emil-unslop-writing
100 / 100 · Low risk
Fine to try.
Strip the tells that mark prose as AI-written, then put a human voice back in. Use when drafting or reviewing any text a person will read — READMEs, docs, release notes, blog posts, commit messages, marketing copy, UI microcopy — or when the user says text "sounds like AI", "reads like ChatGPT", or wants it "de-slopped". Triggers on: slop, de-slop, unslop, AI tells, sounds like AI, reads like ChatGPT, robotic writing, humanize, rewrite this, delve, leverage, crucial, testament, landscape, tapes…
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'emil-unslop-writing' ] || [ -L ~/.agents/skills/'emil-unslop-writing' ]; then echo 'A skill folder named emil-unslop-writing already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/freekmurze/dotfiles' "$d" && git -C "$d" checkout --quiet '26bd6ac3c4ef9afd949dc1de12d96fddc2548710' -- 'config/claude/skills/emil-unslop-writing' && mkdir -p ~/.agents/skills && cp -R "$d"/'config/claude/skills/emil-unslop-writing' ~/.agents/skills/'emil-unslop-writing' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'emil-unslop-writing' ~/.claude/skills/'emil-unslop-writing' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/freekmurze/dotfiles/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-13 | 26bd6ac | 100 |