sergebulaev/threads-skills · skills/threads-humanizer/SKILL.md

threads-humanizer skillA

Remove the AI tells human readers react to in a Threads post or thread: 2026 vocabulary by density, reveal bridges, staccato stacks, stacked triads, performed sincerity; caps em dashes at one per post, never forces rhythm. Includes --mode audit (500-char fit, hook, one-hashtag cap, link placement, warm tone) and --mode profile. Not for beating AI detectors (no edit reliably does). Not for writing from scratch (use threads-post-writer). Keywords: humanize, de-AI Threads post, audit before posting

Latest version
mdr add sergebulaev/threads-skills/threads-humanizer@git:20260905.4ce0847
Exact content
mdr add sergebulaev/threads-skills/threads-humanizer@sha256:5da2bcef3b72cca5
Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ycfixejsbn2vxnur.svg)](https://markdownregistry.com/a/art_ycfixejsbn2vxnur)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260905.4ce0847 latest2026-09-05 4ce0847 16,023 BA view · diff
git:20260730.77b93df2026-07-30 77b93df 6,240 BA view · diff
git:20260705.c753ab32026-07-05 c753ab3 5,775 BA view · diff
git:20260702.2ba1f472026-07-02 2ba1f47 4,956 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.

Source

GitHub

sergebulaev/threads-skills · 25 stars · license MIT · pushed 2026-09-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ycfixejsbn2vxnur
GET https://markdownregistry.com/api/v1/resolve?ref=sergebulaev/threads-skills/threads-humanizer
GET https://markdownregistry.com/api/v1/blob/5da2bcef3b72cca5bf7d9368f300e725b259519e9321f5335bf3e4bc17385d5e