by jalaalrd · Codex Skill · ★ 544
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Featured in: Humanizer & Anti-Slop Skills
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 544 |
| Forks | 53 |
| Category | Codex Skill |
| Quality Score | 67/100 |
| Open Issues | 3 |
| Last Updated | 2026-04-18 |
| Created | 2026-03-27 |
| Platforms | claude-code, cli, codex, gemini |
| Est. Tokens | ~1k |
Anti-AI-Slop Writing Skill A Claude Code skill (and universal SKILL.md) that forces any AI to produce human-sounding text by eliminating statistically detectable AI writing patterns. What It Does Every piece of text the AI produces — tweets, emails, articles, bios, reports, copy and message passes through constraints that eliminate the vocabulary, structure, punctuation, and formatting patterns...
Looking for a anti-ai-slop-writing alternative? If you're comparing anti-ai-slop-writing with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
说人话｜中文优先的去 AI 味改写 skill：保事实、分场景、改完可直接发。Chinese-first rewrite skill for Codex / Claude Code / Cursor / ChatGPT
Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserv
AI agent skills for social media content strategy, creation, and analysis across text-first platforms
AI-writing humanizer for KO/EN/ZH/JA
Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and p
Audience-aware CLI patterns for Node.js + Commander.js. Build CLIs for humans, AI agents, or both.
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: