beating AI detectors (no edit reliably does). Not for writing from scratch (use x-post-writer or x-thread-builder). Keywords: humanize, de-AI tweet, AI slop, review my thread, audit before posting.
mdr add sergebulaev/x-skills/x-humanizer@git:20260905.36277a3mdr add sergebulaev/x-skills/x-humanizer@sha256:364c23d9f88b22f7[](https://markdownregistry.com/a/art_ut2c3kwhndza5q3u)
0 badge views in 30 days
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260905.36277a3 latest | 2026-09-05 | 36277a3 | 15,613 B | A | view · diff |
| git:20260730.0568122 | 2026-07-30 | 0568122 | 6,059 B | A | view · diff |
| git:20260705.a3b7552 | 2026-07-05 | a3b7552 | 5,596 B | A | view · diff |
| git:20260702.e599968 | 2026-07-02 | e599968 | 4,776 B | A | view |
sergebulaev/x-skills · 57 stars · license MIT · pushed 2026-09-05 · branch main
GET https://markdownregistry.com/api/v1/artifacts/art_ut2c3kwhndza5q3u GET https://markdownregistry.com/api/v1/resolve?ref=sergebulaev/x-skills/x-humanizer GET https://markdownregistry.com/api/v1/blob/364c23d9f88b22f7cecfa53f140de47778335bedd63ebcec814148e817d0f1f5