#328328th of 455 in Skills, plugins and prompts
no-ai-slop
Agent skill that edits AI writing patterns out of text while keeping your voice
- Stars
- 13.4k
- License
- MIT
- Last commit
- Sep 2026
- Last release
- Aug 2026
- Language
- Python
43 on 7 Jul 202613,420 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A skill for coding agents such as Claude Code and Codex, invoked as /no-ai-slop. It checks text against 20+ patterns, including binary contrasts, throat-clearing openers, faux-insight setups and fake-profound endings. It can rewrite the text and list its changes, or only quote the patterns it finds. The repo also ships ChatGPT/Codex plugin metadata and a Python build script.
Who it is for: Writers and developers who edit drafts with a coding agent
Strengths
- Edit mode lists every change; detect mode quotes each matched pattern without guessing authorship
- Installs with one npx command or by pasting a prompt into a coding agent
- Ships SKILL.md rules and an eval.md of checks, so the logic is readable
- Also packaged as a ChatGPT and Codex plugin
Weaknesses
- Only 10 of the 20+ patterns are listed in the README
- Needs an LLM-backed agent to run; no standalone tool or CLI
- No benchmarks or measured results on how well voice is preserved
- Targets prose editing, not code
What it needs
- no GPU
- Needs Claude Code, Codex, ChatGPT or another coding agent, Node.js (npx) for the CLI install
- Models: ChatGPT, Claude Code, Codex
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Skills, plugins and prompts
See all 455| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |